English

Comparison and Combination of Sentence Embeddings Derived from Different Supervision Signals

Computation and Language 2022-06-13 v2

Abstract

There have been many successful applications of sentence embedding methods. However, it has not been well understood what properties are captured in the resulting sentence embeddings depending on the supervision signals. In this paper, we focus on two types of sentence embedding methods with similar architectures and tasks: one fine-tunes pre-trained language models on the natural language inference task, and the other fine-tunes pre-trained language models on word prediction task from its definition sentence, and investigate their properties. Specifically, we compare their performances on semantic textual similarity (STS) tasks using STS datasets partitioned from two perspectives: 1) sentence source and 2) superficial similarity of the sentence pairs, and compare their performances on the downstream and probing tasks. Furthermore, we attempt to combine the two methods and demonstrate that combining the two methods yields substantially better performance than the respective methods on unsupervised STS tasks and downstream tasks.

Keywords

Cite

@article{arxiv.2202.02990,
  title  = {Comparison and Combination of Sentence Embeddings Derived from Different Supervision Signals},
  author = {Hayato Tsukagoshi and Ryohei Sasano and Koichi Takeda},
  journal= {arXiv preprint arXiv:2202.02990},
  year   = {2022}
}

Comments

Accepted at *SEM 2022