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.
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.
Originalsprache | englisch |
---|---|
Seiten | 46 |
Seitenumfang | 53 |
Publikationsstatus | Veröffentlicht - 26 März 2018 |
Veranstaltung | Bibliometric-enhanced Information Retrieval - Frenoble, Frankreich Dauer: 26 März 2018 → 26 März 2018 Konferenznummer: 7 https://www.gesis.org/en/services/events/events-archive/conferences/ecir-workshops/ecir-workshop-2018/ |
Workshop
Workshop | Bibliometric-enhanced Information Retrieval |
---|---|
Kurztitel | BIR 2018 |
Land/Gebiet | Frankreich |
Ort | Frenoble |
Zeitraum | 26/03/18 → 26/03/18 |
Internetadresse |
Fields of Expertise
- Information, Communication & Computing