Temporal Information Extraction for Question Answering Using Syntactic Dependencies in an LSTM-based Architecture
Temporal Information Extraction for Question Answering Using Syntactic Dependencies in an LSTM-based Architecture
复制标题
DOI：
10.18653/v1/d17-1092
复制
发表时间：
2017-03
期刊：
影响因子：
--
通讯作者：
Yuanliang Meng;Anna Rumshisky;Alexey Romanov
中科院分区：
文献类型：
--
作者：
Yuanliang Meng;Anna Rumshisky;Alexey Romanov
在本文中，我们提出使用一套简单、统一的基于lstm的模型从文本中恢复不同类型的时间关系。使用实体之间的最短依赖路径作为输入，使用相同的体系结构提取句子内、跨句子和文档创建时间关系。一种“双重检查”技术在分类中反转实体对，提高正面案例的召回率，减少对立类别之间的错误分类。一种高效的剪枝算法可以全局解决冲突。在QA-TempEval （SemEval2015 Task 5）上进行评估，我们提出的技术在很大程度上优于最先进的方法。我们还进行内在评估，并在Timebank-Dense上发布最新的结果。
In this paper, we propose to use a set of simple, uniform in architecture LSTM-based models to recover different kinds of temporal relations from text. Using the shortest dependency path between entities as input, the same architecture is used to extract intra-sentence, cross-sentence, and document creation time relations. A “double-checking” technique reverses entity pairs in classification, boosting the recall of positive cases and reducing misclassifications between opposite classes. An efficient pruning algorithm resolves conflicts globally. Evaluated on QA-TempEval (SemEval2015 Task 5), our proposed technique outperforms state-of-the-art methods by a large margin. We also conduct intrinsic evaluation and post state-of-the-art results on Timebank-Dense.