Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
作者： Nils Reimers , Iryna Gurevych
DOI: 10.18653/V1/D19-1410
关键词:
摘要: BERT (Devlin et al., 2018) and RoBERTa (Liu et al., 2019) has set a new state-of-the-art performance on sentence-pair regression tasks like semantic textual similarity (STS). However, it requires that both sentences are fed into the network, which causes a massive computational overhead: Finding the most similar pair in a collection of 10,000 sentences requires about 50 million inference computations (~ 65 hours) with BERT. The construction of BERT makes it unsuitable for semantic similarity search as well as for unsupervised tasks …
aclweb.org
tu-darmstadt.de
arxiv.org参考文章(37)
Ryan Kiros, Yukun Zhu, Ruslan R Salakhutdinov, Richard Zemel, Raquel Urtasun, Antonio Torralba, Sanja Fidler, None, Skip-thought vectors neural information processing systems. ,vol. 28, pp. 3294- 3302 ,(2015)
Samuel R. Bowman, Gabor Angeli, Christopher Potts, Christopher D. Manning, A large annotated corpus for learning natural language inference empirical methods in natural language processing. pp. 632- 642 ,(2015) , 10.18653/V1/D15-1075
Bill Dolan, Chris Quirk, Chris Brockett, Unsupervised construction of large paraphrase corpora Proceedings of the 20th international conference on Computational Linguistics - COLING '04. pp. 350- 356 ,(2004) , 10.3115/1220355.1220406
Janyce Wiebe, Theresa Wilson, Claire Cardie, Annotating Expressions of Opinions and Emotions in Language language resources and evaluation. ,vol. 39, pp. 165- 210 ,(2005) , 10.1007/S10579-005-7880-9
Xin Li Dan, Xin Li, Dan Roth, Learning question classifiers Proceedings of the 19th international conference on Computational linguistics -. pp. 1- 7 ,(2002) , 10.3115/1072228.1072378
Florian Schroff, Dmitry Kalenichenko, James Philbin, FaceNet: A unified embedding for face recognition and clustering computer vision and pattern recognition. pp. 815- 823 ,(2015) , 10.1109/CVPR.2015.7298682
Bo Pang, Lillian Lee, A Sentimental Education: Sentiment Analysis Using Subjectivity Summarization Based on Minimum Cuts meeting of the association for computational linguistics. pp. 271- 278 ,(2004) , 10.3115/1218955.1218990
Eneko Agirre, Carmen Banea, Claire Cardie, Daniel Cer, Mona Diab, Aitor Gonzalez-Agirre, Weiwei Guo, Rada Mihalcea, German Rigau, Janyce Wiebe, SemEval-2014 Task 10: Multilingual Semantic Textual Similarity Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014). pp. 81- 91 ,(2014) , 10.3115/V1/S14-2010
Aitor Gonzalez-Agirre, Eneko Agirre, Weiwei Guo, Mona Diab, Daniel Cer, *SEM 2013 shared task: Semantic Textual Similarity joint conference on lexical and computational semantics. ,vol. 1, pp. 32- 43 ,(2013)
Minqing Hu, Bing Liu, Mining and summarizing customer reviews knowledge discovery and data mining. pp. 168- 177 ,(2004) , 10.1145/1014052.1014073