Modeling Event Plausibility with Consistent Conceptual Abstraction

04/20/2021
by   Ian Porada, et al.
0

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.

READ FULL TEXT
research
10/13/2021

EventBERT: A Pre-Trained Model for Event Correlation Reasoning

Event correlation reasoning infers whether a natural language paragraph ...
research
05/24/2020

Common Sense or World Knowledge? Investigating Adapter-Based Knowledge Injection into Pretrained Transformers

Following the major success of neural language models (LMs) such as BERT...
research
05/26/2023

Counterfactual reasoning: Testing language models' understanding of hypothetical scenarios

Current pre-trained language models have enabled remarkable improvements...
research
04/15/2021

Time-Stamped Language Model: Teaching Language Models to Understand the Flow of Events

Tracking entities throughout a procedure described in a text is challeng...
research
09/16/2021

Regularized Training of Nearest Neighbor Language Models

Including memory banks in a natural language processing architecture inc...
research
04/14/2021

UPB at SemEval-2021 Task 1: Combining Deep Learning and Hand-Crafted Features for Lexical Complexity Prediction

Reading is a complex process which requires proper understanding of text...

Please sign up or login with your details

Forgot password? Click here to reset