On the compositionality prediction of noun phrases using poincaré embeddings

Abhik Jana, Dmitry Puzyrev, Alexander Panchenko, Pawan Goyal, Chris Biemann, Animesh Mukherjee

    Результат исследований: Глава в книге, отчете, сборнике статейМатериалы для конференциирецензирование

    5 Цитирования (Scopus)

    Аннотация

    The compositionality degree of multiword expressions indicates to what extent the meaning of a phrase can be derived from the meaning of its constituents and their grammatical relations. Prediction of (non)-compositionality is a task that has been frequently addressed with distributional semantic models. We introduce a novel technique to blend hierarchical information with distributional information for predicting compositionality. In particular, we use hypernymy information of the multiword and its constituents encoded in the form of the recently introduced Poincaré embeddings in addition to the distributional information to detect compositionality for noun phrases. Using a weighted average of the distributional similarity and a Poincaré similarity function, we obtain consistent and substantial, statistically significant improvement across three gold standard datasets over state-of-the-art models based on distributional information only. Unlike traditional approaches that solely use an unsupervised setting, we have also framed the problem as a supervised task, obtaining comparable improvements. Further, we publicly release our Poincaré embeddings, which are trained on the output of handcrafted lexical-syntactic patterns on a large corpus.

    Язык оригиналаАнглийский
    Название основной публикацииACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
    ИздательAssociation for Computational Linguistics (ACL)
    Страницы3263-3274
    Число страниц12
    ISBN (электронное издание)9781950737482
    СостояниеОпубликовано - 2020
    Событие57th Annual Meeting of the Association for Computational Linguistics, ACL 2019 - Florence, Италия
    Продолжительность: 28 июл. 20192 авг. 2019

    Серия публикаций

    НазваниеACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference

    Конференция

    Конференция57th Annual Meeting of the Association for Computational Linguistics, ACL 2019
    Страна/TерриторияИталия
    ГородFlorence
    Период28/07/192/08/19

    Fingerprint

    Подробные сведения о темах исследования «On the compositionality prediction of noun phrases using poincaré embeddings». Вместе они формируют уникальный семантический отпечаток (fingerprint).

    Цитировать