Red Dragon AI at TextGraphs 2020 Shared Task : LIT : LSTM-Interleaved Transformer for Multi-Hop Explanation Ranking

Explainable question answering for science questions is a challenging task that requires multihop inference over a large set of fact sentences. To counter the limitations of methods that view each query-document pair in isolation, we propose the LSTM-Interleaved Transformer which incorporates cross-document interactions for improved multi-hop ranking. The LIT architecture can leverage prior ranking positions in the re-ranking setting. Our model is competitive on the current leaderboard for the TextGraphs 2020 shared task, achieving a test-set MAP of 0.5607, and would have gained third place had we submitted before the competition deadline. Our code implementation is made available at https://github.com/mdda/worldtree_corpus/ tree/textgraphs_2020

[1]  Mihai Surdeanu,et al.  Higher-order Lexical Semantic Models for Non-factoid Answer Reranking , 2015, TACL.

[2]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

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

[4]  Sam Witteveen,et al.  Red Dragon AI at TextGraphs 2019 Shared Task: Language Model Assisted Explanation Generation , 2019, TextGraphs@EMNLP.

[5]  Danqi Chen,et al.  Dense Passage Retrieval for Open-Domain Question Answering , 2020, EMNLP.

[6]  Jakob Uszkoreit,et al.  A Decomposable Attention Model for Natural Language Inference , 2016, EMNLP.

[7]  Richard Socher,et al.  The Natural Language Decathlon: Multitask Learning as Question Answering , 2018, ArXiv.

[8]  Dmitry Ustalov,et al.  TextGraphs 2020 Shared Task on Multi-Hop Inference for Explanation Regeneration , 2020, TEXTGRAPHS.

[9]  P. Pérez,et al.  SoDeep: A Sorting Deep Net to Learn Ranking Loss Surrogates , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[11]  Matei Zaharia,et al.  ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT , 2020, SIGIR.

[12]  Marc Najork,et al.  Self-Attentive Document Interaction Networks for Permutation Equivariant Ranking , 2019, ArXiv.

[13]  Fabio Petroni,et al.  Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks , 2020, NeurIPS.

[14]  Peter Clark,et al.  Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering , 2018, EMNLP.

[15]  Jeff Johnson,et al.  Billion-Scale Similarity Search with GPUs , 2017, IEEE Transactions on Big Data.

[16]  Cheng Li,et al.  The LambdaLoss Framework for Ranking Metric Optimization , 2018, CIKM.

[17]  Thomas Wolf,et al.  DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter , 2019, ArXiv.

[18]  Kevin Duh,et al.  Modeling Document Interactions for Learning to Rank with Regularized Self-Attention , 2020, ArXiv.

[19]  Sebastian Riedel,et al.  Constructing Datasets for Multi-hop Reading Comprehension Across Documents , 2017, TACL.

[20]  Jon Almazán,et al.  Learning With Average Precision: Training Image Retrieval With a Listwise Loss , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[21]  Yoshua Bengio,et al.  HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering , 2018, EMNLP.

[22]  Peter A. Jansen,et al.  WorldTree V2: A Corpus of Science-Domain Structured Explanations and Inference Patterns supporting Multi-Hop Inference , 2020, LREC.

[23]  Radoslaw Bialobrzeski,et al.  Context-Aware Learning to Rank with Self-Attention , 2020, ArXiv.

[24]  Mona Attariyan,et al.  Parameter-Efficient Transfer Learning for NLP , 2019, ICML.

[25]  Shuguang Han,et al.  Learning-to-Rank with BERT in TF-Ranking , 2020, ArXiv.

[26]  Tushar Khot,et al.  QASC: A Dataset for Question Answering via Sentence Composition , 2020, AAAI.