Recent advances in deep learning have improved the performance of many Natural Language Processing (NLP) tasks such as translation, question-answering, and text …
SM Mohammad - Computational Linguistics, 2022 - direct.mit.edu
The importance and pervasiveness of emotions in our lives makes affective computing a tremendously important and vibrant line of work. Systems for automatic emotion recognition …
An extractive rationale explains a language model's (LM's) prediction on a given task instance by highlighting the text inputs that most influenced the prediction. Ideally, rationale …
Abstract Explainable Artificial Intelligence refers to developing artificial intelligence models and systems that can provide clear, understandable, and transparent explanations for their …
Rationale extraction can be considered as a straightforward method of improving the model explainability, where rationales are a subsequence of the original inputs, and can be …
We present a novel feature attribution method for explaining text classifiers, and analyze it in the context of hate speech detection. Although feature attribution models usually provide a …
While natural language systems continue improving, they are still imperfect. If a user has a better understanding of how a system works, they may be able to better accomplish their …
J Si, Y Zhu, D Zhou - Proceedings of the AAAI Conference on Artificial …, 2023 - ojs.aaai.org
The opaqueness of the multi-hop fact verification model imposes imperative requirements for explainability. One feasible way is to extract rationales, a subset of inputs, where the …
Large language models (LLMs) often generate inaccurate or fabricated information and generally fail to indicate their confidence, which limits their broader applications. Previous …