Papers › pair2vec: Compositional Word-Pair Embeddings for Cross-Sentence Inference

pair2vec: Compositional Word-Pair Embeddings for Cross-Sentence Inference

20 Oct 2018NAACL 2019 6arXiv:1810.08854archive 2025-07-28

Mandar Joshi, Eunsol Choi, Omer Levy, Daniel S. Weld, Luke Zettlemoyer

Reasoning about implied relationships (e.g., paraphrastic, common sense, encyclopedic) between pairs of words is crucial for many cross-sentence inference problems. This paper proposes new methods for learning and using embeddings of word pairs that implicitly represent background knowledge about such relationships. Our pairwise embeddings are computed as a compositional function on word representations, which is learned by maximizing the pointwise mutual information (PMI) with the contexts in which the two words co-occur. We add these representations to the cross-sentence attention layer of existing inference models (e.g. BiDAF for QA, ESIM for NLI), instead of extending or replacing existing word embeddings. Experiments show a gain of 2.7% on the recently released SQuAD2.0 and 1.3% on MultiNLI. Our representations also aid in better generalization with gains of around 6-7% on adversarial SQuAD datasets, and 8.8% on the adversarial entailment test set by Glockner et al. (2018).

PaperPDFConference PDFCode

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

Code

mandarjoshi90/pair2vec officialmentioned in papermentioned on GitHubpytorch report
asahi417/relbert mentioned on GitHubMIT 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

Common Sense ReasoningSentenceWord Embeddings

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ESIM

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