Abstract
Although advances in neural architectures for NLP problems as well as unsupervised pre-training have led to substantial improvements on question answering and natural language inference, understanding of and reasoning over long texts still poses a substantial challenge. Here, we consider the task of question answering from full narratives (e.g., books or movie scripts), or their summaries, tackling the NarrativeQA challenge (NQA; Kocisky et al. (2018)). We introduce a heuristic extractive version of the data set, which allows us to approach the more feasible problem of answer extraction (rather than generation). We train systems for passage retrieval as well as answer span prediction using this data set. We use pre-trained BERT embeddings for injecting prior knowledge into our system. We show that our setup leads to state of the art performance on summary-level QA. On QA from full narratives, our model outperforms previous models on the METEOR metric. We analyze the relative contributions of pre-trained embeddings and the extractive training paradigm, and provide a detailed error analysis.- Anthology ID:
- D19-5823
- Volume:
- Proceedings of the 2nd Workshop on Machine Reading for Question Answering
- Month:
- November
- Year:
- 2019
- Address:
- Hong Kong, China
- Editors:
- Adam Fisch, Alon Talmor, Robin Jia, Minjoon Seo, Eunsol Choi, Danqi Chen
- Venue:
- WS
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 172–182
- Language:
- URL:
- https://aclanthology.org/D19-5823
- DOI:
- 10.18653/v1/D19-5823
- Cite (ACL):
- Lea Frermann. 2019. Extractive NarrativeQA with Heuristic Pre-Training. In Proceedings of the 2nd Workshop on Machine Reading for Question Answering, pages 172–182, Hong Kong, China. Association for Computational Linguistics.
- Cite (Informal):
- Extractive NarrativeQA with Heuristic Pre-Training (Frermann, 2019)
- PDF:
- https://preview.aclanthology.org/ingest-bitext-workshop/D19-5823.pdf