Temporal Information Extraction for Question Answering Using Syntactic Dependencies in an LSTM-based Architecture
This work addresses temporal information extraction for question answering systems, representing an incremental advance with specific gains in accuracy.
The paper tackles the problem of extracting temporal relations from text for question answering by using LSTM-based models with syntactic dependencies, achieving state-of-the-art performance on QA-TempEval with a large margin improvement.
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.