Transactions of the Association for Computational Linguistics最新文献_第8页

On the Role of Negative Precedent in Legal Outcome Prediction 论负面先例在法律结果预测中的作用

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2022-08-17 DOI: 10.1162/tacl_a_00532

Josef Valvoda, Ryan Cotterell, Simone Teufel

{"title":"On the Role of Negative Precedent in Legal Outcome Prediction","authors":"Josef Valvoda, Ryan Cotterell, Simone Teufel","doi":"10.1162/tacl_a_00532","DOIUrl":"https://doi.org/10.1162/tacl_a_00532","url":null,"abstract":"Every legal case sets a precedent by developing the law in one of the following two ways. It either expands its scope, in which case it sets positive precedent, or it narrows it, in which case it sets negative precedent. Legal outcome prediction, the prediction of positive outcome, is an increasingly popular task in AI. In contrast, we turn our focus to negative outcomes here, and introduce a new task of negative outcome prediction. We discover an asymmetry in existing models’ ability to predict positive and negative outcomes. Where the state-of-the-art outcome prediction model we used predicts positive outcomes at 75.06 F1, it predicts negative outcomes at only 10.09 F1, worse than a random baseline. To address this performance gap, we develop two new models inspired by the dynamics of a court process. Our first model significantly improves positive outcome prediction score to 77.15 F1 and our second model more than doubles the negative outcome prediction performance to 24.01 F1. Despite this improvement, shifting focus to negative outcomes reveals that there is still much room for improvement for outcome prediction models. https://github.com/valvoda/Negative-Precedent-in-Legal-Outcome-Prediction","PeriodicalId":33559,"journal":{"name":"Transactions of the Association for Computational Linguistics","volume":"11 1","pages":"34-48"},"PeriodicalIF":10.9,"publicationDate":"2022-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48320538","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: 10

MENLI: Robust Evaluation Metrics from Natural Language Inference MENLI:来自自然语言推理的鲁棒评估指标

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2022-08-15 DOI: 10.1162/tacl_a_00576

Yanran Chen, Steffen Eger

引用次数: 10

Multi-task Active Learning for Pre-trained Transformer-based Models 基于预训练变压器模型的多任务主动学习

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2022-08-10 DOI: 10.1162/tacl_a_00515

Guy Rotman, Roi Reichart

引用次数: 10

Compositional Evaluation on Japanese Textual Entailment and Similarity 日语语篇纠缠与相似性的作文评价

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2022-08-09 DOI: 10.1162/tacl_a_00518

Hitomi Yanaka, K. Mineshima

{"title":"Compositional Evaluation on Japanese Textual Entailment and Similarity","authors":"Hitomi Yanaka, K. Mineshima","doi":"10.1162/tacl_a_00518","DOIUrl":"https://doi.org/10.1162/tacl_a_00518","url":null,"abstract":"Abstract Natural Language Inference (NLI) and Semantic Textual Similarity (STS) are widely used benchmark tasks for compositional evaluation of pre-trained language models. Despite growing interest in linguistic universals, most NLI/STS studies have focused almost exclusively on English. In particular, there are no available multilingual NLI/STS datasets in Japanese, which is typologically different from English and can shed light on the currently controversial behavior of language models in matters such as sensitivity to word order and case particles. Against this background, we introduce JSICK, a Japanese NLI/STS dataset that was manually translated from the English dataset SICK. We also present a stress-test dataset for compositional inference, created by transforming syntactic structures of sentences in JSICK to investigate whether language models are sensitive to word order and case particles. We conduct baseline experiments on different pre-trained language models and compare the performance of multilingual models when applied to Japanese and other languages. The results of the stress-test experiments suggest that the current pre-trained language models are insensitive to word order and case marking.","PeriodicalId":33559,"journal":{"name":"Transactions of the Association for Computational Linguistics","volume":"10 1","pages":"1266-1284"},"PeriodicalIF":10.9,"publicationDate":"2022-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43354036","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: 8

Abstractive Meeting Summarization: A Survey 摘要会议综述

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2022-08-08 DOI: 10.1162/tacl_a_00578

Virgile Rennard, Guokan Shang, Julie Hunter, M. Vazirgiannis

引用次数: 5

Template-based Abstractive Microblog Opinion Summarization 基于模板的微博意见摘要

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2022-08-08 DOI: 10.1162/tacl_a_00516

I. Bilal, Bo Wang, A. Tsakalidis, Dong Nguyen, R. Procter, M. Liakata

引用次数: 3

Multilingual Coreference Resolution in Multiparty Dialogue 多方对话中的多语言共指解决

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2022-08-02 DOI: 10.1162/tacl_a_00581

Boyuan Zheng, Patrick Xia, M. Yarmohammadi, Benjamin Van Durme

引用次数: 0

Efficient Long-Text Understanding with Short-Text Models 利用短文本模型实现长文本的高效理解

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2022-08-01 DOI: 10.1162/tacl_a_00547

Maor Ivgi, Uri Shaham, Jonathan Berant

{"title":"Efficient Long-Text Understanding with Short-Text Models","authors":"Maor Ivgi, Uri Shaham, Jonathan Berant","doi":"10.1162/tacl_a_00547","DOIUrl":"https://doi.org/10.1162/tacl_a_00547","url":null,"abstract":"Transformer-based pretrained language models (LMs) are ubiquitous across natural language understanding, but cannot be applied to long sequences such as stories, scientific articles, and long documents due to their quadratic complexity. While a myriad of efficient transformer variants have been proposed, they are typically based on custom implementations that require expensive pretraining from scratch. In this work, we propose SLED: SLiding-Encoder and Decoder, a simple approach for processing long sequences that re-uses and leverages battle-tested short-text pretrained LMs. Specifically, we partition the input into overlapping chunks, encode each with a short-text LM encoder and use the pretrained decoder to fuse information across chunks (fusion-in-decoder). We illustrate through controlled experiments that SLED offers a viable strategy for long text understanding and evaluate our approach on SCROLLS, a benchmark with seven datasets across a wide range of language understanding tasks. We find that SLED is competitive with specialized models that are up to 50x larger and require a dedicated and expensive pretraining step.","PeriodicalId":33559,"journal":{"name":"Transactions of the Association for Computational Linguistics","volume":"11 1","pages":"284-299"},"PeriodicalIF":10.9,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42297630","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: 21

Aggretriever: A Simple Approach to Aggregate Textual Representations for Robust Dense Passage Retrieval 聚合检索器：一种用于鲁棒密集通道检索的聚合文本表示的简单方法

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2022-07-31 DOI: 10.1162/tacl_a_00556

Sheng-Chieh Lin, Minghan Li, Jimmy Lin

引用次数: 8

Unit Testing for Concepts in Neural Networks 神经网络概念的单元测试

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2022-07-28 DOI: 10.1162/tacl_a_00514

Charles Lovering, Elizabeth-Jane Pavlick

引用次数: 16