Local Word Embeddings for Query Expansion based on Co-Authorship and Citations

André Rattinger, Jean-Marie Le Goff, Christian Gütl

Publikation: KonferenzbeitragPaperForschungBegutachtung

Abstract

Word embedding techniques have gained a lot of interest
from natural language processing researchers recently and they are valuable resource in identifying a list of semantically related terms for a
search query. These related terms build a natural addition for query expansion, but might mismatch when the application domains use different
jargon. Using the Skip-Gram algorithm of Word2Vec, terms are selected
only from a specific subset of the corpus, which is extended by documents
from co-authorship and citations. We demonstrate that locally-trained
word embeddings with this extension provides a valuable augmentation
and can improve retrieval performance. First result suggest that query
expansion and word embeddings could also benefit from other related
information.
Originalspracheenglisch
Seiten46
Seitenumfang53
PublikationsstatusVeröffentlicht - 26 Mär 2018
VeranstaltungBibliometric-enhanced Information Retrieval - Frenoble, Frankreich
Dauer: 26 Mär 201826 Mär 2018
Konferenznummer: 7
https://www.gesis.org/en/services/events/events-archive/conferences/ecir-workshops/ecir-workshop-2018/

Workshop

WorkshopBibliometric-enhanced Information Retrieval
KurztitelBIR 2018
LandFrankreich
OrtFrenoble
Zeitraum26/03/1826/03/18
Internetadresse

    Fingerprint

Fields of Expertise

  • Information, Communication & Computing

Dieses zitieren

Rattinger, A., Le Goff, J-M., & Gütl, C. (2018). Local Word Embeddings for Query Expansion based on Co-Authorship and Citations. 46. Beitrag in Bibliometric-enhanced Information Retrieval, Frenoble, Frankreich.