Logo: University of Southern California

Events Calendar


  • NL Seminar-Quantifying the morphosyntactic content of Brown Clusters

    Thu, May 30, 2019 @ 11:00 AM - 12:00 PM

    Information Sciences Institute

    Conferences, Lectures, & Seminars


    Speaker: Manuel Ciosici, Aarhus University

    Talk Title: Quantifying the morphosyntactic content of Brown Clusters

    Series: Natural Language Seminar

    Abstract: Brown and Exchange word clusters have long been successfully used as word representations in Natural Language Processing NLP systems. Their success has been attributed to their seeming ability to represent both semantic and syntactic information. Using corpora representing several language families, we test the hypothesis that Brown and Exchange word clusters are highly effective at encoding morphosyntactic information. Our experiments show that word clusters are highly capable of distinguishing Parts of Speech. We show that increases in Average Mutual Information, the clustering algorithms' optimization goal, are highly correlated with improvements in encoding of morphosyntactic information. Our results provide empirical evidence that downstream NLP systems addressing tasks dependent on morphosyntactic information can benefit from word cluster features.


    Biography: Manuel is a soon to graduate Ph.D. student at Aarhus University, Denmark. His research is focused on understanding the kinds of information encoded in word representations and how that information can be used in downstream NLP applications.

    Host: Xusen Yin

    More Info: https://nlg.isi.edu/nl-seminar

    Webcast: https://bluejeans.com/s/diiPj/

    Location: Information Science Institute (ISI) - CR #689

    WebCast Link: https://bluejeans.com/s/diiPj/

    Audiences: Everyone Is Invited

    Contact: Peter Zamar

    Event Link: https://nlg.isi.edu/nl-seminar

    Add to Google CalendarDownload ICS File for OutlookDownload iCal File

Return to Calendar