# Temporal Information Extraction for Question Answering Using Syntactic Dependencies in an LSTM-based Architecture

## TL;DR

This paper introduces a uniform LSTM-based model that effectively extracts various temporal relations from text using dependency paths, improving accuracy over previous methods in question answering tasks.

## Contribution

The authors develop a single architecture that handles intra-sentence, cross-sentence, and document time relations, incorporating a double-checking technique and a global conflict resolution algorithm.

## Key findings

- Outperforms state-of-the-art methods on QA-TempEval dataset
- Achieves higher recall and precision in temporal relation extraction
- Demonstrates the effectiveness of dependency path input in LSTM models

## Abstract

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.