Contextual compositionality detection with external knowledge bases and word embeddings

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt


  • p317-wang

    Forlagets udgivne version, 810 KB, PDF-dokument

When the meaning of a phrase cannot be inferred from the individual meanings of its words (e.g., hot dog), that phrase is said to be non-compositional. Automatic compositionality detection in multiword phrases is critical in any application of semantic processing, such as search engines [9]; failing to detect non-compositional phrases can hurt system effectiveness notably. Existing research treats phrases as either compositional or non-compositional in a deterministic manner. In this paper, we operationalize the viewpoint that compositionality is contextual rather than deterministic, i.e., that whether a phrase is compositional or non-compositional depends on its context. For example, the phrase �green card� is compositional when referring to a green colored card, whereas it is non-compositional when meaning permanent residence authorization. We address the challenge of detecting this type of contextual compositionality as follows: given a multi-word phrase, we enrich the word embedding representing its semantics with evidence about its global context (terms it often collocates with) as well as its local context (narratives where that phrase is used, which we call usage scenarios). We further extend this representation with information extracted from external knowledge bases. The resulting representation incorporates both localized context and more general usage of the phrase and allows to detect its compositionality in a non-deterministic and contextual way. Empirical evaluation of our model on a dataset of phrase compositionality1, manually collected by crowdsourcing contextual compositionality assessments, shows that our model outperforms state-of-the-art baselines notably on detecting phrase compositionality.

TitelThe Web Conference 2019 - Companion of the World Wide Web Conference, WWW 2019
Antal sider7
ForlagAssociation for Computing Machinery
ISBN (Elektronisk)9781450366755
StatusUdgivet - 2019
Begivenhed2019 World Wide Web Conference, WWW 2019 - San Francisco, USA
Varighed: 13 maj 201917 maj 2019


Konference2019 World Wide Web Conference, WWW 2019
BySan Francisco
SponsorAmazon, Bloomberg, Criteo AI Lab, et al., Google, Microsoft

Antal downloads er baseret på statistik fra Google Scholar og

Ingen data tilgængelig

ID: 223251961