Learning Semantic Textual Similarity from Conversations

TL;DR

This paper introduces a new unsupervised method for learning sentence embeddings from conversational data, improving semantic similarity tasks and outperforming many existing neural models.

Contribution

The paper proposes a novel conversational data-based approach for semantic similarity learning, combining multitask training to enhance performance on benchmark datasets.

Findings

Achieves top performance on the STS benchmark

Performs well on SemEval 2017 CQA question similarity

Outperforms many neural models in semantic similarity tasks

Abstract

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's 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.