Open Question Answering with Weakly Supervised Embedding Models — mentioned by nl

Thu, 09 Apr 2015 23:14:45 GMT

This is pretty impressive. It beats average human performance in the history category, but is outperformed by humans in literature. Note that part of the data preparation process includes building a dependency-parse tree. From the abstract I'd thought the model was learning to do that too, which would have been very impressive. In general this approach is somewhat related to [1] in that both rely on knowledge representation similarities. I'm not entirely clear about how this groups approach interfaces the learned model and the IR querying. [1] Open Question Answering with Weakly Supervised…

Paper and discussion history. A mention is not an endorsement.

Open Question Answering with Weakly Supervised Embedding Models · HackerPapers discussions

Open Question Answering with Weakly Supervised Embedding Models — mentioned by nl