Transactions of the Association for Computational Linguistics最新文献_第6页

DMDD: A Large-Scale Dataset for Dataset Mentions Detection DMDD:用于数据集提及检测的大规模数据集

1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2023-01-01 DOI: 10.1162/tacl_a_00592

Huitong Pan, Qi Zhang, Eduard Dragut, Cornelia Caragea, Longin Jan Latecki

引用次数: 2

Dubbing in Practice: A Large Scale Study of Human Localization With Insights for Automatic Dubbing 实践中的配音：一个大规模的人类本地化研究——对自动配音的见解

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2022-12-23 DOI: 10.1162/tacl_a_00551

William Brannon, Yogesh Virkar, Brian Thompson

引用次数: 8

Why Does Surprisal From Larger Transformer-Based Language Models Provide a Poorer Fit to Human Reading Times? 为什么更大的基于变压器的语言模型提供的惊喜更不适合人类的阅读时间?

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2022-12-23 DOI: 10.1162/tacl_a_00548

Byung-Doh Oh, William Schuler

引用次数: 30

Assessing the Capacity of Transformer to Abstract Syntactic Representations: A Contrastive Analysis Based on Long-distance Agreement 变压器抽象句法表征能力的评估——基于长距离一致性的对比分析

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2022-12-08 DOI: 10.1162/tacl_a_00531

Bingzhi Li, Guillaume Wisniewski, Benoit Crabb'e

引用次数: 3

The Emergence of Argument Structure in Artificial Languages 论人工语言中论证结构的产生

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2022-12-01 DOI: 10.1162/tacl_a_00524

Tom Bosc, Pascal Vincent

{"title":"The Emergence of Argument Structure in Artificial Languages","authors":"Tom Bosc, Pascal Vincent","doi":"10.1162/tacl_a_00524","DOIUrl":"https://doi.org/10.1162/tacl_a_00524","url":null,"abstract":"Abstract Computational approaches to the study of language emergence can help us understand how natural languages are shaped by cognitive and sociocultural factors. Previous work focused on tasks where agents refer to a single entity. In contrast, we study how agents predicate, that is, how they express that some relation holds between several entities. We introduce a setup where agents talk about a variable number of entities that can be partially observed by the listener. In the presence of a least-effort pressure, they tend to discuss only entities that are not observed by the listener. Thus we can obtain artificial phrases that denote a single entity, as well as artificial sentences that denote several entities. In natural languages, if we ignore the verb, phrases are usually concatenated, either in a specific order or by adding case markers to form sentences. Our setup allows us to quantify how much this holds in emergent languages using a metric we call concatenability. We also measure transitivity, which quantifies the importance of word order. We demonstrate the usefulness of this new setup and metrics for studying factors that influence argument structure. We compare agents having access to input representations structured into pre-segmented objects with properties, versus unstructured representations. Our results indicate that the awareness of object structure yields a more natural sentence organization.","PeriodicalId":33559,"journal":{"name":"Transactions of the Association for Computational Linguistics","volume":"10 1","pages":"1375-1391"},"PeriodicalIF":10.9,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42504304","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Coreference Resolution through a seq2seq Transition-Based System 基于seq2seq转换系统的共参解析

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2022-11-22 DOI: 10.1162/tacl_a_00543

Bernd Bohnet, Chris Alberti, Michael Collins

引用次数: 6

MACSum: Controllable Summarization with Mixed Attributes MACSum:混合属性的可控摘要

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2022-11-09 DOI: 10.1162/tacl_a_00575

Yusen Zhang, Yang Liu, Ziyi Yang, Yuwei Fang, Yulong Chen, Dragomir R. Radev, Chenguang Zhu, Michael Zeng, Rui Zhang

{"title":"MACSum: Controllable Summarization with Mixed Attributes","authors":"Yusen Zhang, Yang Liu, Ziyi Yang, Yuwei Fang, Yulong Chen, Dragomir R. Radev, Chenguang Zhu, Michael Zeng, Rui Zhang","doi":"10.1162/tacl_a_00575","DOIUrl":"https://doi.org/10.1162/tacl_a_00575","url":null,"abstract":"Abstract Controllable summarization allows users to generate customized summaries with specified attributes. However, due to the lack of designated annotations of controlled summaries, existing work has to craft pseudo datasets by adapting generic summarization benchmarks. Furthermore, most research focuses on controlling single attributes individually (e.g., a short summary or a highly abstractive summary) rather than controlling a mix of attributes together (e.g., a short and highly abstractive summary). In this paper, we propose MACSum, the first human-annotated summarization dataset for controlling mixed attributes. It contains source texts from two domains, news articles and dialogues, with human-annotated summaries controlled by five designed attributes (Length, Extractiveness, Specificity, Topic, and Speaker). We propose two simple and effective parameter-efficient approaches for the new task of mixed controllable summarization based on hard prompt tuning and soft prefix tuning. Results and analysis demonstrate that hard prompt models yield the best performance on most metrics and human evaluations. However, mixed-attribute control is still challenging for summarization tasks. Our dataset and code are available at https://github.com/psunlpgroup/MACSum.","PeriodicalId":33559,"journal":{"name":"Transactions of the Association for Computational Linguistics","volume":"11 1","pages":"787-803"},"PeriodicalIF":10.9,"publicationDate":"2022-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46946847","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 6

An End-to-End Contrastive Self-Supervised Learning Framework for Language Understanding 语言理解的端到端对比自监督学习框架

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2022-11-01 DOI: 10.1162/tacl_a_00521

Hongchao Fang, P. Xie

{"title":"An End-to-End Contrastive Self-Supervised Learning Framework for Language Understanding","authors":"Hongchao Fang, P. Xie","doi":"10.1162/tacl_a_00521","DOIUrl":"https://doi.org/10.1162/tacl_a_00521","url":null,"abstract":"Abstract Self-supervised learning (SSL) methods such as Word2vec, BERT, and GPT have shown great effectiveness in language understanding. Contrastive learning, as a recent SSL approach, has attracted increasing attention in NLP. Contrastive learning learns data representations by predicting whether two augmented data instances are generated from the same original data example. Previous contrastive learning methods perform data augmentation and contrastive learning separately. As a result, the augmented data may not be optimal for contrastive learning. To address this problem, we propose a four-level optimization framework that performs data augmentation and contrastive learning end-to-end, to enable the augmented data to be tailored to the contrastive learning task. This framework consists of four learning stages, including training machine translation models for sentence augmentation, pretraining a text encoder using contrastive learning, finetuning a text classification model, and updating weights of translation data by minimizing the validation loss of the classification model, which are performed in a unified way. Experiments on datasets in the GLUE benchmark (Wang et al., 2018a) and on datasets used in Gururangan et al. (2020) demonstrate the effectiveness of our method.","PeriodicalId":33559,"journal":{"name":"Transactions of the Association for Computational Linguistics","volume":"10 1","pages":"1324-1340"},"PeriodicalIF":10.9,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47193269","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Helpful Neighbors: Leveraging Neighbors in Geographic Feature Pronunciation 有帮助的邻居:利用邻居的地理特征发音

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2022-10-18 DOI: 10.1162/tacl_a_00535

Llion Jones, R. Sproat, Haruko Ishikawa, Alexander Gutkin

引用次数: 1

Improving Low-Resource Cross-lingual Parsing with Expected Statistic Regularization 利用期望统计正则化改进低资源跨语言解析

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2022-10-17 DOI: 10.1162/tacl_a_00537

Thomas Effland, Michael Collins

引用次数: 1