Paraphrase Thought: Sentence Embedding Module Imitating Human Language Recognition

TL;DR

This paper introduces the Paraphrase-Thought model, inspired by human language recognition, to generate sentence embeddings that better capture semantic coherence, leading to improved performance on paraphrase identification tasks.

Contribution

The paper proposes a novel sentence embedding model that emphasizes semantic coherence inspired by human language recognition, outperforming existing methods on benchmark datasets.

Findings

P-thought outperforms benchmarked sentence embedding methods on MS COCO and STS datasets.

The model emphasizes semantic coherence by ensuring similar sentences are close in embedding space.

Experimental results validate the effectiveness of the proposed approach.

Abstract

Sentence embedding is an important research topic in natural language processing. It is essential to generate a good embedding vector that fully reflects the semantic meaning of a sentence in order to achieve an enhanced performance for various natural language processing tasks, such as machine translation and document classification. Thus far, various sentence embedding models have been proposed, and their feasibility has been demonstrated through good performances on tasks following embedding, such as sentiment analysis and sentence classification. However, because the performances of sentence classification and sentiment analysis can be enhanced by using a simple sentence representation method, it is not sufficient to claim that these models fully reflect the meanings of sentences based on good performances for such tasks. In this paper, inspired by human language recognition, we propose the following concept of semantic coherence, which should be satisfied for a good sentence embedding method: similar sentences should be located close to each other in the embedding space. Then, we propose the Paraphrase-Thought (P-thought) model to pursue semantic coherence as much as possible. Experimental results on two paraphrase identification datasets (MS COCO and STS benchmark) show that the P-thought models outperform the benchmarked sentence embedding methods.