Rationale
Related Papers
TrClaim-19: The First Collection for Turkish Check-Worthy Claim Detection with Annotator Rationales
AbstractMassive misinformation spread over Internet has many negative impacts on our lives. While spreading a claim is easy, investigating its veracity is hard and time consuming, Therefore, we urgently need …...
Rationalization through Concepts
Automated predictions require explanations to be interpretable by humans. One type of ex- planation is a rationale, i.e., a selection of in- put features such as relevant text snippets from …...
A Fine-grained Interpretability Evaluation Benchmark for Neural NLP
AbstractWhile there is increasing concern about the interpretability of neural models, the evaluation of interpretability remains an open problem, due to the lack of proper evaluation datasets and metrics. In …...
Explaining Why: How Instructions and User Interfaces Impact Annotator Rationales When Labeling Text Data
AbstractIn the context of data labeling, NLP researchers are increasingly interested in having humans select rationales, a subset of input tokens relevant to the chosen label. We conducted a 332-participant …...
Peeking inside the black box: A Commonsense-aware Generative Framework for Explainable Complaint Detection
AbstractComplaining is an illocutionary act in which the speaker communicates his/her dissatisfaction with a set of circumstances and holds the hearer (the complainee) answerable, directly or indirectly. Considering breakthroughs in …...