Red Dragon AI at TextGraphs 2020 Shared Task : LIT : LSTM-Interleaved Transformer for Multi-Hop Explanation Ranking
Red Dragon AI at TextGraphs 2020 Shared Task : LIT : LSTM-Interleaved Transformer for Multi-Hop Explanation Ranking
复制标题
红龙 AI 在 TextGraphs 2020 共享任务：LIT：LSTM-Interleaved Transformer for Multi-Hop Explanation Ranking
DOI：
10.18653/v1/2020.textgraphs-1.14
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Martin Andrews
中科院分区：
文献类型：
--
作者：
Yew Ken Chia;Sam Witteveen;Martin Andrews
科学问题的可解释问题回答是一项具有挑战性的任务，它需要对大量事实句进行多跳推理。为了克服隔离查看每个查询文档对的方法的局限性，我们提出了LSTM-Interleaved Transformer，它结合了跨文档交互以提高多跳排序。LIT架构可以在重新排名设置中利用先前的排名位置。我们的模型在TextGraphs 2020共享任务的当前排行榜上具有竞争力，实现了0.5607的测试集MAP，如果我们在竞赛截止日期之前提交，将获得第三名。我们的代码实现可以在[https://github.com/mdda/worldtree_corpus/tree/textgraphs_2020](https://github.com/mdda/worldtree_corpus/tree/textgraphs_2020]上获得。
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. Our code implementation is made available at [https://github.com/mdda/worldtree_corpus/tree/textgraphs_2020](https://github.com/mdda/worldtree_corpus/tree/textgraphs_2020).
TextGraphs 2020 解释再生多跳推理共享任务
DOI：
10.18653/v1/2020.textgraphs-1.10
发表时间：
2020
期刊：
Proceedings of the Graph-based Methods for Natural Language Processing (TextGraphs
影响因子：
--
作者：
Jansen, Peter;Ustalov, Dmitry
通讯作者：
Ustalov, Dmitry