Ordinal Common-sense Inference
This addresses the challenge of modeling nuanced human-like reasoning in NLP, though it appears incremental as it builds on existing textual entailment frameworks.
The paper tackles the problem of automated common-sense inference by proposing an ordinal evaluation based on textual entailment, resulting in a dataset and a neural model that scores and generates inferences.
Humans have the capacity to draw common-sense inferences from natural language: various things that are likely but not certain to hold based on established discourse, and are rarely stated explicitly. We propose an evaluation of automated common-sense inference based on an extension of recognizing textual entailment: predicting ordinal human responses on the subjective likelihood of an inference holding in a given context. We describe a framework for extracting common-sense knowledge from corpora, which is then used to construct a dataset for this ordinal entailment task. We train a neural sequence-to-sequence model on this dataset, which we use to score and generate possible inferences. Further, we annotate subsets of previously established datasets via our ordinal annotation protocol in order to then analyze the distinctions between these and what we have constructed.