Contextually propagated term weights for document representation

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

Word embeddings predict a word from its neighbours by learning small, dense embedding vectors. In practice, this prediction corresponds to a semantic score given to the predicted word (or term weight). We present a novel model that, given a target word, redistributes part of that word's weight (that has been computed with word embeddings) across words occurring in similar contexts as the target word. Thus, our model aims to simulate how semantic meaning is shared by words occurring in similar contexts, which is incorporated into bag-of-words document representations. Experimental evaluation in an unsupervised setting against 8 state of the art baselines shows that our model yields the best micro and macro F1 scores across datasets of increasing difficulty.

OriginalsprogEngelsk
TitelSIGIR 2019 - Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval
ForlagAssociation for Computing Machinery
Publikationsdato18 jul. 2019
Sider897-900
ISBN (Elektronisk)9781450361729
DOI
StatusUdgivet - 18 jul. 2019
Begivenhed42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2019 - Paris, Frankrig
Varighed: 21 jul. 201925 jul. 2019

Konference

Konference42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2019
LandFrankrig
ByParis
Periode21/07/201925/07/2019
SponsorACM SIGIR
NavnSIGIR 2019 - Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval

ID: 239566043