Papers › Evaluation of sentence embeddings in downstream and linguistic probing tasks

Evaluation of sentence embeddings in downstream and linguistic probing tasks

16 Jun 2018arXiv:1806.06259archive 2025-07-28

Christian S. Perone, Roberto Silveira, Thomas S. Paula

Despite the fast developmental pace of new sentence embedding methods, it is still challenging to find comprehensive evaluations of these different techniques. In the past years, we saw significant improvements in the field of sentence embeddings and especially towards the development of universal sentence encoders that could provide inductive transfer to a wide variety of downstream tasks. In this work, we perform a comprehensive evaluation of recent methods using a wide variety of downstream and linguistic feature probing tasks. We show that a simple approach using bag-of-words with a recently introduced language model for deep context-dependent word embeddings proved to yield better results in many tasks when compared to sentence encoders trained on entailment datasets. We also show, however, that we are still far away from a universal encoder that can perform consistently across several downstream tasks.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

14 repositories listed; official and paper-mentioned ones first.

allenai/bilm-tf mentioned on GitHubtfApache-2.0 report
cheng18/bilm-tf mentioned on GitHubtfApache-2.0 report
horizonheart/ELMO mentioned on GitHubtfApache-2.0 report
jvdbogae/artverc mentioned on GitHubApache-2.0 report
kunde122/bilm-tf mentioned on GitHubtfApache-2.0 report
mingdachen/bilm-tf mentioned on GitHubtf report
nlp-research/bilm-tf mentioned on GitHubtf report
seunghwan1228/ELMO mentioned on GitHubtfApache-2.0 report
shelleyHLX/bilm_EMLo mentioned on GitHubtf report
sidak/SentEval mentioned on GitHubpytorch report
weixsong/bilm-tf mentioned on GitHubtf report
yangzonglin1994/bilm-tf-extended mentioned on GitHubtfApache-2.0 report
young-zonglin/bilm-tf-extended mentioned on GitHubtfApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Language ModelingLanguage ModellingSentenceSentence EmbeddingSentence EmbeddingsSentence-EmbeddingWord Embeddings

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 Convolution

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections