DMCA
Joint learning of words and meaning representations for open-text semantic parsing (2012)
Cached
Download Links
| Venue: | In Proceedings of 15th International Conference on Artificial Intelligence and Statistics |
| Citations: | 19 - 5 self |
BibTeX
@INPROCEEDINGS{Bordes12jointlearning,
author = {Antoine Bordes and Xavier Glorot and Jason Weston and Yoshua Bengio},
title = {Joint learning of words and meaning representations for open-text semantic parsing},
booktitle = {In Proceedings of 15th International Conference on Artificial Intelligence and Statistics},
year = {2012}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Open-text (or open-domain) semantic parsers are designed to interpret any statement in natural language by inferring a corresponding meaning representation (MR). Unfortunately, large scale systems cannot be easily machine-learned due to lack of directly supervised data. We propose here a method that learns to assign MRs to a wide range of text (using a dictionary of more than 70,000 words, which are mapped to more than 40,000 entities) thanks to a training scheme that combines learning from knowledge bases (WordNet and ConceptNet) with learning from raw text. The model jointly learns representations of words, entities and MRs via a multi-task training process operating on these diverse sources of data. Hence, the system ends up providing methods for knowledge acquisition and word-sense disambiguation within the context of semantic parsing in a single elegant framework. Experiments on these various tasks indicate the promise of the approach. 1
Keyphrases
open-text semantic parsing joint learning semantic parsing semantic parser multi-task training process training scheme word-sense disambiguation various task corresponding meaning representation wide range diverse source knowledge acquisition large scale system single elegant framework raw text knowledge base natural language
