Word Embeddings for Practical Information Retrieval
| dc.contributor.author | Galke, Lukas | |
| dc.contributor.author | Saleh, Ahmed | |
| dc.contributor.author | Scherp, Ansgar | |
| dc.contributor.editor | Eibl, Maximilian | |
| dc.contributor.editor | Gaedke, Martin | |
| dc.date.accessioned | 2017-08-28T23:47:39Z | |
| dc.date.available | 2017-08-28T23:47:39Z | |
| dc.date.issued | 2017 | |
| dc.description.abstract | We assess the suitability of word embeddings for practical information retrieval scenarios. Thus, we assume that users issue ad-hoc short queries where we return the first twenty retrieved documents after applying a boolean matching operation between the query and the documents. We compare the performance of several techniques that leverage word embeddings in the retrieval models to compute the similarity between the query and the documents, namely word centroid similarity, paragraph vectors, Word Mover’s distance, as well as our novel inverse document frequency (IDF) re-weighted word centroid similarity. We evaluate the performance using the ranking metrics mean average precision, mean reciprocal rank, and normalized discounted cumulative gain. Additionally, we inspect the retrieval models’ sensitivity to document length by using either only the title or the full-text of the documents for the retrieval task. We conclude that word centroid similarity is the best competitor to state-of-the-art retrieval models. It can be further improved by re-weighting the word frequencies with IDF before aggregating the respective word vectors of the embedding. The proposed cosine similarity of IDF re-weighted word vectors is competitive to the TF-IDF baseline and even outperforms it in case of the news domain with a relative percentage of 15%. | en |
| dc.identifier.doi | 10.18420/in2017_215 | |
| dc.identifier.isbn | 978-3-88579-669-5 | |
| dc.identifier.pissn | 1617-5468 | |
| dc.language.iso | en | |
| dc.publisher | Gesellschaft für Informatik, Bonn | |
| dc.relation.ispartof | INFORMATIK 2017 | |
| dc.relation.ispartofseries | Lecture Notes in Informatics (LNI) - Proceedings, Volume P-275 | |
| dc.subject | Word embeddings | |
| dc.subject | Document representation | |
| dc.subject | Information retrieval | |
| dc.title | Word Embeddings for Practical Information Retrieval | en |
| gi.citation.endPage | 2167 | |
| gi.citation.startPage | 2155 | |
| gi.conference.date | 25.-29. September 2017 | |
| gi.conference.location | Chemnitz | |
| gi.conference.sessiontitle | Deep Learning in heterogenen Datenbeständen |
Dateien
Originalbündel
1 - 1 von 1