Abstract | ||
---|---|---|
Question Answering (QA) naturally reduces to an entailment problem, namely, verifying whether some text entails the answer to a question. However, for multi-hop QA tasks, which require reasoning with multiple sentences, it remains unclear how best to utilize entailment models pre-trained on large scale datasets such as SNLI, which are based on sentence pairs. We introduce Multee, a general architecture that can effectively use entailment models for multi-hop QA tasks. Multee uses (i) a local module that helps locate important sentences, thereby avoiding distracting information, and (ii) a global module that aggregates information by effectively incorporating importance weights. Importantly, we show that both modules can use entailment functions pre-trained on a large scale NLI datasets. We evaluate performance on MultiRC and OpenBookQA, two multihop QA datasets. When using an entailment function pre-trained on NLI datasets, Multee outperforms QA models trained only on the target QA datasets and the OpenAI transformer models. The code is available at this https URL. |
Year | Venue | Field |
---|---|---|
2019 | arXiv: Computation and Language | Logical consequence,Question answering,Repurposing,Computer science,Natural language processing,Artificial intelligence,Hop (networking) |
DocType | Volume | Citations |
Journal | abs/1904.09380 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Harsh Trivedi | 1 | 4 | 3.51 |
Heeyoung Kwon | 2 | 7 | 2.84 |
Tushar Khot | 3 | 0 | 0.34 |
Ashish Sabharwal | 4 | 1063 | 70.62 |
Niranjan Balasubramanian | 5 | 862 | 55.98 |