1 code implementation • NAACL 2021 • Jiahao Bu, Lei Ren, Shuang Zheng, Yang Yang, Jingang Wang, Fuzheng Zhang, Wei Wu
Aspect category sentiment analysis (ACSA) and review rating prediction (RP) are two essential tasks to detect the fine-to-coarse sentiment polarities.
2 code implementations • ACL 2022 • Shengding Hu, Ning Ding, Huadong Wang, Zhiyuan Liu, Jingang Wang, Juanzi Li, Wei Wu, Maosong Sun
Tuning pre-trained language models (PLMs) with task-specific prompts has been a promising approach for text classification.
1 code implementation • 26 May 2023 • Jiduan Liu, Jiahao Liu, Qifan Wang, Jingang Wang, Wei Wu, Yunsen Xian, Dongyan Zhao, Kai Chen, Rui Yan
In this paper, we propose a novel approach, RankCSE, for unsupervised sentence representation learning, which incorporates ranking consistency and ranking distillation with contrastive learning into a unified framework.
1 code implementation • 11 Jun 2023 • Shicheng Tan, Weng Lam Tam, Yuanchun Wang, Wenwen Gong, Yang Yang, Hongyin Tang, Keqing He, Jiahao Liu, Jingang Wang, Shu Zhao, Peng Zhang, Jie Tang
Currently, the reduction in the parameter scale of large-scale pre-trained language models (PLMs) through knowledge distillation has greatly facilitated their widespread deployment on various devices.
1 code implementation • 20 May 2023 • Chen Zhang, Yang Yang, Jiahao Liu, Jingang Wang, Yunsen Xian, Benyou Wang, Dawei Song
However, when the capacity gap between the teacher and the student is large, a curse of capacity gap appears, invoking a deficiency in distilling LMs.
1 code implementation • COLING 2022 • Chen Zhang, Lei Ren, Fang Ma, Jingang Wang, Wei Wu, Dawei Song
Thus, a natural question arises: Is structural bias still a necessity in the context of PLMs?
1 code implementation • 11 May 2022 • Chen Zhang, Lei Ren, Jingang Wang, Wei Wu, Dawei Song
Prompt-tuning has shown appealing performance in few-shot classification by virtue of its capability in effectively exploiting pre-trained knowledge.
1 code implementation • COLING 2022 • Yutao Mou, Keqing He, Yanan Wu, Pei Wang, Jingang Wang, Wei Wu, Yi Huang, Junlan Feng, Weiran Xu
Traditional intent classification models are based on a pre-defined intent set and only recognize limited in-domain (IND) intent classes.
1 code implementation • 17 Oct 2022 • Weihao Zeng, Keqing He, Zechen Wang, Dayuan Fu, Guanting Dong, Ruotong Geng, Pei Wang, Jingang Wang, Chaobo Sun, Wei Wu, Weiran Xu
Recent advances in neural approaches greatly improve task-oriented dialogue (TOD) systems which assist users to accomplish their goals.
1 code implementation • 17 Oct 2022 • Yutao Mou, Keqing He, Pei Wang, Yanan Wu, Jingang Wang, Wei Wu, Weiran Xu
For OOD clustering stage, we propose a KCC method to form compact clusters by mining true hard negative samples, which bridges the gap between clustering and representation learning.
1 code implementation • 29 May 2022 • Chen Zhang, Yang Yang, Qifan Wang, Jiahao Liu, Jingang Wang, Wei Wu, Dawei Song
In particular, motivated by the finding that the performance of the student is positively correlated to the scale-performance tradeoff of the teacher assistant, MiniDisc is designed with a $\lambda$-tradeoff to measure the optimality of the teacher assistant without trial distillation to the student.
1 code implementation • 17 Jun 2023 • Weihao Zeng, Keqing He, Yejie Wang, Chen Zeng, Jingang Wang, Yunsen Xian, Weiran Xu
Pre-trained language models based on general text enable huge success in the NLP scenario.
1 code implementation • 28 May 2023 • Yutao Mou, Xiaoshuai Song, Keqing He, Chen Zeng, Pei Wang, Jingang Wang, Yunsen Xian, Weiran Xu
Previous methods suffer from a coupling of pseudo label disambiguation and representation learning, that is, the reliability of pseudo labels relies on representation learning, and representation learning is restricted by pseudo labels in turn.
1 code implementation • 16 Oct 2023 • Xiaoshuai Song, Keqing He, Pei Wang, Guanting Dong, Yutao Mou, Jingang Wang, Yunsen Xian, Xunliang Cai, Weiran Xu
The tasks of out-of-domain (OOD) intent discovery and generalized intent discovery (GID) aim to extend a closed intent classifier to open-world intent sets, which is crucial to task-oriented dialogue (TOD) systems.
no code implementations • 5 Jan 2018 • Jingang Wang, Junfeng Tian, Long Qiu, Sheng Li, Jun Lang, Luo Si, Man Lan
It is a challenging and practical research problem to obtain effective compression of lengthy product titles for E-commerce.
no code implementations • WS 2018 • Yongchao Deng, Shanbo Cheng, Jun Lu, Kai Song, Jingang Wang, Shenglan Wu, Liang Yao, Guchun Zhang, Haibo Zhang, Pei Zhang, Changfeng Zhu, Boxing Chen
We participated in 5 translation directions including English ↔ Russian, English ↔ Turkish in both directions and English → Chinese.
no code implementations • 19 May 2019 • Bowen Xing, Lejian Liao, Dandan song, Jingang Wang, Fuzheng Zhang, Zhongyuan Wang, He-Yan Huang
This paper proposes a novel variant of LSTM, termed as aspect-aware LSTM (AA-LSTM), which incorporates aspect information into LSTM cells in the context modeling stage before the attention mechanism.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA)
no code implementations • 19 Oct 2020 • Yang Yang, Junmei Hao, Canjia Li, Zili Wang, Jingang Wang, Fuzheng Zhang, Rao Fu, Peixu Hou, Gong Zhang, Zhongyuan Wang
Existing work on tip generation does not take query into consideration, which limits the impact of tips in search scenarios.
no code implementations • ACL 2021 • Hongyin Tang, Xingwu Sun, Beihong Jin, Jingang Wang, Fuzheng Zhang, Wei Wu
Recently, the retrieval models based on dense representations have been gradually applied in the first stage of the document retrieval tasks, showing better performance than traditional sparse vector space models.
no code implementations • 8 Dec 2021 • Dan Li, Yang Yang, Hongyin Tang, Jingang Wang, Tong Xu, Wei Wu, Enhong Chen
With the booming of pre-trained transformers, representation-based models based on Siamese transformer encoders have become mainstream techniques for efficient text matching.
no code implementations • 5 Mar 2022 • Qifan Wang, Yi Fang, Anirudh Ravula, Ruining He, Bin Shen, Jingang Wang, Xiaojun Quan, Dongfang Liu
Network embedding is an effective technique to learn the low-dimensional representations of nodes in networks.
no code implementations • 18 Apr 2022 • Jiduan Liu, Jiahao Liu, Yang Yang, Jingang Wang, Wei Wu, Dongyan Zhao, Rui Yan
To enhance the performance of dense retrieval models without loss of efficiency, we propose a GNN-encoder model in which query (passage) information is fused into passage (query) representations via graph neural networks that are constructed by queries and their top retrieved passages.
no code implementations • COLING 2022 • Borun Chen, Hongyin Tang, Jiahao Bu, Kai Zhang, Jingang Wang, Qifan Wang, Hai-Tao Zheng, Wei Wu, Liqian Yu
However, most current models use Chinese characters as inputs and are not able to encode semantic information contained in Chinese words.
no code implementations • 31 Aug 2022 • Keqing He, Jingang Wang, Chaobo Sun, Wei Wu
In this paper, we propose a novel unified knowledge prompt pre-training framework, UFA (\textbf{U}nified Model \textbf{F}or \textbf{A}ll Tasks), for customer service dialogues.
no code implementations • 10 Oct 2022 • Fang Ma, Chen Zhang, Lei Ren, Jingang Wang, Qifan Wang, Wei Wu, Xiaojun Quan, Dawei Song
Prompt tuning learns soft prompts to condition frozen Pre-trained Language Models (PLMs) for performing downstream tasks in a parameter-efficient manner.
1 code implementation • 19 Oct 2022 • Yutao Mou, Pei Wang, Keqing He, Yanan Wu, Jingang Wang, Wei Wu, Weiran Xu
Specifically, we design a K-nearest neighbor contrastive learning (KNCL) objective for representation learning and introduce a KNN-based scoring function for OOD detection.
no code implementations • 15 Dec 2022 • Liqi Yan, Qifan Wang, Siqi Ma, Jingang Wang, Changbin Yu
Instance segmentation in videos, which aims to segment and track multiple objects in video frames, has garnered a flurry of research attention in recent years.
no code implementations • 20 Mar 2023 • Ying Mo, Hongyin Tang, Jiahao Liu, Qifan Wang, Zenglin Xu, Jingang Wang, Wei Wu, Zhoujun Li
There are three types of NER tasks, including flat, nested and discontinuous entity recognition.
no code implementations • 21 May 2023 • Chen Zhang, Yang Yang, Jingang Wang, Dawei Song
Finetuning pretrained language models (LMs) have enabled appealing performance on a diverse array of tasks.
no code implementations • 30 May 2023 • Zhuocheng Gong, Jiahao Liu, Qifan Wang, Yang Yang, Jingang Wang, Wei Wu, Yunsen Xian, Dongyan Zhao, Rui Yan
While transformer-based pre-trained language models (PLMs) have dominated a number of NLP applications, these models are heavy to deploy and expensive to use.
1 code implementation • 17 Jun 2023 • Weihao Zeng, Lulu Zhao, Keqing He, Ruotong Geng, Jingang Wang, Wei Wu, Weiran Xu
In this paper, we explore the compositional generalization for multi-attribute controllable dialogue generation where a model can learn from seen attribute values and generalize to unseen combinations.
no code implementations • 17 Aug 2023 • Ying Mo, Jian Yang, Jiahao Liu, Qifan Wang, Ruoyu Chen, Jingang Wang, Zhoujun Li
A multi-view contrastive learning framework is introduced to encompass semantic contrasts between source, codeswitched, and target sentences, as well as contrasts among token-to-token relations.
no code implementations • 20 Oct 2023 • Pei Wang, Keqing He, Yutao Mou, Xiaoshuai Song, Yanan Wu, Jingang Wang, Yunsen Xian, Xunliang Cai, Weiran Xu
Detecting out-of-domain (OOD) intents from user queries is essential for a task-oriented dialogue system.
no code implementations • 24 Oct 2023 • Jiduan Liu, Jiahao Liu, Qifan Wang, Jingang Wang, Xunliang Cai, Dongyan Zhao, Ran Lucien Wang, Rui Yan
In particular, our approach extracts knowledge from LLMs to construct a knowledge store, from which the small-scale model can retrieve relevant information and leverage it for effective inference.
no code implementations • 30 Oct 2023 • Zhuocheng Gong, Jiahao Liu, Qifan Wang, Jingang Wang, Xunliang Cai, Dongyan Zhao, Rui Yan
The effectiveness of ICL can be attributed to the strong language modeling capabilities of large language models (LLMs), which enable them to learn the mapping between input and labels based on in-context demonstrations.
no code implementations • 14 Feb 2024 • Yejie Wang, Keqing He, Guanting Dong, Pei Wang, Weihao Zeng, Muxi Diao, Yutao Mou, Mengdi Zhang, Jingang Wang, Xunliang Cai, Weiran Xu
It learns diverse instruction targets and combines a code evaluation objective to enhance its code generation ability.
no code implementations • 17 Feb 2024 • Ying Mo, Jian Yang, Jiahao Liu, Shun Zhang, Jingang Wang, Zhoujun Li
Recently, there has been increasing interest in exploring the capabilities of advanced large language models (LLMs) in the field of information extraction (IE), specifically focusing on tasks related to named entity recognition (NER) and relation extraction (RE).
no code implementations • 27 Feb 2024 • Pei Wang, Keqing He, Yejie Wang, Xiaoshuai Song, Yutao Mou, Jingang Wang, Yunsen Xian, Xunliang Cai, Weiran Xu
Out-of-domain (OOD) intent detection aims to examine whether the user's query falls outside the predefined domain of the system, which is crucial for the proper functioning of task-oriented dialogue (TOD) systems.
no code implementations • 11 Mar 2024 • Zhuocheng Gong, Jiahao Liu, Jingang Wang, Xunliang Cai, Dongyan Zhao, Rui Yan
Our findings reveal several connections between the properties of perturbations and LLM performance, providing insights into the failure cases of uniform quantization and suggesting potential solutions to improve the robustness of LLM quantization.
no code implementations • 18 Apr 2024 • Pengfei Wu, Jiahao Liu, Zhuocheng Gong, Qifan Wang, Jinpeng Li, Jingang Wang, Xunliang Cai, Dongyan Zhao
In this paper, we propose a novel parallel decoding approach, namely \textit{hidden transfer}, which decodes multiple successive tokens simultaneously in a single forward pass.