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 1904.03339cs.CL
收藏

SemEval-2019上的ThisIsCompetition任务9:域外样本的BERT不稳定

ThisIsCompetition at SemEval-2019 Task 9: BERT is unstable for out-of-domain samples

Kangwon National University(江原国立大学);Sogang University(西江大学);University of Edinburgh(爱丁堡大学)

Cheoneum Park, Juae Kim, Hyeon-gu Lee, Reinald Kim Amplayo, Harksoo Kim, Jungyun Seo, Changki Lee

摘要:

本文介绍了我们的系统,稳定建议推理联合编码器(JESSI),用于SemEval 2019任务9:从在线评论和论坛中挖掘建议。JESSI是两个句子编码器的组合:(a)一个使用从对数双线性回归(GloVe)和翻译(CoVe)模型学习的多个预训练词嵌入,以及(b)一个来自预训练深度双向Transformer(BERT)的单词编码。在训练域外样本时,我们包含了一个域对抗训练模块。我们的实验表明,虽然BERT在域内样本中表现得非常好,但模型的几次运行表明,它对域外样本是不稳定的。通过(1)将BERT与非BERT编码器相结合,以及(2)在BERT之上使用基于RNN的分类器,可以极大地缓解该问题。我们的最终模型在子任务A(即域内)上以77.78%的F分数获得第二名,在子任务B(即域外)上获得了79.59%的F分数,即使没有使用任何额外的外部数据。

英文摘要:

This paper describes our system, Joint Encoders for Stable Suggestion Inference (JESSI), for the SemEval 2019 Task 9: Suggestion Mining from Online Reviews and Forums. JESSI is a combination of two sentence encoders: (a) one using multiple pre-trained word embeddings learned from log-bilinear regression (GloVe) and translation (CoVe) models, and (b) one on top of word encodings from a pre-trained deep bidirectional transformer (BERT). We include a domain adversarial training module when training for out-of-domain samples. Our experiments show that while BERT performs exceptionally well for in-domain samples, several runs of the model show that it is unstable for out-of-domain samples. The problem is mitigated tremendously by (1) combining BERT with a non-BERT encoder, and (2) using an RNN-based classifier on top of BERT. Our final models obtained second place with 77.78\% F-Score on Subtask A (i.e. in-domain) and achieved an F-Score of 79.59\% on Subtask B (i.e. out-of-domain), even without using any additional external data.

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。

↑