论文信息 - Red Dragon AI at TextGraphs 2019 Shared Task: Language Model Assisted Explanation Generation

Red Dragon AI at TextGraphs 2019 Shared Task: Language Model Assisted Explanation Generation

The TextGraphs-13 Shared Task on Explanation Regeneration (Jansen and Ustalov, 2019) asked participants to develop methods to reconstruct gold explanations for elementary science questions. Red Dragon AI’s entries used the language of the questions and explanation text directly, rather than a constructing a separate graph-like representation. Our leaderboard submission placed us 3rd in the competition, but we present here three methods of increasing sophistication, each of which scored successively higher on the test set after the competition close.

Sam Witteveen | Martin Andrews | Yew Ken Chia

[1] Ming-Wei Chang,et al. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[2] Clayton T. Morrison,et al. WorldTree: A Corpus of Explanation Graphs for Elementary Science Questions supporting Multi-hop Inference , 2018, LREC.

[3] Oren Etzioni,et al. Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge , 2018, ArXiv.

[4] Peter Jansen,et al. Controlling Information Aggregation for Complex Question Answering , 2018, ECIR.

[5] Omer Levy,et al. RoBERTa: A Robustly Optimized BERT Pretraining Approach , 2019, ArXiv.

[6] Peter Jansen,et al. Multi-class Hierarchical Question Classification for Multiple Choice Science Exams , 2019, LREC.

[7] Peter Jansen,et al. Multi-hop Inference for Sentence-level TextGraphs: How Challenging is Meaningfully Combining Information for Science Question Answering? , 2018, TextGraphs@NAACL-HLT.

[8] Dmitry Ustalov,et al. TextGraphs 2019 Shared Task on Multi-Hop Inference for Explanation Regeneration , 2019, EMNLP.