Open Question Answering with Weakly Supervised Embedding Models

16 Apr 2014Antoine Bordes • Jason Weston • Nicolas Usunier

Building computers able to answer questions on any subject is a long standing goal of artificial intelligence. Promising progress has recently been achieved by methods that learn to map questions to logical forms or database queries. Such approaches can be effective but at the cost of either large amounts of human-labeled data or by defining lexicons and grammars tailored by practitioners.

Full paper

Evaluation


Task Dataset Model Metric name Metric value Global rank Compare
Question Answering Reverb Weakly Supervised Embeddings Accuracy 73% # 1
Question Answering WebQuestions Weakly Supervised Embeddings F1 29.7% # 3