Published on

LIT : LSTM-Interleaved Transformer for Multi-Hop Explanation Ranking

Textgraphs@COLING-2020 Shared Task Paper

This paper for the workshop Shared Task was accepted to the Textgraphs-14 workshop at COLING-2020 in Barcelona, Spain (held online).


Explainable question answering for science questions is a challenging task that requires multi-hop 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.

Poster Version

COLING-2020 Textgraphs poster thumbnail

And the BiBTeX entry for the arXiv version:

  author       = {Yew Ken Chia and
                  Sam Witteveen and
                  Martin Andrews},
  title        = {Red Dragon {AI} at TextGraphs 2020 Shared Task: {LIT} : LSTM-Interleaved
                  Transformer for Multi-Hop Explanation Ranking},
  journal      = {CoRR},
  volume       = {abs/2012.14164},
  year         = {2020},
  url          = {},
  eprinttype    = {arXiv},
  eprint       = {2012.14164},
  timestamp    = {Tue, 05 Jan 2021 16:02:31 +0100},
  biburl       = {},
  bibsource    = {dblp computer science bibliography,}