Discovering Aspectual Classes of Russian Verbs in Untagged Large Corpora

Aleksandr Drozd, Anna Gladkova, Satoshi Matsuoka

    Publikation: Konference artikel i Proceeding eller bog/rapport kapitelKonferencebidrag i proceedingsForskningpeer review

    Abstract

    This paper presents a case study of discovering and classifying verbs in large web-corpora. Many tasks in natural language processing require corpora containing billions of words, and with such volumes of data co-occurrence extraction becomes one of the performance bottlenecks in the Vector Space Models of computational linguistics. We propose a co-occurrence extraction kernel based on ternary trees as an alternative (or a complimentary stage) to conventional map-reduce based approach, this kernel achieves an order of magnitude improvement in memory footprint and processing speed. Our classifier successfully and efficiently identified verbs in a 1.2-billion words untagged corpus of Russian fiction and distinguished between their two aspectual classes. The model proved efficient even for low-frequency vocabulary, including nonce verbs and neologisms.
    OriginalsprogEngelsk
    TitelProceedings of 2015 IEEE International Conference on Data Science and Data Intensive Systems (DSDIS)
    Antal sider8
    Publikationsdato2015
    Sider61-68
    DOI
    StatusUdgivet - 2015

    Emneord

    • Verb Classification
    • Large Web-Corpora
    • Co-occurrence Extraction
    • Vector Space Models
    • Natural Language Processing

    Fingeraftryk

    Dyk ned i forskningsemnerne om 'Discovering Aspectual Classes of Russian Verbs in Untagged Large Corpora'. Sammen danner de et unikt fingeraftryk.

    Citationsformater