North American Chapter of the Association for Computational Linguistics最新文献_第6页

EASE: Entity-Aware Contrastive Learning of Sentence Embedding 句子嵌入的实体感知对比学习

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-05-09 DOI: 10.48550/arXiv.2205.04260

Sosuke Nishikawa, Ryokan Ri, Ikuya Yamada, Yoshimasa Tsuruoka, I. Echizen

引用次数: 15

BLINK with Elasticsearch for Efficient Entity Linking in Business Conversations BLINK与Elasticsearch在商业对话中有效的实体链接

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-05-09 DOI: 10.48550/arXiv.2205.04438

Md Tahmid Rahman Laskar, Cheng Chen, Aliaksandr Martsinovich, Jonathan Johnston, Xue-Yong Fu, TN ShashiBhushan, Simon Corston-Oliver

引用次数: 14

ProQA: Structural Prompt-based Pre-training for Unified Question Answering ProQA:基于结构化提示的统一问答预训练

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-05-09 DOI: 10.48550/arXiv.2205.04040

Wanjun Zhong, Yifan Gao, Ning Ding, Yujia Qin, Zhiyuan Liu, Ming Zhou, Jiahai Wang, Jian Yin, Nan Duan

{"title":"ProQA: Structural Prompt-based Pre-training for Unified Question Answering","authors":"Wanjun Zhong, Yifan Gao, Ning Ding, Yujia Qin, Zhiyuan Liu, Ming Zhou, Jiahai Wang, Jian Yin, Nan Duan","doi":"10.48550/arXiv.2205.04040","DOIUrl":"https://doi.org/10.48550/arXiv.2205.04040","url":null,"abstract":"Question Answering (QA) is a longstanding challenge in natural language processing. Existing QA works mostly focus on specific question types, knowledge domains, or reasoning skills. The specialty in QA research hinders systems from modeling commonalities between tasks and generalization for wider applications. To address this issue, we present ProQA, a unified QA paradigm that solves various tasks through a single model. ProQA takes a unified structural prompt as the bridge and improves the QA-centric ability by structural prompt-based pre-training. Through a structurally designed prompt-based input schema, ProQA concurrently models the knowledge generalization for all QA tasks while keeping the knowledge customization for every specific QA task. Furthermore, ProQA is pre-trained with structural prompt-formatted large-scale synthesized corpus, which empowers the model with the commonly-required QA ability. Experimental results on 11 QA benchmarks demonstrate that ProQA consistently boosts performance on both full data fine-tuning, few-shot learning, and zero-shot testing scenarios. Furthermore, ProQA exhibits strong ability in both continual learning and transfer learning by taking the advantages of the structural prompt.","PeriodicalId":382084,"journal":{"name":"North American Chapter of the Association for Computational Linguistics","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125557960","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 21

Unsupervised Slot Schema Induction for Task-oriented Dialog 面向任务对话框的无监督槽模式归纳

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-05-09 DOI: 10.48550/arXiv.2205.04515

Dian Yu, Mingqiu Wang, Yuan Cao, Izhak Shafran, Laurent El Shafey, H. Soltau

引用次数: 8

Improving negation detection with negation-focused pre-training 以否定为中心的预训练改进否定检测

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-05-09 DOI: 10.48550/arXiv.2205.04012

Thinh Hung Truong, Timothy Baldwin, Trevor Cohn, K. Verspoor

引用次数: 9

Counterfactually Augmented Data and Unintended Bias: The Case of Sexism and Hate Speech Detection 反事实增强数据和意外偏见:性别歧视和仇恨言论检测的案例

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-05-09 DOI: 10.48550/arXiv.2205.04238

Indira Sen, Mattia Samory, Claudia Wagner, Isabelle Augenstein

引用次数: 11

Should We Rely on Entity Mentions for Relation Extraction? Debiasing Relation Extraction with Counterfactual Analysis 我们应该依赖实体提及来提取关系吗?反事实分析的去偏关系提取

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-05-08 DOI: 10.48550/arXiv.2205.03784

Yiwei Wang, Muhao Chen, Wenxuan Zhou, Yujun Cai, Yuxuan Liang, Dayiheng Liu, Baosong Yang, Juncheng Liu, Bryan Hooi

{"title":"Should We Rely on Entity Mentions for Relation Extraction? Debiasing Relation Extraction with Counterfactual Analysis","authors":"Yiwei Wang, Muhao Chen, Wenxuan Zhou, Yujun Cai, Yuxuan Liang, Dayiheng Liu, Baosong Yang, Juncheng Liu, Bryan Hooi","doi":"10.48550/arXiv.2205.03784","DOIUrl":"https://doi.org/10.48550/arXiv.2205.03784","url":null,"abstract":"Recent literature focuses on utilizing the entity information in the sentence-level relation extraction (RE), but this risks leaking superficial and spurious clues of relations. As a result, RE still suffers from unintended entity bias, i.e., the spurious correlation between entity mentions (names) and relations. Entity bias can mislead the RE models to extract the relations that do not exist in the text. To combat this issue, some previous work masks the entity mentions to prevent the RE models from over-fitting entity mentions. However, this strategy degrades the RE performance because it loses the semantic information of entities. In this paper, we propose the CoRE (Counterfactual Analysis based Relation Extraction) debiasing method that guides the RE models to focus on the main effects of textual context without losing the entity information. We first construct a causal graph for RE, which models the dependencies between variables in RE models. Then, we propose to conduct counterfactual analysis on our causal graph to distill and mitigate the entity bias, that captures the causal effects of specific entity mentions in each instance. Note that our CoRE method is model-agnostic to debias existing RE systems during inference without changing their training processes. Extensive experimental results demonstrate that our CoRE yields significant gains on both effectiveness and generalization for RE. The source code is provided at: https://github.com/vanoracai/CoRE.","PeriodicalId":382084,"journal":{"name":"North American Chapter of the Association for Computational Linguistics","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127476181","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 23

A Structured Span Selector 结构化Span选择器

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-05-08 DOI: 10.18653/v1/2022.naacl-main.189

Tianyu Liu, Yuchen Jiang, Ryan Cotterell, Mrinmaya Sachan

引用次数: 4

Context-Aware Abbreviation Expansion Using Large Language Models 使用大型语言模型的上下文感知缩写扩展

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-05-08 DOI: 10.48550/arXiv.2205.03767

Shanqing Cai, Subhashini Venugopalan, K. Tomanek, Ajit Narayanan, M. Morris, Michael P. Brenner

{"title":"Context-Aware Abbreviation Expansion Using Large Language Models","authors":"Shanqing Cai, Subhashini Venugopalan, K. Tomanek, Ajit Narayanan, M. Morris, Michael P. Brenner","doi":"10.48550/arXiv.2205.03767","DOIUrl":"https://doi.org/10.48550/arXiv.2205.03767","url":null,"abstract":"Motivated by the need for accelerating text entry in augmentative and alternative communication (AAC) for people with severe motor impairments, we propose a paradigm in which phrases are abbreviated aggressively as primarily word-initial letters. Our approach is to expand the abbreviations into full-phrase options by leveraging conversation context with the power of pretrained large language models (LLMs). Through zero-shot, few-shot, and fine-tuning experiments on four public conversation datasets, we show that for replies to the initial turn of a dialog, an LLM with 64B parameters is able to exactly expand over 70% of phrases with abbreviation length up to 10, leading to an effective keystroke saving rate of up to about 77% on these exact expansions. Including a small amount of context in the form of a single conversation turn more than doubles abbreviation expansion accuracies compared to having no context, an effect that is more pronounced for longer phrases. Additionally, the robustness of models against typo noise can be enhanced through fine-tuning on noisy data.","PeriodicalId":382084,"journal":{"name":"North American Chapter of the Association for Computational Linguistics","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124828850","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 12

CORWA: A Citation-Oriented Related Work Annotation Dataset CORWA:一个面向引用的相关工作注释数据集

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-05-07 DOI: 10.48550/arXiv.2205.03512

Xiangci Li, Biswadip Mandal, Jessica Ouyang

{"title":"CORWA: A Citation-Oriented Related Work Annotation Dataset","authors":"Xiangci Li, Biswadip Mandal, Jessica Ouyang","doi":"10.48550/arXiv.2205.03512","DOIUrl":"https://doi.org/10.48550/arXiv.2205.03512","url":null,"abstract":"Academic research is an exploratory activity to discover new solutions to problems. By this nature, academic research works perform literature reviews to distinguish their novelties from prior work. In natural language processing, this literature review is usually conducted under the “Related Work” section. The task of related work generation aims to automatically generate the related work section given the rest of the research paper and a list of papers to cite. Prior work on this task has focused on the sentence as the basic unit of generation, neglecting the fact that related work sections consist of variable length text fragments derived from different information sources. As a first step toward a linguistically-motivated related work generation framework, we present a Citation Oriented Related Work Annotation (CORWA) dataset that labels different types of citation text fragments from different information sources. We train a strong baseline model that automatically tags the CORWA labels on massive unlabeled related work section texts. We further suggest a novel framework for human-in-the-loop, iterative, abstractive related work generation.","PeriodicalId":382084,"journal":{"name":"North American Chapter of the Association for Computational Linguistics","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126722731","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5