Contextual compositionality detection with external knowledge bases and word embeddings

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review


  • p317-wang

    Final published version, 810 KB, PDF document

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.

Original languageEnglish
Title of host publicationThe Web Conference 2019 - Companion of the World Wide Web Conference, WWW 2019
Number of pages7
PublisherAssociation for Computing Machinery
Publication date2019
ISBN (Electronic)9781450366755
Publication statusPublished - 2019
Event2019 World Wide Web Conference, WWW 2019 - San Francisco, United States
Duration: 13 May 201917 May 2019


Conference2019 World Wide Web Conference, WWW 2019
LandUnited States
BySan Francisco
SponsorAmazon, Bloomberg, Criteo AI Lab, et al., Google, Microsoft

    Research areas

  • Compositionality detection, Knowledge base, Word embedding

Number of downloads are based on statistics from Google Scholar and

No data available

ID: 223251961