3 code implementations • EMNLP 2021 • Runxin Xu, Fuli Luo, Zhiyuan Zhang, Chuanqi Tan, Baobao Chang, Songfang Huang, Fei Huang
Recent pretrained language models extend from millions to billions of parameters.
2 code implementations • 14 Dec 2021 • Runxin Xu, Fuli Luo, Chengyu Wang, Baobao Chang, Jun Huang, Songfang Huang, Fei Huang
Unified in contrastive learning, CAP enables the pruned model to learn from the pre-trained model for task-agnostic knowledge, and fine-tuned model for task-specific knowledge.
1 code implementation • 17 Feb 2021 • Tianyu Liu, Xin Zheng, Baobao Chang, Zhifang Sui
In open domain table-to-text generation, we notice that the unfaithful generation usually contains hallucinated content which can not be aligned to any input table record.
1 code implementation • 31 Dec 2022 • Qingxiu Dong, Damai Dai, Ce Zheng, Zhiyong Wu, Baobao Chang, Xu sun, Jingjing Xu, Lei LI, Zhifang Sui
With the increasing ability of large language models (LLMs), in-context learning (ICL) has become a new paradigm for natural language processing (NLP), where LLMs make predictions only based on contexts augmented with a few examples.
2 code implementations • ACL 2022 • Ningyu Zhang, Mosha Chen, Zhen Bi, Xiaozhuan Liang, Lei LI, Xin Shang, Kangping Yin, Chuanqi Tan, Jian Xu, Fei Huang, Luo Si, Yuan Ni, Guotong Xie, Zhifang Sui, Baobao Chang, Hui Zong, Zheng Yuan, Linfeng Li, Jun Yan, Hongying Zan, Kunli Zhang, Buzhou Tang, Qingcai Chen
Artificial Intelligence (AI), along with the recent progress in biomedical language understanding, is gradually changing medical practice.
Ranked #1 on Semantic Similarity on CHIP-STS
3 code implementations • ACL 2022 • Damai Dai, Li Dong, Yaru Hao, Zhifang Sui, Baobao Chang, Furu Wei
In this paper, we present preliminary studies on how factual knowledge is stored in pretrained Transformers by introducing the concept of knowledge neurons.
2 code implementations • 14 Sep 2023 • Haozhe Zhao, Zefan Cai, Shuzheng Si, Xiaojian Ma, Kaikai An, Liang Chen, Zixuan Liu, Sheng Wang, Wenjuan Han, Baobao Chang
In this paper, we address the limitation above by 1) introducing vision-language Model with Multi-Modal In-Context Learning(MMICL), a new approach to allow the VLM to deal with multi-modal inputs efficiently; 2) proposing a novel context scheme to augment the in-context learning ability of the VLM; 3) constructing the Multi-modal In-Context Learning (MIC) dataset, designed to enhance the VLM's ability to understand complex multi-modal prompts.
Ranked #16 on Visual Reasoning on Winoground
2 code implementations • 24 May 2019 • Fuli Luo, Peng Li, Jie zhou, Pengcheng Yang, Baobao Chang, Zhifang Sui, Xu sun
Therefore, in this paper, we propose a dual reinforcement learning framework to directly transfer the style of the text via a one-step mapping model, without any separation of content and style.
Ranked #1 on Unsupervised Text Style Transfer on GYAFC
2 code implementations • ACL 2021 • Runxin Xu, Tianyu Liu, Lei LI, Baobao Chang
Existing methods are not effective due to two challenges of this task: a) the target event arguments are scattered across sentences; b) the correlation among events in a document is non-trivial to model.
Ranked #2 on Document-level Event Extraction on ChFinAnn
3 code implementations • 27 Nov 2017 • Tianyu Liu, Kexiang Wang, Lei Sha, Baobao Chang, Zhifang Sui
In the decoding phase, dual attention mechanism which contains word level attention and field level attention is proposed to model the semantic relevance between the generated description and the table.
Ranked #1 on Table-to-Text Generation on WikiBio
2 code implementations • EMNLP 2020 • Shuang Zeng, Runxin Xu, Baobao Chang, Lei LI
Document-level relation extraction aims to extract relations among entities within a document.
Ranked #12 on Relation Extraction on DocRED
1 code implementation • 11 Mar 2024 • Liang Chen, Haozhe Zhao, Tianyu Liu, Shuai Bai, Junyang Lin, Chang Zhou, Baobao Chang
To this end, we introduce FastV, a versatile plug-and-play method designed to optimize computational efficiency by learning adaptive attention patterns in early layers and pruning visual tokens in subsequent ones.
1 code implementation • 3 Oct 2023 • Liang Chen, Yichi Zhang, Shuhuai Ren, Haozhe Zhao, Zefan Cai, Yuchi Wang, Peiyi Wang, Tianyu Liu, Baobao Chang
In this study, we explore the potential of Multimodal Large Language Models (MLLMs) in improving embodied decision-making processes for agents.
1 code implementation • 21 Feb 2024 • Liang Chen, Yichi Zhang, Shuhuai Ren, Haozhe Zhao, Zefan Cai, Yuchi Wang, Peiyi Wang, Xiangdi Meng, Tianyu Liu, Baobao Chang
To address this, we introduce Embodied-Instruction-Evolution (EIE), an automatic framework for synthesizing instruction tuning examples in multimodal embodied environments.
1 code implementation • ACL 2018 • Fuli Luo, Tianyu Liu, Qiaolin Xia, Baobao Chang, Zhifang Sui
GAS models the semantic relationship between the context and the gloss in an improved memory network framework, which breaks the barriers of the previous supervised methods and knowledge-based methods.
Ranked #3 on Word Sense Disambiguation on SemEval 2015 Task 13
1 code implementation • ACL 2019 • Fuli Luo, Peng Li, Pengcheng Yang, Jie zhou, Yutong Tan, Baobao Chang, Zhifang Sui, Xu sun
In this paper, we focus on the task of fine-grained text sentiment transfer (FGST).
1 code implementation • IJCNLP 2019 • Fuli Luo, Shunyao Li, Pengcheng Yang, Lei LI, Baobao Chang, Zhifang Sui, Xu sun
It consists of a generator to produce pun sentences, and a discriminator to distinguish between the generated pun sentences and the real sentences with specific word senses.
1 code implementation • ACL 2022 • Damai Dai, Li Dong, Shuming Ma, Bo Zheng, Zhifang Sui, Baobao Chang, Furu Wei
We point out that existing learning-to-route MoE methods suffer from the routing fluctuation issue, i. e., the target expert of the same input may change along with training, but only one expert will be activated for the input during inference.
1 code implementation • 16 Nov 2023 • Yuliang Liu, Xiangru Tang, Zefan Cai, Junjie Lu, Yichi Zhang, Yanjun Shao, Zexuan Deng, Helan Hu, Kaikai An, Ruijun Huang, Shuzheng Si, Sheng Chen, Haozhe Zhao, Liang Chen, Yan Wang, Tianyu Liu, Zhiwei Jiang, Baobao Chang, Yujia Qin, Wangchunshu Zhou, Yilun Zhao, Arman Cohan, Mark Gerstein
While Large Language Models (LLMs) have demonstrated proficiency in code generation benchmarks, translating these results into practical development scenarios - where leveraging existing repository-level libraries is the norm - remains challenging.
2 code implementations • 22 May 2023 • Ce Zheng, Lei LI, Qingxiu Dong, Yuxuan Fan, Zhiyong Wu, Jingjing Xu, Baobao Chang
Inspired by in-context learning (ICL), a new paradigm based on demonstration contexts without parameter updating, we explore whether ICL can edit factual knowledge.
1 code implementation • NAACL 2022 • Peiyi Wang, Runxin Xu, Tianyu Liu, Qingyu Zhou, Yunbo Cao, Baobao Chang, Zhifang Sui
Few-Shot Sequence Labeling (FSSL) is a canonical paradigm for the tagging models, e. g., named entity recognition and slot filling, to generalize on an emerging, resource-scarce domain.
Ranked #6 on Few-shot NER on Few-NERD (INTER)
1 code implementation • 29 Sep 2022 • Liang Chen, Bofei Gao, Baobao Chang
In this paper, we provide a detailed description of our system at CAMRP-2022 evaluation.
1 code implementation • Findings (ACL) 2021 • Shuang Zeng, Yuting Wu, Baobao Chang
However, not all entity pairs can be connected with a path and have the correct logical reasoning paths in their graph.
Ranked #19 on Relation Extraction on DocRED
2 code implementations • 6 Mar 2022 • Liang Chen, Runxin Xu, Baobao Chang
Label smoothing and vocabulary sharing are two widely used techniques in neural machine translation models.
2 code implementations • ACL 2022 • Liang Chen, Runxin Xu, Baobao Chang
Label smoothing and vocabulary sharing are two widely used techniques in neural machine translation models.
1 code implementation • NAACL 2022 • Runxin Xu, Peiyi Wang, Tianyu Liu, Shuang Zeng, Baobao Chang, Zhifang Sui
In this paper, we focus on extracting event arguments from an entire document, which mainly faces two critical problems: a) the long-distance dependency between trigger and arguments over sentences; b) the distracting context towards an event in the document.
Document-level Event Extraction Event Argument Extraction +2
1 code implementation • 2 May 2022 • Shoujie Tong, Qingxiu Dong, Damai Dai, YiFan Song, Tianyu Liu, Baobao Chang, Zhifang Sui
For each instance in a batch, we involve other instances in the same batch to interact with it.
2 code implementations • Findings (NAACL) 2022 • Liang Chen, Peiyi Wang, Runxin Xu, Tianyu Liu, Zhifang Sui, Baobao Chang
As Abstract Meaning Representation (AMR) implicitly involves compound semantic annotations, we hypothesize auxiliary tasks which are semantically or formally related can better enhance AMR parsing.
Ranked #7 on AMR Parsing on LDC2020T02 (using extra training data)
1 code implementation • ACL 2022 • Peiyi Wang, Liang Chen, Tianyu Liu, Damai Dai, Yunbo Cao, Baobao Chang, Zhifang Sui
Abstract Meaning Representation (AMR) parsing aims to translate sentences to semantic representation with a hierarchical structure, and is recently empowered by pretrained sequence-to-sequence models.
1 code implementation • 5 Dec 2022 • Ce Zheng, Yiming Wang, Baobao Chang
Such methods usually model role classification as naive multi-class classification and treat arguments individually, which neglects label semantics and interactions between arguments and thus hindering performance and generalization of models.
1 code implementation • 29 Aug 2021 • Peiyi Wang, Runxin Xu, Tianyu Liu, Damai Dai, Baobao Chang, Zhifang Sui
However, we find they suffer from trigger biases that signify the statistical homogeneity between some trigger words and target event types, which we summarize as trigger overlapping and trigger separability.
1 code implementation • COLING 2022 • Shuzheng Si, Shuang Zeng, Jiaxing Lin, Baobao Chang
Named Entity Recognition is the task to locate and classify the entities in the text.
1 code implementation • 4 Dec 2020 • Damai Dai, Jing Ren, Shuang Zeng, Baobao Chang, Zhifang Sui
In classification, we combine the entity representations from both two levels into more comprehensive representations for relation extraction.
Ranked #34 on Relation Extraction on DocRED
1 code implementation • 20 Oct 2023 • Kaikai An, Ce Zheng, Bofei Gao, Haozhe Zhao, Baobao Chang
Recent researches measure the similarity or matching score between targets and candidate frames by modeling frame definitions.
1 code implementation • NAACL 2022 • Ce Zheng, Xudong Chen, Runxin Xu, Baobao Chang
In this paper, we propose a Knowledge-guided Incremental semantic parser with Double-graph (KID).
2 code implementations • 18 May 2023 • Liang Chen, Shuming Ma, Dongdong Zhang, Furu Wei, Baobao Chang
We conduct experiments on a multilingual machine translation benchmark in 11 languages.
1 code implementation • 1 Sep 2017 • Lei Sha, Lili Mou, Tianyu Liu, Pascal Poupart, Sujian Li, Baobao Chang, Zhifang Sui
Generating texts from structured data (e. g., a table) is important for various natural language processing tasks such as question answering and dialog systems.
1 code implementation • ACL (RepL4NLP) 2021 • Damai Dai, Hua Zheng, Fuli Luo, Pengcheng Yang, Baobao Chang, Zhifang Sui
Conventional Knowledge Graph Completion (KGC) assumes that all test entities appear during training.
1 code implementation • CONLL 2020 • Tianyu Liu, Xin Zheng, Xiaoan Ding, Baobao Chang, Zhifang Sui
The prior work on natural language inference (NLI) debiasing mainly targets at one or few known biases while not necessarily making the models more robust.
1 code implementation • 13 Oct 2023 • Bofei Gao, Liang Chen, Peiyi Wang, Zhifang Sui, Baobao Chang
Abstract Meaning Representation (AMR) parsing aims to extract an abstract semantic graph from a given sentence.
1 code implementation • 12 Apr 2024 • Haozhe Zhao, Zefan Cai, Shuzheng Si, Liang Chen, Yufeng He, Kaikai An, Baobao Chang
Therefore, we introduce ALSACE to leverage the learned knowledge from the well-performing languages to guide under-performing ones within the same mPLM, eliminating the need for additional labeled multilingual data.
no code implementations • 3 Apr 2017 • Feng Qian, Lei Sha, Baobao Chang, Lu-chen Liu, Ming Zhang
As for semantic role labeling (SRL) task, when it comes to utilizing parsing information, both traditional methods and recent recurrent neural network (RNN) based methods use the feature engineering way.
no code implementations • 22 Feb 2017 • Qiaolin Xia, Baobao Chang, Zhifang Sui
Previous studies on Chinese semantic role labeling (SRL) have concentrated on single semantically annotated corpus.
no code implementations • 15 Jun 2016 • Qi Li, Tianshi Li, Baobao Chang
Word embeddings play a significant role in many modern NLP systems.
no code implementations • 27 Sep 2016 • Tao Ge, Qing Dou, Xiaoman Pan, Heng Ji, Lei Cui, Baobao Chang, Zhifang Sui, Ming Zhou
We introduce a novel Burst Information Network (BINet) representation that can display the most important information and illustrate the connections among bursty entities, events and keywords in the corpus.
no code implementations • NAACL 2016 • Lei Sha, Sujian Li, Baobao Chang, Zhifang Sui
Automatic event schema induction (AESI) means to extract meta-event from raw text, in other words, to find out what types (templates) of event may exist in the raw text and what roles (slots) may exist in each event type.
no code implementations • EMNLP 2018 • Fuli Luo, Tianyu Liu, Zexue He, Qiaolin Xia, Zhifang Sui, Baobao Chang
The goal of Word Sense Disambiguation (WSD) is to identify the correct meaning of a word in the particular context.
no code implementations • EMNLP 2018 • Tao Ge, Qing Dou, Heng Ji, Lei Cui, Baobao Chang, Zhifang Sui, Furu Wei, Ming Zhou
This paper proposes to study fine-grained coordinated cross-lingual text stream alignment through a novel information network decipherment paradigm.
no code implementations • EMNLP 2018 • Wenhui Wang, Baobao Chang, Mairgup Mansur
Pre-trained word embeddings and language model have been shown useful in a lot of tasks.
no code implementations • ACL 2017 • Wenhui Wang, Nan Yang, Furu Wei, Baobao Chang, Ming Zhou
We first match the question and passage with gated attention-based recurrent networks to obtain the question-aware passage representation.
Ranked #35 on Question Answering on SQuAD1.1 dev
no code implementations • ACL 2017 • Qiaolin Xia, Lei Sha, Baobao Chang, Zhifang Sui
But the training data of single corpus is often limited.
no code implementations • EMNLP 2017 • Kexiang Wang, Tianyu Liu, Zhifang Sui, Baobao Chang
Multi-document summarization provides users with a short text that summarizes the information in a set of related documents.
no code implementations • EMNLP 2017 • Tianyu Liu, Kexiang Wang, Baobao Chang, Zhifang Sui
Distant-supervised relation extraction inevitably suffers from wrong labeling problems because it heuristically labels relational facts with knowledge bases.
no code implementations • WS 2017 • Feng Qian, Lei Sha, Baobao Chang, Lu-chen Liu, Ming Zhang
In Semantic Role Labeling (SRL) task, the tree structured dependency relation is rich in syntax information, but it is not well handled by existing models.
no code implementations • COLING 2016 • Tingsong Jiang, Tianyu Liu, Tao Ge, Lei Sha, Baobao Chang, Sujian Li, Zhifang Sui
In this paper, we present a novel time-aware knowledge graph completion model that is able to predict links in a KG using both the existing facts and the temporal information of the facts.
no code implementations • COLING 2016 • Lei Sha, Baobao Chang, Zhifang Sui, Sujian Li
After read the premise again, the model can get a better understanding of the premise, which can also affect the understanding of the hypothesis.
Ranked #42 on Natural Language Inference on SNLI
no code implementations • COLING 2016 • Tao Ge, Lei Cui, Baobao Chang, Zhifang Sui, Ming Zhou
Retrospective event detection is an important task for discovering previously unidentified events in a text stream.
no code implementations • WS 2019 • Da Yin, Xiao Liu, Xiuyu Wu, Baobao Chang
In this paper, we propose a soft label approach to target-level sentiment classification task, in which a history-based soft labeling model is proposed to measure the possibility of a context word as an opinion word.
no code implementations • ACL 2019 • Tianyu Liu, Fuli Luo, Pengcheng Yang, Wei Wu, Baobao Chang, Zhifang Sui
To relieve these problems, we first propose force attention (FA) method to encourage the generator to pay more attention to the uncovered attributes to avoid potential key attributes missing.
no code implementations • ACL 2019 • Fuli Luo, Damai Dai, Pengcheng Yang, Tianyu Liu, Baobao Chang, Zhifang Sui, Xu sun
Therefore, we propose a generic and novel framework which consists of a sentiment analyzer and a sentimental generator, respectively addressing the two challenges.
no code implementations • LREC 2020 • Tianyu Liu, Xin Zheng, Baobao Chang, Zhifang Sui
Many recent studies have shown that for models trained on datasets for natural language inference (NLI), it is possible to make correct predictions by merely looking at the hypothesis while completely ignoring the premise.
1 code implementation • EMNLP 2020 • Xiaoan Ding, Tianyu Liu, Baobao Chang, Zhifang Sui, Kevin Gimpel
We explore training objectives for discriminative fine-tuning of our generative classifiers, showing improvements over log loss fine-tuning from prior work .
no code implementations • EMNLP 2020 • Kexiang Wang, Baobao Chang, Zhifang Sui
Multi-document summarization (MDS) aims at producing a good-quality summary for several related documents.
no code implementations • 14 Dec 2020 • Tianyang Cao, Shuang Zeng, Songge Zhao, Mairgup Mansur, Baobao Chang
Recent years have seen significant advancement in text generation tasks with the help of neural language models.
no code implementations • 26 Mar 2021 • Damai Dai, Hua Zheng, Zhifang Sui, Baobao Chang
Conventional Machine Reading Comprehension (MRC) has been well-addressed by pattern matching, but the ability of commonsense reasoning remains a gap between humans and machines.
no code implementations • 20 Apr 2021 • Qingxiu Dong, Zhifang Sui, Weidong Zhan, Baobao Chang
Starting from the concept, com-position, development and meaning of natural language evaluation, this article classifies and summarizes the tasks and char-acteristics of mainstream natural language evaluation, and then summarizes the problems and causes of natural language pro-cessing evaluation.
no code implementations • NAACL 2021 • Hua Zheng, Damai Dai, Lei LI, Tianyu Liu, Zhifang Sui, Baobao Chang, Yang Liu
In this paper, we tackle the task of Definition Generation (DG) in Chinese, which aims at automatically generating a definition for a word.
no code implementations • 21 Jun 2021 • Peiyi Wang, Tianyu Liu, Damai Dai, Runxin Xu, Baobao Chang, Zhifang Sui
Table encoder extracts sentiment at token-pair level, so that the compositional feature between targets and opinions can be easily captured.
no code implementations • COLING 2020 • Kexiang Wang, Tianyu Liu, Baobao Chang, Zhifang Sui
The widespread adoption of reference-based automatic evaluation metrics such as ROUGE has promoted the development of document summarization.
no code implementations • CCL 2021 • Yuan Zong, Baobao Chang
“中文分词是自然语言处理领域的基础工作, 然而前人的医学文本分词工作都只是直接套用通用分词的方法, 而医学文本多专用术语的特点让分词系统需要对医学专用术语和医学文本中的非医学术语文本提供不同的分词粒度。本文提出了双编码器医学文本中文分词模型, 利用辅助编码器为医学专有术语提供粗粒度表示。模型将需要粗粒度分词的医学专用术语和需要通用分词粒度的文本分开, 在提升医学专用术语的分词能力的同时最大限度地避免了其粗粒度对于医学文本中通用文本分词的干扰。”
no code implementations • 26 Mar 2022 • Sha Yuan, Hanyu Zhao, Shuai Zhao, Jiahong Leng, Yangxiao Liang, Xiaozhi Wang, Jifan Yu, Xin Lv, Zhou Shao, Jiaao He, Yankai Lin, Xu Han, Zhenghao Liu, Ning Ding, Yongming Rao, Yizhao Gao, Liang Zhang, Ming Ding, Cong Fang, Yisen Wang, Mingsheng Long, Jing Zhang, Yinpeng Dong, Tianyu Pang, Peng Cui, Lingxiao Huang, Zheng Liang, HuaWei Shen, HUI ZHANG, Quanshi Zhang, Qingxiu Dong, Zhixing Tan, Mingxuan Wang, Shuo Wang, Long Zhou, Haoran Li, Junwei Bao, Yingwei Pan, Weinan Zhang, Zhou Yu, Rui Yan, Chence Shi, Minghao Xu, Zuobai Zhang, Guoqiang Wang, Xiang Pan, Mengjie Li, Xiaoyu Chu, Zijun Yao, Fangwei Zhu, Shulin Cao, Weicheng Xue, Zixuan Ma, Zhengyan Zhang, Shengding Hu, Yujia Qin, Chaojun Xiao, Zheni Zeng, Ganqu Cui, Weize Chen, Weilin Zhao, Yuan YAO, Peng Li, Wenzhao Zheng, Wenliang Zhao, Ziyi Wang, Borui Zhang, Nanyi Fei, Anwen Hu, Zenan Ling, Haoyang Li, Boxi Cao, Xianpei Han, Weidong Zhan, Baobao Chang, Hao Sun, Jiawen Deng, Chujie Zheng, Juanzi Li, Lei Hou, Xigang Cao, Jidong Zhai, Zhiyuan Liu, Maosong Sun, Jiwen Lu, Zhiwu Lu, Qin Jin, Ruihua Song, Ji-Rong Wen, Zhouchen Lin, LiWei Wang, Hang Su, Jun Zhu, Zhifang Sui, Jiajun Zhang, Yang Liu, Xiaodong He, Minlie Huang, Jian Tang, Jie Tang
With the rapid development of deep learning, training Big Models (BMs) for multiple downstream tasks becomes a popular paradigm.
no code implementations • COLING 2022 • Tianyang Cao, Shuang Zeng, Xiaodan Xu, Mairgup Mansur, Baobao Chang
A math word problem (MWP) is a coherent narrative which reflects the underlying logic of math equations.
no code implementations • 15 Apr 2022 • Damai Dai, Wenbin Jiang, Jiyuan Zhang, Weihua Peng, Yajuan Lyu, Zhifang Sui, Baobao Chang, Yong Zhu
In this paper, in order to alleviate the parameter competition problem, we propose a Mixture-of-Expert (MoE) based question answering method called MoEBQA that decouples the computation for different types of questions by sparse routing.
no code implementations • ACL 2022 • Runxin Xu, Fuli Luo, Baobao Chang, Songfang Huang, Fei Huang
The emergence of multilingual pre-trained language models makes it possible to adapt to target languages with only few labeled examples. However, vanilla fine-tuning tends to achieve degenerated and unstable results, owing to the Language Interference among different languages, and Parameter Overload under the few-sample transfer learning scenarios. To address two problems elegantly, we propose S^4-Tuning, a Simple Cross-lingual Sub-network Tuning method.
no code implementations • CCL 2022 • Xudong Chen, Ce Zheng, Baobao Chang
“框架语义分析任务是自然语言处理领域的一项基础性任务。先前的研究工作大多针对单目标词进行模型设计, 无法一次性完成多个目标词的框架语义结构提取。本文提出了一个面向多目标的框架语义分析模型, 实现对多目标词的联合预测。该模型对框架语义分析的各项子任务进行交互性建模, 实现子任务间的双向交互。此外, 本文利用关系图网络对框架关系信息进行编码, 将其作为框架语义学知识融入模型中。实验表明, 本文模型在不借助额外语料的情况下相比之前模型都有不同程度的提高。消融实验证明了本文模型设计的有效性。此外我们分析了模型目前存在的局限性以及未来的改进方向。”
no code implementations • CCL 2022 • Tianyang Cao, Xiaodan Xu, Baobao Chang
“数学文字题是一段能反映数学等式潜在逻辑的叙述性文本。成功的数学问题生成在语言生成和教育领域都具有广阔的应用前景。前人的工作大多需要人工标注的模板或关键词作为输入, 且未考虑数学表达式本身的特点。本文提出了一种多任务联合训练的问题文本生成模型。我们设计了三个辅助任务, 包括数字间关系抽取、数值排序和片段替换预测。他们与生成目标联合训练, 用以监督解码器的学习, 增强模型对运算逻辑和问题条件的感知能力。实验证明所提方法能有效提升生成的数学文字题的质量。”
1 code implementation • 6 May 2023 • Shuzheng Si, Zefan Cai, Shuang Zeng, Guoqiang Feng, Jiaxing Lin, Baobao Chang
Distantly-Supervised Named Entity Recognition effectively alleviates the burden of time-consuming and expensive annotation in the supervised setting.
no code implementations • 20 May 2023 • Yufeng He, Zefan Cai, Xu Gan, Baobao Chang
Our method transforms discrete tokens in a natural way and applies continuous diffusion on them to successfully fuse extracted image features for diffusion caption generation.
no code implementations • 24 May 2023 • Zefan Cai, Xin Zheng, Tianyu Liu, Xu Wang, Haoran Meng, Jiaqi Han, Gang Yuan, Binghuai Lin, Baobao Chang, Yunbo Cao
In the constant updates of the product dialogue systems, we need to retrain the natural language understanding (NLU) model as new data from the real users would be merged into the existent data accumulated in the last updates.
no code implementations • 10 Jun 2023 • Zefan Cai, Baobao Chang, Wenjuan Han
While the emergence of powerful language models along with Chain-of-thought prompting has made automation more and more omnipresent, it sometimes demonstrates its weakness in long-term or multi-step logical reasoning.
no code implementations • NAACL 2022 • Shuzheng Si, Shuang Zeng, Baobao Chang
Then, we adopt a fast and effective edit operation scoring network to model the relation between two tokens.
no code implementations • 14 Nov 2023 • Helan Hu, Shuzheng Si, Haozhe Zhao, Shuang Zeng, Kaikai An, Zefan Cai, Baobao Chang
Distantly-Supervised Named Entity Recognition (DS-NER) effectively alleviates the burden of annotation, but meanwhile suffers from the label noise.
no code implementations • 15 Jan 2024 • Rongyu Zhang, Zefan Cai, Huanrui Yang, Zidong Liu, Denis Gudovskiy, Tomoyuki Okuno, Yohei Nakata, Kurt Keutzer, Baobao Chang, Yuan Du, Li Du, Shanghang Zhang
Finetuning a pretrained vision model (PVM) is a common technique for learning downstream vision tasks.
no code implementations • 5 Mar 2024 • Zefan Cai, Po-Nien Kung, Ashima Suvarna, Mingyu Derek Ma, Hritik Bansal, Baobao Chang, P. Jeffrey Brantingham, Wei Wang, Nanyun Peng
We hypothesize that a diverse set of event types and definitions are the key for models to learn to follow event definitions while existing event extraction datasets focus on annotating many high-quality examples for a few event types.