arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2007.14128cs.CLcs.LGstat.ML
收藏

BUT-FIT在SemEval-2020任务5:使用深度预训练的语言表示模型自动检测反事实陈述

BUT-FIT at SemEval-2020 Task 5: Automatic detection of counterfactual statements with deep pre-trained language representation models

Brno University of Technology(布尔诺理工大学)

Martin Fajcik, Josef Jon, Martin Docekal, Pavel Smrz

摘要:

本文介绍了BUT-FIT在SemEval-2020任务5:语言中的因果推理建模:检测反事实。挑战的重点是检测一个给定的陈述是否包含反事实(子任务1),并从文本中提取反事实的先行和后继部分(子任务2)。我们尝试了各种最先进的语言表示模型(LRM)。我们发现Roberta LRM在这两个子任务中表现最好。我们在子任务2的精确匹配和F1中都获得了第一名,在子任务1中排名第二。

英文摘要:

This paper describes BUT-FIT's submission at SemEval-2020 Task 5: Modelling Causal Reasoning in Language: Detecting Counterfactuals. The challenge focused on detecting whether a given statement contains a counterfactual (Subtask 1) and extracting both antecedent and consequent parts of the counterfactual from the text (Subtask 2). We experimented with various state-of-the-art language representation models (LRMs). We found RoBERTa LRM to perform the best in both subtasks. We achieved the first place in both exact match and F1 for Subtask 2 and ranked second for Subtask 1.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑