Pith. sign in

REVIEW

Tracking linguistic information in transformer-based sentence embeddings through targeted sparsification

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 2407.18119 v1 pith:4JI2FUKM submitted 2024-07-25 cs.CL

classification cs.CL
keywords informationsentenceembeddingslinguisticmodelsanalysesinputtransformer-based
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Analyses of transformer-based models have shown that they encode a variety of linguistic information from their textual input. While these analyses have shed a light on the relation between linguistic information on one side, and internal architecture and parameters on the other, a question remains unanswered: how is this linguistic information reflected in sentence embeddings? Using datasets consisting of sentences with known structure, we test to what degree information about chunks (in particular noun, verb or prepositional phrases), such as grammatical number, or semantic role, can be localized in sentence embeddings. Our results show that such information is not distributed over the entire sentence embedding, but rather it is encoded in specific regions. Understanding how the information from an input text is compressed into sentence embeddings helps understand current transformer models and help build future explainable neural models.

Discussion (0). Continue with ORCID to comment.

Pith tools