Papers › Semantic sentence similarity: size does not always matter

Semantic sentence similarity: size does not always matter

16 Jun 2021arXiv:2106.08648archive 2025-07-28

Danny Merkx, Stefan L. Frank, Mirjam Ernestus

This study addresses the question whether visually grounded speech recognition (VGS) models learn to capture sentence semantics without access to any prior linguistic knowledge. We produce synthetic and natural spoken versions of a well known semantic textual similarity database and show that our VGS model produces embeddings that correlate well with human semantic similarity judgements. Our results show that a model trained on a small image-caption database outperforms two models trained on much larger databases, indicating that database size is not all that matters. We also investigate the importance of having multiple captions per image and find that this is indeed helpful even if the total number of images is lower, suggesting that paraphrasing is a valuable learning signal. While the general trend in the field is to create ever larger datasets to train models on, our findings indicate other characteristics of the database can just as important important.

PaperPDFCode

Code

DannyMerkx/speech2image officialmentioned in papermentioned on GitHubpytorch 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

Grounded language learningImage RetrievalLearning Semantic RepresentationsSemantic SimilaritySemantic Textual SimilaritySentenceSentence EmbeddingsSentence SimilaritySpeech RecognitionVisual Groundingspeech-recognition

Datasets

Introduced by this paper, per the archive.

SpokenSTS

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamCyclical Learning Rate PolicyLSTMSigmoid ActivationTanh Activation

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