Contextually propagated term weights for document representation
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
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.
Original language | English |
---|---|
Title of host publication | SIGIR 2019 - Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval |
Publisher | Association for Computing Machinery |
Publication date | 18 Jul 2019 |
Pages | 897-900 |
ISBN (Electronic) | 9781450361729 |
DOIs | |
Publication status | Published - 18 Jul 2019 |
Event | 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2019 - Paris, France Duration: 21 Jul 2019 → 25 Jul 2019 |
Conference
Conference | 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2019 |
---|---|
Land | France |
By | Paris |
Periode | 21/07/2019 → 25/07/2019 |
Sponsor | ACM SIGIR |
Series | SIGIR 2019 - Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval |
---|
- Contextual semantics, Document representation, Word embeddings
Research areas
Links
- http://arxiv.org/pdf/1906.00674
Submitted manuscript
ID: 239566043