Research Area:  Machine Learning
We present a novel approach to learn representations for sentence-level semantic similarity using conversational data. Our method trains an unsupervised model to predict conversational input-response pairs. The resulting sentence embeddings perform well on the semantic textual similarity (STS) benchmark and SemEval 2017 Community Question Answering (CQA) question similarity subtask. Performance is further improved by introducing multitask training combining the conversational input-response prediction task and a natural language inference task. Extensive experiments show the proposed model achieves the best performance among all neural models on the STS benchmark and is competitive with the state-of-the-art feature engineered and mixed systems in both tasks
Keywords:  
Semantic Textual Similarity
Machine Learning
Deep Learning
Author(s) Name:  Yinfei Yang, Steve Yuan, Daniel Cer, Sheng-yi Kong, Noah Constant, Petr Pilar, Heming Ge, Yun-Hsuan Sung, Brian Strope, Ray Kurzweil
Journal name:  Computer Science
Conferrence name:  
Publisher name:  arXiv:1804.07754
DOI:  10.48550/arXiv.1804.07754
Volume Information:  
Paper Link:   https://arxiv.org/abs/1804.07754