1 code implementation • COLING 2022 • Zhongyuan Wang, YiXuan Wang, Shaolei Wang, Wanxiang Che
Supervised methods have achieved remarkable results in disfluency detection.
1 code implementation • ACL 2022 • Libo Qin, Qiguang Chen, Tianbao Xie, Qixin Li, Jian-Guang Lou, Wanxiang Che, Min-Yen Kan
Specifically, we employ contrastive learning, leveraging bilingual dictionaries to construct multilingual views of the same utterance, then encourage their representations to be more similar than negative example pairs, which achieves to explicitly align representations of similar sentences across languages.
1 code implementation • EMNLP 2021 • Libo Qin, Tianbao Xie, Shijue Huang, Qiguang Chen, Xiao Xu, Wanxiang Che
Consistency Identification has obtained remarkable success on open-domain dialogue, which can be used for preventing inconsistent response generation.
1 code implementation • COLING 2022 • Baoxin Wang, Xingyi Duan, Dayong Wu, Wanxiang Che, Zhigang Chen, Guoping Hu
The Chinese text correction (CTC) focuses on detecting and correcting Chinese spelling errors and grammatical errors.
1 code implementation • COLING 2022 • Yuxuan Wang, Zhilin Lei, Yuqiu Ji, Wanxiang Che
Annotation conversion is an effective way to construct datasets under new annotation guidelines based on existing datasets with little human labour.
1 code implementation • COLING 2022 • Libo Qin, Qiguang Chen, Tianbao Xie, Qian Liu, Shijue Huang, Wanxiang Che, Zhou Yu
Consistency identification in task-oriented dialog (CI-ToD) usually consists of three subtasks, aiming to identify inconsistency between current system response and current user response, dialog history and the corresponding knowledge base.
no code implementations • 8 Jul 2025 • Shangzhan Li, Zefan Wang, Ye He, YuXuan Li, Qi Shi, Jianling Li, Yonggang Hu, Wanxiang Che, Xu Han, Zhiyuan Liu, Maosong Sun
Kernel development in deep learning requires optimizing computational units across hardware while balancing memory management, parallelism, and hardware-specific optimizations through extensive empirical tuning.
1 code implementation • 5 Jun 2025 • Zhiyuan Ma, Jiayu Liu, Xianzhen Luo, Zhenya Huang, Qingfu Zhu, Wanxiang Che
However, current models face two major limitations: (1) unreliable tool planning and invocation due to low-quality instruction datasets (e. g., widespread hallucinated API calls), and (2) weak tool reflection abilities (over 90% of errors cannot be corrected) resulting from static imitation learning.
1 code implementation • 30 May 2025 • Hao Chen, Yukun Yan, Sen Mei, Wanxiang Che, Zhenghao Liu, Qi Shi, Xinze Li, Yuchun Fan, Pengcheng Huang, Qiushi Xiong, Zhiyuan Liu, Maosong Sun
Retrieval-Augmented Generation (RAG) augments Large Language Models (LLMs) with external knowledge to improve factuality.
no code implementations • 24 May 2025 • YiXuan Wang, Yijun Liu, Shiyu Ji, Yuzhuang Xu, Yang Xu, Qingfu Zhu, Wanxiang Che
Using prompt-based probing, we obtain both the original and reflective distributions of draft tokens in a single forward pass.
no code implementations • 24 May 2025 • YiXuan Wang, Shiyu Ji, Yijun Liu, Yuzhuang Xu, Yang Xu, Qingfu Zhu, Wanxiang Che
By using these lookahead queries as the observation window for importance estimation, LAQ achieves more consistent and accurate KV cache eviction aligned with real inference scenarios.
no code implementations • 21 May 2025 • Zihui Cheng, Qiguang Chen, Xiao Xu, Jiaqi Wang, Weiyun Wang, Hao Fei, Yidong Wang, Alex Jinpeng Wang, Zhi Chen, Wanxiang Che, Libo Qin
Additionally, we explore the internal nature of visual thoughts, finding that visual thoughts serve as intermediaries between the input image and reasoning to deeper transformer layers, enabling more advanced visual information transmission.
no code implementations • 21 May 2025 • Weixiang Zhao, Jiahe Guo, Yang Deng, Tongtong Wu, Wenxuan Zhang, Yulin Hu, Xingyu Sui, Yanyan Zhao, Wanxiang Che, Bing Qin, Tat-Seng Chua, Ting Liu
Multilingual reasoning remains a significant challenge for large language models (LLMs), with performance disproportionately favoring high-resource languages.
no code implementations • 21 May 2025 • Xuanliang Zhang, Dingzirui Wang, Keyan Xu, Qingfu Zhu, Wanxiang Che
Recently, reasoning large language models (RLLMs) with Long Chain-of-Thought (Long CoT) significantly enhance reasoning capabilities, leading to brilliant performance on table reasoning.
1 code implementation • 20 May 2025 • Xianzhen Luo, Qingfu Zhu, Zhiming Zhang, Mingzheng Xu, Tianhao Cheng, YiXuan Wang, Zheng Chu, Shijie Xuyang, Zhiyuan Ma, Yuantao Fan, Wanxiang Che
Code Sensitivity refers to the ability of Code LLMs to recognize and respond to details changes in problem descriptions.
2 code implementations • 19 May 2025 • Qiguang Chen, Libo Qin, Jinhao Liu, Yue Liao, Jiaqi Wang, Jingxuan Zhou, Wanxiang Che
However, two primary challenges remain for real-world applications: (1) the lack of quantitative metrics and actionable guidelines for evaluating and optimizing measurable boundaries of CoT capability, and (2) the absence of methods to assess boundaries of unmeasurable CoT capability, such as multimodal perception.
no code implementations • 16 May 2025 • Xianzhen Luo, Shijie Xuyang, Tianhao Cheng, Zheng Chu, Houyi Li, Ziqi Wang, Siming Huang, Qingfu Zhu, Qiufeng Wang, Xiangyu Zhang, Shuigeng Zhou, Wanxiang Che
Understanding the relationship between data compression and the capabilities of Large Language Models (LLMs) is crucial, especially in specialized domains like code intelligence.
no code implementations • 4 Apr 2025 • Bingxiang He, Wenbin Zhang, Jiaxi Song, Cheng Qian, Zixuan Fu, Bowen Sun, Ning Ding, Haiwen Hong, Longtao Huang, Hui Xue, Ganqu Cui, Wanxiang Che, Zhiyuan Liu, Maosong Sun
Preference learning is critical for aligning large language models (LLMs) with human values, yet its success hinges on high-quality datasets comprising three core components: Preference \textbf{A}nnotations, \textbf{I}nstructions, and \textbf{R}esponse Pairs.
1 code implementation • 23 Mar 2025 • Weixiang Zhao, Xingyu Sui, Jiahe Guo, Yulin Hu, Yang Deng, Yanyan Zhao, Bing Qin, Wanxiang Che, Tat-Seng Chua, Ting Liu
Recent advancements in Large Reasoning Models (LRMs), such as OpenAI's o1/o3 and DeepSeek-R1, have demonstrated remarkable performance in specialized reasoning tasks through human-like deliberative thinking and long chain-of-thought reasoning.
1 code implementation • 10 Mar 2025 • Xiaoming Shi, Zeming Liu, Yiming Lei, Chenkai Zhang, Haitao Leng, Chuan Wang, Qingjie Liu, Wanxiang Che, Shaoguo Liu, Size Li, Yunhong Wang
To mitigate this challenge, we propose a novel task and create a human-to-human video-driven multilingual mixed-type dialogue corpus, termed KwaiChat, containing a total of 93, 209 videos and 246, 080 dialogues, across 4 dialogue types, 30 domains, 4 languages, and 13 topics.
1 code implementation • 24 Feb 2025 • Xuanliang Zhang, Dingzirui Wang, Keyan Xu, Qingfu Zhu, Wanxiang Che
To align the model TATQA capabilities in English with other languages, we develop a baseline, Ours.
1 code implementation • 11 Jan 2025 • Xuanle Zhao, Xianzhen Luo, Qi Shi, Chi Chen, Shuo Wang, Wanxiang Che, Zhiyuan Liu, Maosong Sun
: (1) Low executability and poor restoration of chart details in the generated code and (2) Lack of large-scale and diverse training data.
1 code implementation • 17 Dec 2024 • Bohan Li, Jiannan Guan, Longxu Dou, Yunlong Feng, Dingzirui Wang, Yang Xu, Enbo Wang, Qiguang Chen, Bichen Wang, Xiao Xu, Yimeng Zhang, Libo Qin, Yanyan Zhao, Qingfu Zhu, Wanxiang Che
In this paper, we optimize the task by constructing MBTIBench, the first manually annotated high-quality MBTI personality detection dataset with soft labels, under the guidance of psychologists.
1 code implementation • 17 Dec 2024 • Zihui Cheng, Qiguang Chen, Jin Zhang, Hao Fei, Xiaocheng Feng, Wanxiang Che, Min Li, Libo Qin
Large Vision-Language Models (LVLMs) have recently demonstrated amazing success in multi-modal tasks, including advancements in Multi-modal Chain-of-Thought (MCoT) reasoning.
1 code implementation • 16 Dec 2024 • Xuanliang Zhang, Dingzirui Wang, Baoxin Wang, Longxu Dou, Xinyuan Lu, Keyan Xu, Dayong Wu, Qingfu Zhu, Wanxiang Che
To address these challenges, we propose a QA benchmark for scientific tables and text with diverse reasoning types (SciTaT).
no code implementations • 12 Dec 2024 • Yuzhuang Xu, Shiyu Ji, Qingfu Zhu, Wanxiang Che
Powerful large language models (LLMs) are increasingly expected to be deployed with lower computational costs, enabling their capabilities on resource-constrained devices.
no code implementations • 8 Dec 2024 • Xiao Xu, Tianhao Niu, Yuxi Xie, Libo Qin, Wanxiang Che, Min-Yen Kan
Multimodal Large Language Models (MLLMs) excel in vision--language tasks by pre-training solely on coarse-grained concept annotations (e. g., image captions).
no code implementations • 28 Oct 2024 • Honglin Mu, Han He, Yuxin Zhou, Yunlong Feng, Yang Xu, Libo Qin, Xiaoming Shi, Zeming Liu, Xudong Han, Qi Shi, Qingfu Zhu, Wanxiang Che
Existing black-box jailbreak methods often rely on model feedback, repeatedly submitting queries with detectable malicious instructions during the attack search process.
no code implementations • 27 Oct 2024 • Libo Qin, Qiguang Chen, Hao Fei, Zhi Chen, Min Li, Wanxiang Che
Recently, rapid advancements in Multi-Modal In-Context Learning (MM-ICL) have achieved notable success, which is capable of achieving superior performance across various tasks without requiring additional parameter tuning.
1 code implementation • 8 Oct 2024 • Qiguang Chen, Libo Qin, Jiaqi Wang, Jinxuan Zhou, Wanxiang Che
Chain-of-Thought (CoT) reasoning has emerged as a promising approach for enhancing the performance of large language models (LLMs) on complex reasoning tasks.
no code implementations • 6 Oct 2024 • Weixiang Zhao, Yulin Hu, Jiahe Guo, Xingyu Sui, Tongtong Wu, Yang Deng, Yanyan Zhao, Bing Qin, Wanxiang Che, Ting Liu
Despite the growing global demand for large language models (LLMs) that serve users from diverse linguistic backgrounds, most cutting-edge LLMs remain predominantly English-centric.
1 code implementation • 2 Oct 2024 • Dingzirui Wang, Xuanliang Zhang, Qiguang Chen, Longxu Dou, Xiao Xu, Rongyu Cao, Yingwei Ma, Qingfu Zhu, Wanxiang Che, Binhua Li, Fei Huang, Yongbin Li
To address this, inspired by transfer learning, we propose In-Context Transfer Learning (ICTL), which synthesizes target task demonstrations by transferring labeled demonstrations from similar source tasks.
no code implementations • 18 Sep 2024 • Wang Xu, Shuo Wang, Weilin Zhao, Xu Han, Yukun Yan, Yudi Zhang, Zhe Tao, Zhiyuan Liu, Wanxiang Che
To address this limitation, researchers have proposed duplex models.
1 code implementation • 3 Sep 2024 • Zhi Chen, Qiguang Chen, Libo Qin, Qipeng Guo, Haijun Lv, Yicheng Zou, Wanxiang Che, Hang Yan, Kai Chen, Dahua Lin
In order to achieve success in long context tasks, a large amount of work has been done to enhance the long context capabilities of the model through synthetic data.
1 code implementation • 16 Aug 2024 • Dingzirui Wang, Longxu Dou, Xuanliang Zhang, Qingfu Zhu, Wanxiang Che
Therefore, in this paper, we propose to employ the decomposed correction to enhance text-to-SQL performance.
1 code implementation • 16 Aug 2024 • Xuanliang Zhang, Dingzirui Wang, Longxu Dou, Baoxin Wang, Dayong Wu, Qingfu Zhu, Wanxiang Che
Most existing methods employ a fixed tabular format to represent the table, which could limit the performance.
no code implementations • 2 Jul 2024 • Yang Xu, Yunlong Feng, Honglin Mu, Yutai Hou, Yitong Li, Xinghao Wang, Wanjun Zhong, Zhongyang Li, Dandan Tu, Qingfu Zhu, Min Zhang, Wanxiang Che
However, when compressing tool documentation, existing methods suffer from the weaknesses of key information loss (specifically, tool/parameter name errors) and difficulty in adjusting the length of compressed sequences based on documentation lengths.
1 code implementation • 1 Jul 2024 • Yuxuan Wang, Yijun Liu, Fei Yu, Chen Huang, Kexin Li, Zhiguo Wan, Wanxiang Che
Our in-depth category-level analysis reveals a lack of Chinese cultural knowledge in existing VLMs.
1 code implementation • 25 Jun 2024 • YiXuan Wang, Baoxin Wang, Yijun Liu, Qingfu Zhu, Dayong Wu, Wanxiang Che
Nowadays, data augmentation through synthetic data has been widely used in the field of Grammatical Error Correction (GEC) to alleviate the problem of data scarcity.
1 code implementation • 25 Jun 2024 • YiXuan Wang, Xianzhen Luo, Fuxuan Wei, Yijun Liu, Qingfu Zhu, Xuanyu Zhang, Qing Yang, Dongliang Xu, Wanxiang Che
To address this problem, we propose the Make Some Noise (MSN) training framework as a replacement for the supervised fine-tuning stage of the large language model.
1 code implementation • 25 Jun 2024 • Yunlong Feng, Dechuan Teng, Yang Xu, Honglin Mu, Xiao Xu, Libo Qin, Qingfu Zhu, Wanxiang Che
Decompilation transforms compiled code back into a high-level programming language for analysis when source code is unavailable.
1 code implementation • 20 Jun 2024 • Yongheng Zhang, Qiguang Chen, Min Li, Wanxiang Che, Libo Qin
Cross-lingual chain-of-thought can effectively complete reasoning tasks across languages, which gains increasing attention.
no code implementations • 15 Jun 2024 • Libo Qin, Fuxuan Wei, Qiguang Chen, Jingxuan Zhou, Shijue Huang, Jiasheng Si, Wenpeng Lu, Wanxiang Che
To solve this problem, we present the pioneering work of Cross-task Interactive Prompting (CroPrompt) for SLU, which enables the model to interactively leverage the information exchange across the correlated tasks in SLU.
no code implementations • 12 Jun 2024 • Hao Yang, Yanyan Zhao, Yang Wu, Shilong Wang, Tian Zheng, Hongbo Zhang, Zongyang Ma, Wanxiang Che, Bing Qin
Compared to traditional sentiment analysis, which only considers text, multimodal sentiment analysis needs to consider emotional signals from multimodal sources simultaneously and is therefore more consistent with the way how humans process sentiment in real-world scenarios.
1 code implementation • 26 May 2024 • Qiguang Chen, Libo Qin, Jin Zhang, Zhi Chen, Xiao Xu, Wanxiang Che
In addition, we highlight that the current VLLMs still struggle to correctly reason in M$^3$CoT and there remains a large gap between existing VLLMs and human performance in M$^3$CoT, despite their superior results on previous MCoT benchmarks.
1 code implementation • 21 May 2024 • Libo Qin, Qiguang Chen, Xiachong Feng, Yang Wu, Yongheng Zhang, Yinghui Li, Min Li, Wanxiang Che, Philip S. Yu
While large language models (LLMs) like ChatGPT have shown impressive capabilities in Natural Language Processing (NLP) tasks, a systematic investigation of their potential in this field remains largely unexplored.
no code implementations • 10 Apr 2024 • Yunlong Feng, Yang Xu, Libo Qin, Yasheng Wang, Wanxiang Che
The framework motivates the model itself to automatically generate rationales on existing datasets.
no code implementations • 7 Apr 2024 • Libo Qin, Qiguang Chen, YuHang Zhou, Zhi Chen, Yinghui Li, Lizi Liao, Min Li, Wanxiang Che, Philip S. Yu
To this end, in this paper, we present a thorough review and provide a unified perspective to summarize the recent progress as well as emerging trends in multilingual large language models (MLLMs) literature.
1 code implementation • 31 Mar 2024 • Lizhi Lin, Honglin Mu, Zenan Zhai, Minghan Wang, Yuxia Wang, Renxi Wang, Junjie Gao, Yixuan Zhang, Wanxiang Che, Timothy Baldwin, Xudong Han, Haonan Li
Generative models are rapidly gaining popularity and being integrated into everyday applications, raising concerns over their safe use as various vulnerabilities are exposed.
1 code implementation • 26 Mar 2024 • YiXuan Wang, Baoxin Wang, Yijun Liu, Dayong Wu, Wanxiang Che
In this light, we propose the LM-Combiner, a rewriting model that can directly modify the over-correction of GEC system outputs without a model ensemble.
1 code implementation • 17 Mar 2024 • Honglin Mu, Yang Xu, Yunlong Feng, Xiaofeng Han, Yitong Li, Yutai Hou, Wanxiang Che
With the rise of Large Language Models (LLMs), AI assistants' ability to utilize tools, especially through API calls, has advanced notably.
no code implementations • 1 Mar 2024 • Xianzhen Luo, Qingfu Zhu, Zhiming Zhang, Xu Wang, Qing Yang, Dongliang Xu, Wanxiang Che
Presently, two dominant paradigms for collecting tuning data are natural-instruct (human-written) and self-instruct (automatically generated).
1 code implementation • 17 Feb 2024 • Yuzhuang Xu, Xu Han, Zonghan Yang, Shuo Wang, Qingfu Zhu, Zhiyuan Liu, Weidong Liu, Wanxiang Che
Model quantification uses low bit-width values to represent the weight matrices of existing models to be quantized, which is a promising approach to reduce both storage and computational overheads of deploying highly anticipated LLMs.
1 code implementation • 16 Feb 2024 • Xianzhen Luo, Qingfu Zhu, Zhiming Zhang, Libo Qin, Xuanyu Zhang, Qing Yang, Dongliang Xu, Wanxiang Che
In this paper, we conduct comprehensive experiments on the programming languages used in PoT and find that no single language consistently delivers optimal performance across all tasks and models.
no code implementations • 16 Feb 2024 • Qi Shi, Han Cui, Haofeng Wang, Qingfu Zhu, Wanxiang Che, Ting Liu
Question answering over heterogeneous data requires reasoning over diverse sources of data, which is challenging due to the large scale of information and organic coupling of heterogeneous data.
1 code implementation • 16 Feb 2024 • Xuanliang Zhang, Dingzirui Wang, Longxu Dou, Qingfu Zhu, Wanxiang Che
The open-domain text-to-SQL task aims to retrieve question-relevant tables from massive databases and generate SQL.
no code implementations • 16 Feb 2024 • Dingzirui Wang, Longxu Dou, Xuanliang Zhang, Qingfu Zhu, Wanxiang Che
Numerical reasoning is an essential ability for NLP systems to handle numeric information.
1 code implementation • 16 Feb 2024 • Dingzirui Wang, Longxu Dou, Xuanliang Zhang, Qingfu Zhu, Wanxiang Che
Currently, the in-context learning method based on large language models (LLMs) has become the mainstream of text-to-SQL research.
1 code implementation • 13 Feb 2024 • Xuanliang Zhang, Dingzirui Wang, Longxu Dou, Qingfu Zhu, Wanxiang Che
In this paper, we analyze the mainstream techniques used to improve table reasoning performance in the LLM era, and the advantages of LLMs compared to pre-LLMs for solving table reasoning.
1 code implementation • 6 Feb 2024 • Dechuan Teng, Chunlin Lu, Xiao Xu, Wanxiang Che, Libo Qin
Recently, Profile-based Spoken Language Understanding (SLU) has gained increasing attention, which aims to incorporate various types of supplementary profile information (i. e., Knowledge Graph, User Profile, Context Awareness) to eliminate the prevalent ambiguities in user utterances.
no code implementations • 16 Jan 2024 • Weixiang Zhao, Shilong Wang, Yulin Hu, Yanyan Zhao, Bing Qin, Xuanyu Zhang, Qing Yang, Dongliang Xu, Wanxiang Che
Existing methods devise the learning module to acquire task-specific knowledge with parameter-efficient tuning (PET) block and the selection module to pick out the corresponding one for the testing input, aiming at handling the challenges of catastrophic forgetting and knowledge transfer in CL.
no code implementations • 15 Nov 2023 • Libo Qin, Wenbo Pan, Qiguang Chen, Lizi Liao, Zhou Yu, Yue Zhang, Wanxiang Che, Min Li
End-to-end task-oriented dialogue (EToD) can directly generate responses in an end-to-end fashion without modular training, which attracts escalating popularity.
1 code implementation • 23 Oct 2023 • Libo Qin, Qiguang Chen, Fuxuan Wei, Shijue Huang, Wanxiang Che
The cross-lingual alignment prompting is responsible for aligning representations across different languages, whereas the task-specific solver prompting is used to generate the final chain of thoughts and results for the reasoning task.
1 code implementation • 23 Oct 2023 • Yuanxing Liu, Wei-Nan Zhang, Yifan Chen, Yuchi Zhang, Haopeng Bai, Fan Feng, Hengbin Cui, Yongbin Li, Wanxiang Che
This paper investigates the effectiveness of combining LLM and CRS in E-commerce pre-sales dialogues, proposing two collaboration methods: CRS assisting LLM and LLM assisting CRS.
1 code implementation • 21 Aug 2023 • Dingzirui Wang, Longxu Dou, Wenbin Zhang, Junyu Zeng, Wanxiang Che
So in this paper, we try to use equations as IMRs to solve the numerical reasoning task by addressing two problems: (1) Theoretically, how to prove that the equation is an IMR with higher generation accuracy than programs; (2) Empirically, how to improve the generation accuracy of equations with LLMs.
1 code implementation • 14 Jul 2023 • Libo Qin, Shijue Huang, Qiguang Chen, Chenran Cai, Yudi Zhang, Bin Liang, Wanxiang Che, Ruifeng Xu
Multi-modal sarcasm detection has attracted much recent attention.
1 code implementation • 15 Jun 2023 • Hongyuan Dong, Weinan Zhang, Wanxiang Che
Despite the promising prospects, the performance of prompting model largely depends on the design of prompt template and verbalizer.
no code implementations • 5 Jun 2023 • Wenwen Yu, Chengquan Zhang, Haoyu Cao, Wei Hua, Bohan Li, Huang Chen, MingYu Liu, Mingrui Chen, Jianfeng Kuang, Mengjun Cheng, Yuning Du, Shikun Feng, Xiaoguang Hu, Pengyuan Lyu, Kun Yao, Yuechen Yu, Yuliang Liu, Wanxiang Che, Errui Ding, Cheng-Lin Liu, Jiebo Luo, Shuicheng Yan, Min Zhang, Dimosthenis Karatzas, Xing Sun, Jingdong Wang, Xiang Bai
It is hoped that this competition will attract many researchers in the field of CV and NLP, and bring some new thoughts to the field of Document AI.
1 code implementation • 31 May 2023 • Xiao Xu, Bei Li, Chenfei Wu, Shao-Yen Tseng, Anahita Bhiwandiwalla, Shachar Rosenman, Vasudev Lal, Wanxiang Che, Nan Duan
With only 4M VLP data, ManagerTower achieves superior performances on various downstream VL tasks, especially 79. 15% accuracy on VQAv2 Test-Std, 86. 56% IR@1 and 95. 64% TR@1 on Flickr30K.
1 code implementation • 17 May 2023 • Libo Qin, Qiguang Chen, Xiao Xu, Yunlong Feng, Wanxiang Che
Spoken Language Understanding (SLU) is one of the core components of a task-oriented dialogue system, which aims to extract the semantic meaning of user queries (e. g., intents and slots).
no code implementations • 9 May 2023 • Bo Sun, Baoxin Wang, YiXuan Wang, Wanxiang Che, Dayong Wu, Shijin Wang, Ting Liu
Our experiments show that powerful pre-trained models perform poorly on this corpus.
no code implementations • 5 May 2023 • Yuanxing Liu, Weinan Zhang, Baohua Dong, Yan Fan, Hang Wang, Fan Feng, Yifan Chen, Ziyu Zhuang, Hengbin Cui, Yongbin Li, Wanxiang Che
In this paper, we construct a user needs-centric E-commerce conversational recommendation dataset (U-NEED) from real-world E-commerce scenarios.
no code implementations • 27 Apr 2023 • Dingzirui Wang, Longxu Dou, Wanxiang Che
In this paper, we introduce ConDA, which generates interactive questions and corresponding SQL results.
no code implementations • 19 Apr 2023 • Bohan Li, Longxu Dou, Yutai Hou, Yunlong Feng, Honglin Mu, Qingfu Zhu, Qinghua Sun, Wanxiang Che
Prompt-based learning has shown considerable promise in reformulating various downstream tasks as cloze problems by combining original input with a predetermined template.
no code implementations • 18 Apr 2023 • Yunlong Feng, Bohan Li, Libo Qin, Xiao Xu, Wanxiang Che
Cross-domain text classification aims to adapt models to a target domain that lacks labeled data.
no code implementations • 9 Apr 2023 • Wenbo Pan, Qiguang Chen, Xiao Xu, Wanxiang Che, Libo Qin
Zero-shot dialogue understanding aims to enable dialogue to track the user's needs without any training data, which has gained increasing attention.
no code implementations • 4 Feb 2023 • Bohan Li, Xiao Xu, Xinghao Wang, Yutai Hou, Yunlong Feng, Feng Wang, Xuanliang Zhang, Qingfu Zhu, Wanxiang Che
In contrast, generative methods bring more image diversity in the augmented images but may not preserve semantic consistency, thus incorrectly changing the essential semantics of the original image.
no code implementations • 5 Jan 2023 • Bo Zheng, Zhouyang Li, Fuxuan Wei, Qiguang Chen, Libo Qin, Wanxiang Che
Multilingual spoken language understanding (SLU) consists of two sub-tasks, namely intent detection and slot filling.
1 code implementation • 3 Jan 2023 • Longxu Dou, Yan Gao, Xuqi Liu, Mingyang Pan, Dingzirui Wang, Wanxiang Che, Dechen Zhan, Min-Yen Kan, Jian-Guang Lou
In this paper, we study the problem of knowledge-intensive text-to-SQL, in which domain knowledge is necessary to parse expert questions into SQL queries over domain-specific tables.
1 code implementation • 27 Dec 2022 • Longxu Dou, Yan Gao, Mingyang Pan, Dingzirui Wang, Wanxiang Che, Dechen Zhan, Jian-Guang Lou
Text-to-SQL semantic parsing is an important NLP task, which greatly facilitates the interaction between users and the database and becomes the key component in many human-computer interaction systems.
no code implementations • 27 Dec 2022 • Dingzirui Wang, Longxu Dou, Wanxiang Che
Table-and-text hybrid question answering (HybridQA) is a widely used and challenging NLP task commonly applied in the financial and scientific domain.
no code implementations • 12 Dec 2022 • Qingfu Zhu, Xianzhen Luo, Fang Liu, Cuiyun Gao, Wanxiang Che
Natural language processing for programming aims to use NLP techniques to assist programming.
1 code implementation • 10 Nov 2022 • Yiming Cui, Wanxiang Che, Shijin Wang, Ting Liu
We propose LERT, a pre-trained language model that is trained on three types of linguistic features along with the original MLM pre-training task, using a linguistically-informed pre-training (LIP) strategy.
Ranked #6 on
Stock Market Prediction
on Astock
1 code implementation • COLING 2022 • Yutai Hou, Hongyuan Dong, Xinghao Wang, Bohan Li, Wanxiang Che
Prompting method is regarded as one of the crucial progress for few-shot nature language processing.
1 code implementation • 11 Aug 2022 • Honghong Zhao, Baoxin Wang, Dayong Wu, Wanxiang Che, Zhigang Chen, Shijin Wang
In this paper, we present an overview of the CTC 2021, a Chinese text correction task for native speakers.
2 code implementations • 17 Jun 2022 • Xiao Xu, Chenfei Wu, Shachar Rosenman, Vasudev Lal, Wanxiang Che, Nan Duan
Vision-Language (VL) models with the Two-Tower architecture have dominated visual-language representation learning in recent years.
1 code implementation • 25 May 2022 • Yang Xu, Yutai Hou, Wanxiang Che, Min Zhang
On the newly defined cross-lingual model editing task, we empirically demonstrate the failure of monolingual baselines in propagating the edit to multiple languages and the effectiveness of the proposed language anisotropic model editing.
1 code implementation • 18 Apr 2022 • Libo Qin, Qiguang Chen, Tianbao Xie, Qixin Li, Jian-Guang Lou, Wanxiang Che, Min-Yen Kan
We present Global--Local Contrastive Learning Framework (GL-CLeF) to address this shortcoming.
no code implementations • 15 Apr 2022 • Bo Sun, Baoxin Wang, Wanxiang Che, Dayong Wu, Zhigang Chen, Ting Liu
These errors have been studied extensively and are relatively simple for humans.
1 code implementation • Findings (ACL) 2022 • Yutai Hou, Cheng Chen, Xianzhen Luo, Bohan Li, Wanxiang Che
Such inverse prompting only requires a one-turn prediction for each slot type and greatly speeds up the prediction.
1 code implementation • 15 Mar 2022 • Longxu Dou, Yan Gao, Mingyang Pan, Dingzirui Wang, Wanxiang Che, Dechen Zhan, Jian-Guang Lou
Existing text-to-SQL semantic parsers are typically designed for particular settings such as handling queries that span multiple tables, domains or turns which makes them ineffective when applied to different settings.
no code implementations • 10 Feb 2022 • Baoxin Wang, Qingye Meng, Ziyue Wang, Honghong Zhao, Dayong Wu, Wanxiang Che, Shijin Wang, Zhigang Chen, Cong Liu
Knowledge graph embedding (KGE) models learn the representation of entities and relations in knowledge graphs.
Ranked #4 on
Link Property Prediction
on ogbl-wikikg2
1 code implementation • 20 Jan 2022 • Zhen Yu, Xiaosen Wang, Wanxiang Che, Kun He
Existing textual adversarial attacks usually utilize the gradient or prediction confidence to generate adversarial examples, making it hard to be deployed in real-world applications.
1 code implementation • 22 Dec 2021 • Xiao Xu, Libo Qin, Kaiji Chen, Guoxing Wu, Linlin Li, Wanxiang Che
Current researches on spoken language understanding (SLU) heavily are limited to a simple setting: the plain text-based SLU that takes the user utterance as input and generates its corresponding semantic frames (e. g., intent and slots).
Ranked #1 on
Semantic Frame Parsing
on ProSLU
2 code implementations • 6 Dec 2021 • Kaustubh D. Dhole, Varun Gangal, Sebastian Gehrmann, Aadesh Gupta, Zhenhao Li, Saad Mahamood, Abinaya Mahendiran, Simon Mille, Ashish Shrivastava, Samson Tan, Tongshuang Wu, Jascha Sohl-Dickstein, Jinho D. Choi, Eduard Hovy, Ondrej Dusek, Sebastian Ruder, Sajant Anand, Nagender Aneja, Rabin Banjade, Lisa Barthe, Hanna Behnke, Ian Berlot-Attwell, Connor Boyle, Caroline Brun, Marco Antonio Sobrevilla Cabezudo, Samuel Cahyawijaya, Emile Chapuis, Wanxiang Che, Mukund Choudhary, Christian Clauss, Pierre Colombo, Filip Cornell, Gautier Dagan, Mayukh Das, Tanay Dixit, Thomas Dopierre, Paul-Alexis Dray, Suchitra Dubey, Tatiana Ekeinhor, Marco Di Giovanni, Tanya Goyal, Rishabh Gupta, Louanes Hamla, Sang Han, Fabrice Harel-Canada, Antoine Honore, Ishan Jindal, Przemyslaw K. Joniak, Denis Kleyko, Venelin Kovatchev, Kalpesh Krishna, Ashutosh Kumar, Stefan Langer, Seungjae Ryan Lee, Corey James Levinson, Hualou Liang, Kaizhao Liang, Zhexiong Liu, Andrey Lukyanenko, Vukosi Marivate, Gerard de Melo, Simon Meoni, Maxime Meyer, Afnan Mir, Nafise Sadat Moosavi, Niklas Muennighoff, Timothy Sum Hon Mun, Kenton Murray, Marcin Namysl, Maria Obedkova, Priti Oli, Nivranshu Pasricha, Jan Pfister, Richard Plant, Vinay Prabhu, Vasile Pais, Libo Qin, Shahab Raji, Pawan Kumar Rajpoot, Vikas Raunak, Roy Rinberg, Nicolas Roberts, Juan Diego Rodriguez, Claude Roux, Vasconcellos P. H. S., Ananya B. Sai, Robin M. Schmidt, Thomas Scialom, Tshephisho Sefara, Saqib N. Shamsi, Xudong Shen, Haoyue Shi, Yiwen Shi, Anna Shvets, Nick Siegel, Damien Sileo, Jamie Simon, Chandan Singh, Roman Sitelew, Priyank Soni, Taylor Sorensen, William Soto, Aman Srivastava, KV Aditya Srivatsa, Tony Sun, Mukund Varma T, A Tabassum, Fiona Anting Tan, Ryan Teehan, Mo Tiwari, Marie Tolkiehn, Athena Wang, Zijian Wang, Gloria Wang, Zijie J. Wang, Fuxuan Wei, Bryan Wilie, Genta Indra Winata, Xinyi Wu, Witold Wydmański, Tianbao Xie, Usama Yaseen, Michael A. Yee, Jing Zhang, Yue Zhang
Data augmentation is an important component in the robustness evaluation of models in natural language processing (NLP) and in enhancing the diversity of the data they are trained on.
1 code implementation • 5 Oct 2021 • Bohan Li, Yutai Hou, Wanxiang Che
One of the main focuses of the DA methods is to improve the diversity of training data, thereby helping the model to better generalize to unseen testing data.
no code implementations • 27 Sep 2021 • Yutai Hou, Yingce Xia, Lijun Wu, Shufang Xie, Yang Fan, Jinhua Zhu, Wanxiang Che, Tao Qin, Tie-Yan Liu
We regard the DTI triplets as a sequence and use a Transformer-based model to directly generate them without using the detailed annotations of entities and relations.
1 code implementation • 23 Sep 2021 • Libo Qin, Tianbao Xie, Shijue Huang, Qiguang Chen, Xiao Xu, Wanxiang Che
Consistency Identification has obtained remarkable success on open-domain dialogue, which can be used for preventing inconsistent response generation.
1 code implementation • EMNLP 2021 • Zeming Liu, Haifeng Wang, Zheng-Yu Niu, Hua Wu, Wanxiang Che
In this paper, we provide a bilingual parallel human-to-human recommendation dialog dataset (DuRecDial 2. 0) to enable researchers to explore a challenging task of multilingual and cross-lingual conversational recommendation.
2 code implementations • EMNLP 2021 • Bo Zheng, Li Dong, Shaohan Huang, Saksham Singhal, Wanxiang Che, Ting Liu, Xia Song, Furu Wei
We find that many languages are under-represented in recent cross-lingual language models due to the limited vocabulary capacity.
1 code implementation • 26 Aug 2021 • Yiming Cui, Wei-Nan Zhang, Wanxiang Che, Ting Liu, Zhigang Chen, Shijin Wang
Achieving human-level performance on some of the Machine Reading Comprehension (MRC) datasets is no longer challenging with the help of powerful Pre-trained Language Models (PLMs).
no code implementations • ACL 2021 • Jun Xu, Zeyang Lei, Haifeng Wang, Zheng-Yu Niu, Hua Wu, Wanxiang Che
Learning discrete dialog structure graph from human-human dialogs yields basic insights into the structure of conversation, and also provides background knowledge to facilitate dialog generation.
1 code implementation • ACL 2021 • Bo Zheng, Li Dong, Shaohan Huang, Wenhui Wang, Zewen Chi, Saksham Singhal, Wanxiang Che, Ting Liu, Xia Song, Furu Wei
Fine-tuning pre-trained cross-lingual language models can transfer task-specific supervision from one language to the others.
no code implementations • Joint Conference on Lexical and Computational Semantics 2021 • Ziqing Yang, Yiming Cui, Chenglei Si, Wanxiang Che, Ting Liu, Shijin Wang, Guoping Hu
Adversarial training (AT) as a regularization method has proved its effectiveness on various tasks.
1 code implementation • EMNLP (MRQA) 2021 • Ziqing Yang, Wentao Ma, Yiming Cui, Jiani Ye, Wanxiang Che, Shijin Wang
Multilingual pre-trained models have achieved remarkable performance on cross-lingual transfer learning.
1 code implementation • ACL 2021 • Libo Qin, Fuxuan Wei, Tianbao Xie, Xiao Xu, Wanxiang Che, Ting Liu
Multi-intent SLU can handle multiple intents in an utterance, which has attracted increasing attention.
Ranked #10 on
Slot Filling
on MixATIS
no code implementations • Findings (ACL) 2021 • Yutai Hou, Yongkui Lai, Cheng Chen, Wanxiang Che, Ting Liu
However, dialogue language understanding contains two closely related tasks, i. e., intent detection and slot filling, and often benefits from jointly learning the two tasks.
1 code implementation • 10 May 2021 • Yiming Cui, Ting Liu, Wanxiang Che, Zhigang Chen, Shijin Wang
Achieving human-level performance on some of Machine Reading Comprehension (MRC) datasets is no longer challenging with the help of powerful Pre-trained Language Models (PLMs).
Ranked #1 on
Multi-Choice MRC
on ExpMRC - RACE+ (test)
1 code implementation • 4 Mar 2021 • Libo Qin, Tianbao Xie, Wanxiang Che, Ting Liu
Spoken Language Understanding (SLU) aims to extract the semantics frame of user queries, which is a core component in a task-oriented dialog system.
no code implementations • 31 Dec 2020 • Jun Xu, Zeyang Lei, Haifeng Wang, Zheng-Yu Niu, Hua Wu, Wanxiang Che, Ting Liu
Learning interpretable dialog structure from human-human dialogs yields basic insights into the structure of conversation, and also provides background knowledge to facilitate dialog generation.
8 code implementations • ACL 2021 • Yang Xu, Yiheng Xu, Tengchao Lv, Lei Cui, Furu Wei, Guoxin Wang, Yijuan Lu, Dinei Florencio, Cha Zhang, Wanxiang Che, Min Zhang, Lidong Zhou
Pre-training of text and layout has proved effective in a variety of visually-rich document understanding tasks due to its effective model architecture and the advantage of large-scale unlabeled scanned/digital-born documents.
Ranked #1 on
Key Information Extraction
on SROIE
1 code implementation • 24 Dec 2020 • Libo Qin, Zhouyang Li, Wanxiang Che, Minheng Ni, Ting Liu
The dialog context information (contextual information) and the mutual interaction information are two key factors that contribute to the two related tasks.
1 code implementation • 13 Dec 2020 • Yutai Hou, Sanyuan Chen, Wanxiang Che, Cheng Chen, Ting Liu
Slot filling, a fundamental module of spoken language understanding, often suffers from insufficient quantity and diversity of training data.
no code implementations • CONLL 2020 • Longxu Dou, Yunlong Feng, Yuqiu Ji, Wanxiang Che, Ting Liu
This paper describes our submission system (HIT-SCIR) for the CoNLL 2020 shared task: Cross-Framework and Cross-Lingual Meaning Representation Parsing.
1 code implementation • EMNLP 2020 • Shaolei Wang, Zhongyuan Wang, Wanxiang Che, Ting Liu
Most existing approaches to disfluency detection heavily rely on human-annotated corpora, which is expensive to obtain in practice.
no code implementations • 11 Oct 2020 • Yutai Hou, Yongkui Lai, Yushan Wu, Wanxiang Che, Ting Liu
In this paper, we study the few-shot multi-label classification for user intent detection.
1 code implementation • 8 Oct 2020 • Libo Qin, Tailu Liu, Wanxiang Che, Bingbing Kang, Sendong Zhao, Ting Liu
Instead of adopting the self-attention mechanism in vanilla Transformer, we propose a co-interactive module to consider the cross-impact by building a bidirectional connection between the two related tasks.
1 code implementation • 8 Oct 2020 • Dechuan Teng, Libo Qin, Wanxiang Che, Sendong Zhao, Ting Liu
In this paper, we improve Chinese spoken language understanding (SLU) by injecting word information.
no code implementations • 1 Oct 2020 • Shaolei Wang, Baoxin Wang, Jiefu Gong, Zhongyuan Wang, Xiao Hu, Xingyi Duan, Zizhuo Shen, Gang Yue, Ruiji Fu, Dayong Wu, Wanxiang Che, Shijin Wang, Guoping Hu, Ting Liu
Grammatical error diagnosis is an important task in natural language processing.
1 code implementation • EMNLP (ACL) 2021 • Wanxiang Che, Yunlong Feng, Libo Qin, Ting Liu
We introduce \texttt{N-LTP}, an open-source neural language technology platform supporting six fundamental Chinese NLP tasks: {lexical analysis} (Chinese word segmentation, part-of-speech tagging, and named entity recognition), {syntactic parsing} (dependency parsing), and {semantic parsing} (semantic dependency parsing and semantic role labeling).
3 code implementations • 17 Sep 2020 • Yutai Hou, Jiafeng Mao, Yongkui Lai, Cheng Chen, Wanxiang Che, Zhigang Chen, Ting Liu
In this paper, we present FewJoint, a novel Few-Shot Learning benchmark for NLP.
no code implementations • 16 Aug 2020 • Libo Qin, Wanxiang Che, Yangming Li, Minheng Ni, Ting Liu
In dialog system, dialog act recognition and sentiment classification are two correlative tasks to capture speakers intentions, where dialog act and sentiment can indicate the explicit and the implicit intentions separately.
no code implementations • ACL 2020 • Jun Xu, Haifeng Wang, Zheng-Yu Niu, Hua Wu, Wanxiang Che, Ting Liu
To address the challenge of policy learning in open-domain multi-turn conversation, we propose to represent prior information about dialog transitions as a graph and learn a graph grounded dialog policy, aimed at fostering a more coherent and controllable dialog.
no code implementations • ACL 2020 • Yangming Li, Kaisheng Yao, Libo Qin, Wanxiang Che, Xiaolong Li, Ting Liu
Data-driven approaches using neural networks have achieved promising performances in natural language generation (NLG).
1 code implementation • 11 Jun 2020 • Libo Qin, Minheng Ni, Yue Zhang, Wanxiang Che
Compared with the existing work, our method does not rely on bilingual sentences for training, and requires only one training process for multiple target languages.
2 code implementations • ACL 2020 • Yutai Hou, Wanxiang Che, Yongkui Lai, Zhihan Zhou, Yijia Liu, Han Liu, Ting Liu
In this paper, we explore the slot tagging with only a few labeled support sentences (a. k. a.
1 code implementation • ACL 2020 • Bo Zheng, Haoyang Wen, Yaobo Liang, Nan Duan, Wanxiang Che, Daxin Jiang, Ming Zhou, Ting Liu
Natural Questions is a new challenging machine reading comprehension benchmark with two-grained answers, which are a long answer (typically a paragraph) and a short answer (one or more entities inside the long answer).
2 code implementations • ACL 2020 • Zeming Liu, Haifeng Wang, Zheng-Yu Niu, Hua Wu, Wanxiang Che, Ting Liu
We propose a new task of conversational recommendation over multi-type dialogs, where the bots can proactively and naturally lead a conversation from a non-recommendation dialog (e. g., QA) to a recommendation dialog, taking into account user's interests and feedback.
no code implementations • 30 Apr 2020 • Libo Qin, Minheng Ni, Yue Zhang, Wanxiang Che, Yangming Li, Ting Liu
Spoken language understanding has been addressed as a supervised learning problem, where a set of training data is available for each domain.
6 code implementations • Findings of the Association for Computational Linguistics 2020 • Yiming Cui, Wanxiang Che, Ting Liu, Bing Qin, Shijin Wang, Guoping Hu
Bidirectional Encoder Representations from Transformers (BERT) has shown marvelous improvements across various NLP tasks, and consecutive variants have been proposed to further improve the performance of the pre-trained language models.
Ranked #13 on
Stock Market Prediction
on Astock
1 code implementation • EMNLP 2020 • Sanyuan Chen, Yutai Hou, Yiming Cui, Wanxiang Che, Ting Liu, Xiangzhan Yu
Deep pretrained language models have achieved great success in the way of pretraining first and then fine-tuning.
1 code implementation • ACL 2020 • Libo Qin, Xiao Xu, Wanxiang Che, Yue Zhang, Ting Liu
However, there has been relatively little research on how to effectively use data from all domains to improve the performance of each domain and also unseen domains.
Ranked #1 on
Task-Oriented Dialogue Systems
on Kvret
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Libo Qin, Xiao Xu, Wanxiang Che, Ting Liu
Such an interaction layer is applied to each token adaptively, which has the advantage to automatically extract the relevant intents information, making a fine-grained intent information integration for the token-level slot prediction.
Ranked #4 on
Intent Detection
on SNIPS
1 code implementation • COLING 2020 • Yiming Cui, Ting Liu, Ziqing Yang, Zhipeng Chen, Wentao Ma, Wanxiang Che, Shijin Wang, Guoping Hu
To add diversity in this area, in this paper, we propose a new task called Sentence Cloze-style Machine Reading Comprehension (SC-MRC).
1 code implementation • ACL 2020 • Ziqing Yang, Yiming Cui, Zhipeng Chen, Wanxiang Che, Ting Liu, Shijin Wang, Guoping Hu
In this paper, we introduce TextBrewer, an open-source knowledge distillation toolkit designed for natural language processing.
no code implementations • 19 Dec 2019 • Yiming Cui, Wanxiang Che, Wei-Nan Zhang, Ting Liu, Shijin Wang, Guoping Hu
Story Ending Prediction is a task that needs to select an appropriate ending for the given story, which requires the machine to understand the story and sometimes needs commonsense knowledge.
no code implementations • 14 Nov 2019 • Yiming Cui, Wei-Nan Zhang, Wanxiang Che, Ting Liu, Zhipeng Chen, Shijin Wang, Guoping Hu
Recurrent Neural Networks (RNN) are known as powerful models for handling sequential data, and especially widely utilized in various natural language processing tasks.
no code implementations • 9 Nov 2019 • Ziqing Yang, Yiming Cui, Wanxiang Che, Ting Liu, Shijin Wang, Guoping Hu
With virtual adversarial training (VAT), we explore the possibility of improving the RC models with semi-supervised learning and prove that examples from a different task are also beneficial.
no code implementations • CONLL 2019 • Wanxiang Che, Longxu Dou, Yang Xu, Yuxuan Wang, Yijia Liu, Ting Liu
This paper describes our system (HIT-SCIR) for CoNLL 2019 shared task: Cross-Framework Meaning Representation Parsing.
Ranked #1 on
UCCA Parsing
on CoNLL 2019
1 code implementation • IJCNLP 2019 • Yuxuan Wang, Wanxiang Che, Jiang Guo, Yijia Liu, Ting Liu
In this approach, a linear transformation is learned from contextual word alignments to align the contextualized embeddings independently trained in different languages.
1 code implementation • IJCNLP 2019 • Libo Qin, Yijia Liu, Wanxiang Che, Haoyang Wen, Yangming Li, Ting Liu
Querying the knowledge base (KB) has long been a challenge in the end-to-end task-oriented dialogue system.
Ranked #6 on
Task-Oriented Dialogue Systems
on KVRET
1 code implementation • 10 Sep 2019 • Yutai Hou, Meng Fang, Wanxiang Che, Ting Liu
The framework builds a user simulator by first generating diverse dialogue data from templates and then build a new State2Seq user simulator on the data.
2 code implementations • IJCNLP 2019 • Libo Qin, Wanxiang Che, Yangming Li, Haoyang Wen, Ting Liu
In our framework, we adopt a joint model with Stack-Propagation which can directly use the intent information as input for slot filling, thus to capture the intent semantic knowledge.
Ranked #2 on
Intent Detection
on SNIPS
1 code implementation • IJCNLP 2019 • Yiming Cui, Wanxiang Che, Ting Liu, Bing Qin, Shijin Wang, Guoping Hu
In this paper, we propose Cross-Lingual Machine Reading Comprehension (CLMRC) task for the languages other than English.
no code implementations • 15 Aug 2019 • Shaolei Wang, Wanxiang Che, Qi Liu, Pengda Qin, Ting Liu, William Yang Wang
The pre-trained network is then fine-tuned using human-annotated disfluency detection training data.
1 code implementation • ACL 2019 • Shuhuai Ren, Yihe Deng, Kun He, Wanxiang Che
Experiments on three popular datasets using convolutional as well as LSTM models show that PWWS reduces the classification accuracy to the most extent, and keeps a very low word substitution rate.
no code implementations • 20 Jun 2019 • Yutai Hou, Zhihan Zhou, Yijia Liu, Ning Wang, Wanxiang Che, Han Liu, Ting Liu
It calculates emission score with similarity based methods and obtains transition score with a specially designed transfer mechanism.
2 code implementations • 19 Jun 2019 • Yiming Cui, Wanxiang Che, Ting Liu, Bing Qin, Ziqing Yang
To demonstrate the effectiveness of these models, we create a series of Chinese pre-trained language models as our baselines, including BERT, RoBERTa, ELECTRA, RBT, etc.
1 code implementation • IJCNLP 2019 • Yiming Cui, Ting Liu, Wanxiang Che, Li Xiao, Zhipeng Chen, Wentao Ma, Shijin Wang, Guoping Hu
Machine Reading Comprehension (MRC) has become enormously popular recently and has attracted a lot of attention.
1 code implementation • EMNLP 2018 • Yijia Liu, Wanxiang Che, Bo Zheng, Bing Qin, Ting Liu
In this paper, we propose a new rich resource enhanced AMR aligner which produces multiple alignments and a new transition system for AMR parsing along with its oracle parser.
Ranked #2 on
AMR Parsing
on LDC2014T12:
1 code implementation • CONLL 2018 • Wanxiang Che, Yijia Liu, Yuxuan Wang, Bo Zheng, Ting Liu
This paper describes our system (HIT-SCIR) submitted to the CoNLL 2018 shared task on Multilingual Parsing from Raw Text to Universal Dependencies.
Ranked #3 on
Dependency Parsing
on Universal Dependencies
1 code implementation • COLING 2018 • Yutai Hou, Yijia Liu, Wanxiang Che, Ting Liu
In this paper, we study the problem of data augmentation for language understanding in task-oriented dialogue system.
no code implementations • WS 2018 • Ruiji Fu, Zhengqi Pei, Jiefu Gong, Wei Song, Dechuan Teng, Wanxiang Che, Shijin Wang, Guoping Hu, Ting Liu
This paper describes our system at NLPTEA-2018 Task {\#}1: Chinese Grammatical Error Diagnosis.
no code implementations • COLING 2018 • Haoyang Wen, Yijia Liu, Wanxiang Che, Libo Qin, Ting Liu
Classic pipeline models for task-oriented dialogue system require explicit modeling the dialogue states and hand-crafted action spaces to query a domain-specific knowledge base.
Ranked #7 on
Task-Oriented Dialogue Systems
on KVRET
1 code implementation • ACL 2018 • Yijia Liu, Wanxiang Che, Huaipeng Zhao, Bing Qin, Ting Liu
Many natural language processing tasks can be modeled into structured prediction and solved as a search problem.
1 code implementation • NAACL 2018 • Yijia Liu, Yi Zhu, Wanxiang Che, Bing Qin, Nathan Schneider, Noah A. Smith
Nonetheless, using the new treebank, we build a pipeline system to parse raw tweets into UD.
Ranked #2 on
Dependency Parsing
on Tweebank
no code implementations • IJCNLP 2017 • Wanxiang Che, Yue Zhang
Neural networks, also with a fancy name deep learning, just right can overcome the above {``}feature engineering{''} problem.
2 code implementations • 29 Sep 2017 • Wei-Nan Zhang, Zhigang Chen, Wanxiang Che, Guoping Hu, Ting Liu
In this paper, we introduce the first evaluation of Chinese human-computer dialogue technology.
1 code implementation • EMNLP 2017 • Shaolei Wang, Wanxiang Che, Yue Zhang, Meishan Zhang, Ting Liu
In this paper, we model the problem of disfluency detection using a transition-based framework, which incrementally constructs and labels the disfluency chunk of input sentences using a new transition system without syntax information.
no code implementations • CONLL 2017 • Wanxiang Che, Jiang Guo, Yuxuan Wang, Bo Zheng, Huaipeng Zhao, Yang Liu, Dechuan Teng, Ting Liu
Our system includes three pipelined components: \textit{tokenization}, \textit{Part-of-Speech} (POS) \textit{tagging} and \textit{dependency parsing}.
no code implementations • COLING 2016 • Jiang Guo, Wanxiang Che, Haifeng Wang, Ting Liu, Jun Xu
This paper describes a unified neural architecture for identifying and classifying multi-typed semantic relations between words in a sentence.
no code implementations • COLING 2016 • Shaolei Wang, Wanxiang Che, Ting Liu
We treat disfluency detection as a sequence-to-sequence problem and propose a neural attention-based model which can efficiently model the long-range dependencies between words and make the resulting sentence more likely to be grammatically correct.
no code implementations • COLING 2016 • Jiang Guo, Wanxiang Che, Haifeng Wang, Ting Liu
Various treebanks have been released for dependency parsing.
no code implementations • WS 2016 • Bo Zheng, Wanxiang Che, Jiang Guo, Ting Liu
This paper introduces our Chinese Grammatical Error Diagnosis (CGED) system in the NLP-TEA-3 shared task for CGED.
no code implementations • 3 Jun 2016 • Jiang Guo, Wanxiang Che, Haifeng Wang, Ting Liu
Various treebanks have been released for dependency parsing.
1 code implementation • 19 Apr 2016 • Yijia Liu, Wanxiang Che, Jiang Guo, Bing Qin, Ting Liu
Many natural language processing (NLP) tasks can be generalized into segmentation problem.
no code implementations • 5 Mar 2016 • Jiang Guo, Wanxiang Che, David Yarowsky, Haifeng Wang, Ting Liu
Cross-lingual model transfer has been a promising approach for inducing dependency parsers for low-resource languages where annotated treebanks are not available.
Cross-lingual zero-shot dependency parsing
Representation Learning