North American Chapter of the Association for Computational Linguistics最新文献_第3页

Grounding in social media: An approach to building a chit-chat dialogue model 社交媒体的基础:建立闲聊对话模型的方法

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-06-12 DOI: 10.48550/arXiv.2206.05696

Ritvik Choudhary, Daisuke Kawahara

引用次数: 2

Building a Personalized Dialogue System with Prompt-Tuning 建立一个个性化的对话系统与提示调整

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-06-11 DOI: 10.48550/arXiv.2206.05399

Tomohito Kasahara, Daisuke Kawahara, N. Tung, Sheng Li, K. Shinzato, Toshinori Sato

引用次数: 9

Defending Compositionality in Emergent Languages 在新兴语言中捍卫组合性

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-06-09 DOI: 10.48550/arXiv.2206.04751

Michal Auersperger, Pavel Pecina

引用次数: 4

Modularized Transfer Learning with Multiple Knowledge Graphs for Zero-shot Commonsense Reasoning 零shot常识推理的多知识图模块化迁移学习

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-06-08 DOI: 10.48550/arXiv.2206.03715

Yu Jin Kim, Beong-woo Kwak, Youngwook Kim, Reinald Kim Amplayo, Seung-won Hwang, Jinyoung Yeo

引用次数: 6

RAAT: Relation-Augmented Attention Transformer for Relation Modeling in Document-Level Event Extraction 文档级事件抽取中关系建模的关系增强注意转换器

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-06-07 DOI: 10.48550/arXiv.2206.03377

Yuan Liang, Zhuoxuan Jiang, Di Yin, Bo Ren

引用次数: 8

What do tokens know about their characters and how do they know it? 符号对它们的字符有什么了解?它们是怎么知道的?

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-06-06 DOI: 10.48550/arXiv.2206.02608

Ayush Kaushal, Kyle Mahowald

{"title":"What do tokens know about their characters and how do they know it?","authors":"Ayush Kaushal, Kyle Mahowald","doi":"10.48550/arXiv.2206.02608","DOIUrl":"https://doi.org/10.48550/arXiv.2206.02608","url":null,"abstract":"Pre-trained language models (PLMs) that use subword tokenization schemes can succeed at a variety of language tasks that require character-level information, despite lacking explicit access to the character composition of tokens. Here, studying a range of models (e.g., GPT- J, BERT, RoBERTa, GloVe), we probe what word pieces encode about character-level information by training classifiers to predict the presence or absence of a particular alphabetical character in a token, based on its embedding (e.g., probing whether the model embedding for “cat” encodes that it contains the character “a”). We find that these models robustly encode character-level information and, in general, larger models perform better at the task. We show that these results generalize to characters from non-Latin alphabets (Arabic, Devanagari, and Cyrillic). Then, through a series of experiments and analyses, we investigate the mechanisms through which PLMs acquire English-language character information during training and argue that this knowledge is acquired through multiple phenomena, including a systematic relationship between particular characters and particular parts of speech, as well as natural variability in the tokenization of related strings.","PeriodicalId":382084,"journal":{"name":"North American Chapter of the Association for Computational Linguistics","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114743008","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: 10

Neural Retriever and Go Beyond: A Thesis Proposal 神经寻回与超越:论文提案

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-05-31 DOI: 10.48550/arXiv.2205.16005

Man Luo

{"title":"Neural Retriever and Go Beyond: A Thesis Proposal","authors":"Man Luo","doi":"10.48550/arXiv.2205.16005","DOIUrl":"https://doi.org/10.48550/arXiv.2205.16005","url":null,"abstract":"Information Retriever (IR) aims to find the relevant documents (e.g. snippets, passages, and articles) to a given query at large scale. IR plays an important role in many tasks such as open domain question answering and dialogue systems, where external knowledge is needed. In the past, searching algorithms based on term matching have been widely used. Recently, neural-based algorithms (termed as neural retrievers) have gained more attention which can mitigate the limitations of traditional methods. Regardless of the success achieved by neural retrievers, they still face many challenges, e.g. suffering from a small amount of training data and failing to answer simple entity-centric questions. Furthermore, most of the existing neural retrievers are developed for pure-text query. This prevents them from handling multi-modality queries (i.e. the query is composed of textual description and images). This proposal has two goals. First, we introduce methods to address the abovementioned issues of neural retrievers from three angles, new model architectures, IR-oriented pretraining tasks, and generating large scale training data. Second, we identify the future research direction and propose potential corresponding solution.","PeriodicalId":382084,"journal":{"name":"North American Chapter of the Association for Computational Linguistics","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115637538","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: 1

Analyzing Modality Robustness in Multimodal Sentiment Analysis 多模态情感分析中的情态鲁棒性分析

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-05-30 DOI: 10.48550/arXiv.2205.15465

Devamanyu Hazarika, Yingting Li, Bo Cheng, Shuai Zhao, Roger Zimmermann, Soujanya Poria

引用次数: 11

Few-shot Subgoal Planning with Language Models 基于语言模型的次目标规划

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-05-28 DOI: 10.48550/arXiv.2205.14288

Lajanugen Logeswaran, Yao Fu, Moontae Lee, Honglak Lee

引用次数: 16

Relation-Specific Attentions over Entity Mentions for Enhanced Document-Level Relation Extraction 对实体提及的关系特定关注，用于增强文档级关系提取

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-05-28 DOI: 10.48550/arXiv.2205.14393

Jiaxin Yu, Deqing Yang, Shuyu Tian

引用次数: 12