Question Answering in Natural Language: the Special Case of Temporal Expressions
LISN-CNRS, Université Paris-Saclay, France, Armand Stricker · Student Research Workshop .../Proceedings of the Student Research Workshop ... · 2021
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.Absolute, when a moment is totally explicit and unambiguous such as Monday, October 6th, 2019.Deictic, when the moment of enunciation must be used to determine the moment to which the expression refers: two weeks ago.We can assume, for example, that the moment of Question Answering in Natural Language: the Special Case of Temporal Expressions