Abstract | ||
---|---|---|
We present a new method for estimating vector space representations of words: embedding learning by concept induction. We test this method on a highly parallel corpus and learn semantic representations of words in 1259 different languages in a single common space. An extensive experimental evaluation on crosslingual word similarity and sentiment analysis indicates that concept-based multilingual embedding learning performs better than previous approaches. |
Year | Venue | Field |
---|---|---|
2018 | PROCEEDINGS OF THE 56TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL), VOL 1 | Vector space,Embedding,Sentiment analysis,Computer science,Artificial intelligence,Natural language processing,Machine learning |
DocType | Volume | Citations |
Conference | P18-1 | 0 |
PageRank | References | Authors |
0.34 | 27 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Philipp Dufter | 1 | 1 | 4.74 |
Mengjie Zhao | 2 | 0 | 0.34 |
Martin Schmitt | 3 | 1 | 1.02 |
Alexander M. Fraser | 4 | 660 | 40.50 |
Hinrich Schütze | 5 | 2113 | 362.21 |