Yordanov, Y;
Kocijan, V;
Lukasiewicz, T;
Camburu, OM;
(2022)
Few-Shot Out-of-Domain Transfer Learning of Natural Language Explanations in a Label-Abundant Setup.
In:
Findings of the Association for Computational Linguistics: EMNLP 2022.
(pp. pp. 3486-3501).
Association for Computational Linguistics: Abu Dhabi, United Arab Emirates.
Preview |
Text
2022.findings-emnlp.255.pdf - Published Version Download (1MB) | Preview |
Abstract
Training a model to provide natural language explanations (NLEs) for its predictions usually requires the acquisition of task-specific NLEs, which is time- and resource-consuming. A potential solution is the few-shot out-of-domain transfer of NLEs from a parent task with many NLEs to a child task. In this work, we examine the setup in which the child task has few NLEs but abundant labels. We establish four few-shot transfer learning methods that cover the possible fine-tuning combinations of the labels and NLEs for the parent and child tasks. We transfer explainability from a large natural language inference dataset (e-SNLI) separately to two child tasks: (1) hard cases of pronoun resolution, where we introduce the small-e-WinoGrande dataset of NLEs on top of the WinoGrande dataset, and (2) commonsense validation (ComVE). Our results demonstrate that the parent task helps with NLE generation and we establish the best methods for this setup.
| Type: | Proceedings paper |
|---|---|
| Title: | Few-Shot Out-of-Domain Transfer Learning of Natural Language Explanations in a Label-Abundant Setup |
| Event: | Findings of the Association for Computational Linguistics: EMNLP 2022 |
| Open access status: | An open access version is available from UCL Discovery |
| Publisher version: | https://aclanthology.org/2022.findings-emnlp.255/ |
| Language: | English |
| Additional information: | Copyright © 1963–2023 ACL; other materials are copyrighted by their respective copyright holders. Materials prior to 2016 here are licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 3.0 International License. Permission is granted to make copies for the purposes of teaching and research. Materials published in or after 2016 are licensed on a Creative Commons Attribution 4.0 International License. |
| 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.ucl.ac.uk/id/eprint/10167321 |
Archive Staff Only
 |
View Item |
