Pith. sign in

REVIEW

Comparison and Combination of Sentence Embeddings Derived from Different Supervision Signals

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2202.02990 v2 pith:4WP225DG submitted 2022-02-07 cs.CL

classification cs.CL
keywords sentencemethodstaskslanguagebeencomparedownstreamembedding
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original 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.

Discussion (0). Continue with ORCID to comment.

Pith tools