Contextually propagated term weights for document representation
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
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.
Originalsprog | Engelsk |
---|---|
Titel | SIGIR 2019 - Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval |
Forlag | Association for Computing Machinery |
Publikationsdato | 18 jul. 2019 |
Sider | 897-900 |
ISBN (Elektronisk) | 9781450361729 |
DOI | |
Status | Udgivet - 18 jul. 2019 |
Begivenhed | 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2019 - Paris, Frankrig Varighed: 21 jul. 2019 → 25 jul. 2019 |
Konference
Konference | 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2019 |
---|---|
Land | Frankrig |
By | Paris |
Periode | 21/07/2019 → 25/07/2019 |
Sponsor | ACM SIGIR |
Navn | SIGIR 2019 - Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval |
---|
Links
- http://arxiv.org/pdf/1906.00674
Indsendt manuskript
ID: 239566043