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

通过引入 Multee, 一种能够有效使用预训练自然语言推理模型的通用结构，本文在 MultiRC 和 OpenBookQA 这两个多阶段问题回答的数据集上进行了实验。使用 NLI 预训练模型的 Multee 模型在性能上明显优于仅在目标数据集上进行训练的 QA 模型和 OpenAI 迁移学习模型。