Till sidans topp

Sidansvarig: Webbredaktionen
Sidan uppdaterades: 2016-04-11 13:37

Tipsa en vän
Utskriftsversion

Luis Nieto Piña, slutseminarium - Göteborgs universitet Till startsida
Webbkarta
Till innehåll Läs mer om hur kakor används på gu.se

Luis Nieto Piña, slutseminarium

Doktorandseminarium

Luis Nieto Piña, doktorand i språkvetenskaplig databehandling, håller sitt slutseminarium.

Underlag finns under Seminarieartiklar på det lokala intranätet för personal vid institutionen för svenska språket. Du behöver logga in med ditt personliga lösenord.

Om du inte har möjlighet att logga in på intranätet, kontakta Luis Nieto Piña för underlag.


Abstract
Representation of written language semantics is a crucial component of many natural language processing applications, from part-of-speech tagging to text summarization. These representations allow computer applications that work with language to process and manipulate the meaning of text. In the last few years, a family of models have been successfully developed based on automatically embedding semantics from large collections of text into a vector space, where semantic and lexical similarity is a function of geometric distance. Such models have typically been applied to learning representations for word forms, which have been widely applied, and proven to be highly successful, as characterizations of semantics at the word level. However, a word-level approach to representing semantics suffers from conflation of several word senses into one representation in the case of polysemic words: by assigning one representation to each word, the different meanings of polysemic words are bundled together into one representation.

In this thesis, we present a number of models that try to tackle this problem by automatically learning representations for word senses instead of for words. In particular, we try to achieve this by using two separate sources of information: corpora and lexica for the Swedish language. Throughout the five publications compiled in this thesis, we demonstrate that it is possible to generate word sense representations from these sources of data individually and in conjunction, and observe that combining them into a single model yields superior results in terms of accuracy and coverage. Furthermore, in our evaluation of the different representational models proposed here, we showcase the applicability of word sense representations both in downstream natural language processing applications and in the improvement and expansion of existing linguistic resources.

Föreläsare: Luis Nieto Piña, doktorand i språkvetenskaplig databehandling

Datum: 2019-01-23

Tid: 13:15 - 15:00

Kategorier: Språk, Humaniora

Arrangör: Institutionen för svenska språket

Plats: Lennart Torstenssonsgatan 6-8
L308

Kontaktperson: Stina Ericsson

Sidansvarig: Webbredaktionen|Sidan uppdaterades: 2016-04-11
Dela:

På Göteborgs universitet använder vi kakor (cookies) för att webbplatsen ska fungera på ett bra sätt för dig. Genom att surfa vidare godkänner du att vi använder kakor.  Vad är kakor?