Modeling Event Plausibility with Consistent Conceptual Abstraction
Ian Porada, Kaheer Suleman, Adam Trischler, Jackie Chi Kit Cheung
Abstract
Understanding natural language requires common sense, one aspect of which is the ability to discern the plausibility of events. While distributional models—most recently pre-trained, Transformer language models—have demonstrated improvements in modeling event plausibility, their performance still falls short of humans’. In this work, we show that Transformer-based plausibility models are markedly inconsistent across the conceptual classes of a lexical hierarchy, inferring that “a person breathing” is plausible while “a dentist breathing” is not, for example. We find this inconsistency persists even when models are softly injected with lexical knowledge, and we present a simple post-hoc method of forcing model consistency that improves correlation with human plausibility judgements.
BibTeX
@inproceedings{porada-etal-2021-modeling,
title = "Modeling Event Plausibility with Consistent Conceptual Abstraction",
author = "Porada, Ian and
Suleman, Kaheer and
Trischler, Adam and
Cheung, Jackie Chi Kit",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.138/",
doi = "10.18653/v1/2021.naacl-main.138",
pages = "1732--1743"
}