Question Answering in Natural Language: the Special Case of Temporal Expressions
This work addresses temporal question answering for natural language processing applications, but it is incremental as it applies existing methods to a specialized case.
The paper tackles temporal question answering by adapting answer extraction methods from general QA to find answers to temporal questions within paragraphs, using a new dataset based on WikiWars, and shows that deep learning models can achieve this with answers directly present in text.
Although general question answering has been well explored in recent years, temporal question answering is a task which has not received as much focus. Our work aims to leverage a popular approach used for general question answering, answer extraction, in order to find answers to temporal questions within a paragraph. To train our model, we propose a new dataset, inspired by SQuAD, specifically tailored to provide rich temporal information. We chose to adapt the corpus WikiWars, which contains several documents on history's greatest conflicts. Our evaluation shows that a deep learning model trained to perform pattern matching, often used in general question answering, can be adapted to temporal question answering, if we accept to ask questions whose answers must be directly present within a text.