Generating hypothetical events for abductive inference
Abductive reasoning starts from some observations and aims at finding the most plausible explanation for these observations. To perform abduction, humans often make use of temporal and causal inferences, and knowledge about how some hypothetical situation can result in different outcomes. This work...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Chapter/Article Conference Paper |
| Language: | English |
| Published: |
August 2021
|
| In: |
The 10th Conference on Lexical and Computational Semantics - proceedings of the conference
Year: 2021, Pages: 67-77 |
| DOI: | 10.18653/v1/2021.starsem-1.6 |
| Online Access: | Verlag, lizenzpflichtig, Volltext: https://doi.org/10.18653/v1/2021.starsem-1.6 Verlag, lizenzpflichtig, Volltext: https://aclanthology.org/2021.starsem-1.6 
|
| Author Notes: | Debjit Paul, Anette Frank |
| Summary: | Abductive reasoning starts from some observations and aims at finding the most plausible explanation for these observations. To perform abduction, humans often make use of temporal and causal inferences, and knowledge about how some hypothetical situation can result in different outcomes. This work offers the first study of how such knowledge impacts the Abductive NLI task - which consists in choosing the more likely explanation for given observations. We train a specialized language model LMI that is tasked to generate what could happen next from a hypothetical scenario that evolves from a given event. We then propose a multi-task model MTL to solve the Abductive NLI task, which predicts a plausible explanation by a) considering different possible events emerging from candidate hypotheses - events generated by LMI - and b) selecting the one that is most similar to the observed outcome. We show that our MTL model improves over prior vanilla pre-trained LMs fine-tuned on Abductive NLI. Our manual evaluation and analysis suggest that learning about possible next events from different hypothetical scenarios supports abductive inference. |
|---|---|
| Item Description: | Gesehen am 10.07.2023 |
| Physical Description: | Online Resource |
| ISBN: | 9781954085770 |
| DOI: | 10.18653/v1/2021.starsem-1.6 |