Sha, L;
Camburu, OM;
Lukasiewicz, T;
(2023)
Rationalizing predictions by adversarial information calibration.
Artificial Intelligence
, 315
, Article 103828. 10.1016/j.artint.2022.103828.
Preview |
Text
Camburu_2301.06009.pdf - Accepted Version Download (3MB) | Preview |
Abstract
Explaining the predictions of AI models is paramount in safety-critical applications, such as in legal or medical domains. One form of explanation for a prediction is an extractive rationale, i.e., a subset of features of an instance that lead the model to give its prediction on that instance. For example, the subphrase “he stole the mobile phone” can be an extractive rationale for the prediction of “Theft”. Previous works on generating extractive rationales usually employ a two-phase model: a selector that selects the most important features (i.e., the rationale) followed by a predictor that makes the prediction based exclusively on the selected features. One disadvantage of these works is that the main signal for learning to select features comes from the comparison of the answers given by the predictor to the ground-truth answers. In this work, we propose to squeeze more information from the predictor via an information calibration method. More precisely, we train two models jointly: one is a typical neural model that solves the task at hand in an accurate but black-box manner, and the other is a selector-predictor model that additionally produces a rationale for its prediction. The first model is used as a guide for the second model. We use an adversarial technique to calibrate the information extracted by the two models such that the difference between them is an indicator of the missed or over-selected features. In addition, for natural language tasks, we propose a language-model-based regularizer to encourage the extraction of fluent rationales. Experimental results on a sentiment analysis task, a hate speech recognition task, as well as on three tasks from the legal domain show the effectiveness of our approach to rationale extraction.
| Type: | Article |
|---|---|
| Title: | Rationalizing predictions by adversarial information calibration |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1016/j.artint.2022.103828 |
| Publisher version: | https://doi.org/10.1016/j.artint.2022.103828 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | Science & Technology, Technology, Computer Science, Artificial Intelligence, Computer Science, Rationale extraction, Interpretability, Natural language processing, Information calibration, Deep neural networks, NEURAL-NETWORK, ATTENTION, RULES |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery-pp.ucl.ac.uk/id/eprint/10164406 |
Archive Staff Only
 |
View Item |
