Key-Value Memory Networks for Directly Reading Documents

EMNLP 2016 Alexander Miller • Adam Fisch • Jesse Dodge • Amir-Hossein Karimi • Antoine Bordes • Jason Weston

Directly reading documents and being able to answer questions from them is an unsolved challenge. To avoid its inherent difficulty, question answering (QA) has been directed towards using Knowledge Bases (KBs) instead, which has proven effective. Unfortunately KBs often suffer from being too restrictive, as the schema cannot support certain types of answers, and too sparse, e.g. Wikipedia contains much more information than Freebase.

Full paper

Evaluation


Task Dataset Model Metric name Metric value Global rank Compare
Question Answering WikiQA Key-Value Memory Network MAP 0.7069 # 3
Question Answering WikiQA Key-Value Memory Network MRR 0.7265 # 3