Reading Wikipedia to Answer Open-Domain Questions

This paper proposes to tackle open- domain question answering using Wikipedia as the unique knowledge source: the answer to any factoid question is a text span in a Wikipedia article. This task of machine reading at scale combines the challenges of document retrieval (finding the relevant articles) with that of machine comprehension of text (identifying the answer spans from those articles). Our approach combines a search component based on bigram hashing and TF-IDF matching with a multi-layer recurrent neural network model trained to detect answers in Wikipedia paragraphs. Our experiments on multiple existing QA datasets indicate that (1) both modules are highly competitive with respect to existing counterparts and (2) multitask learning using distant supervision on their combination is an effective complete system on this challenging task.

PDF Abstract ACL 2017 PDF ACL 2017 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Open-Domain Question Answering SQuAD1.1 DrQA EM 70.0 # 1
Question Answering SQuAD1.1 Document Reader (single model) EM 70.733 # 154
F1 79.353 # 157
Hardware Burden None # 1
Operations per network pass None # 1
Question Answering SQuAD1.1 dev DrQA (Document Reader only) EM 69.5 # 39
F1 78.8 # 41

Results from Other Papers


Task Dataset Model Metric Name Metric Value Rank Source Paper Compare
Question Answering Natural Questions (long) DrQA F1 46.1 # 8
Question Answering Natural Questions (short) DrQA F1 35.7 # 5
Question Answering Quasart-T DrQA EM 37.7 # 7
Open-Domain Question Answering SearchQA DrQA EM 41.9 # 9

Methods


No methods listed for this paper. Add relevant methods here