Towards Open-Text Semantic Parsing via Multi-Task Learning of Structured Embeddings

Details Towards Open-Text Semantic Parsing via Multi-Task Learning of Structured Embeddings Towards Open-Text Semantic Parsing via Multi-Task Learning of Structured Embeddings

2011-07-19

arxiv.org/abs/1107.3663v1

Computer Science

Artificial Intelligence

Scientific paper

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 WordNet and ConceptNet with learning from raw text. The model learns structured embeddings of words, entities and MRs via a multi-task training process operating on these diverse sources of data that integrates all the learnt knowledge into a single system. This work ends up combining methods for knowledge acquisition, semantic parsing, and word-sense disambiguation. Experiments on various tasks indicate that our approach is indeed successful and can form a basis for future more sophisticated systems.

Affiliated with

Also associated with

No associations

Rating

Towards Open-Text Semantic Parsing via Multi-Task Learning of Structured Embeddings does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Towards Open-Text Semantic Parsing via Multi-Task Learning of Structured Embeddings, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Towards Open-Text Semantic Parsing via Multi-Task Learning of Structured Embeddings will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-514353