Related papers: FiD-Ex: Improving Sequence-to-Sequence Models for Extractive Rationale Generation

FiD-Ex: Improving Sequence-to-Sequence Models for Extractive Rationale Generation

URL: http://arxiv.org/abs/2012.15482v1
Date: Thu, 31 Dec 2020 07:22:15 GMT
Title: FiD-Ex: Improving Sequence-to-Sequence Models for Extractive Rationale Generation
Authors: Kushal Lakhotia, Bhargavi Paranjape, Asish Ghoshal, Wen-tau Yih, Yashar Mehdad, Srinivasan Iyer
Abstract summary: We develop FiD-Ex, which addresses shortcomings for seq2seq models by introducing sentence markers to eliminate explanation fabrication. FiD-Ex significantly improves over prior work in terms of explanation metrics and task accuracy, on multiple tasks from the ERASER explainability benchmark.
Score: 19.73842483996047
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Natural language (NL) explanations of model predictions are gaining popularity as a means to understand and verify decisions made by large black-box pre-trained models, for NLP tasks such as Question Answering (QA) and Fact Verification. Recently, pre-trained sequence to sequence (seq2seq) models have proven to be very effective in jointly making predictions, as well as generating NL explanations. However, these models have many shortcomings; they can fabricate explanations even for incorrect predictions, they are difficult to adapt to long input documents, and their training requires a large amount of labeled data. In this paper, we develop FiD-Ex, which addresses these shortcomings for seq2seq models by: 1) introducing sentence markers to eliminate explanation fabrication by encouraging extractive generation, 2) using the fusion-in-decoder architecture to handle long input contexts, and 3) intermediate fine-tuning on re-structured open domain QA datasets to improve few-shot performance. FiD-Ex significantly improves over prior work in terms of explanation metrics and task accuracy, on multiple tasks from the ERASER explainability benchmark, both in the fully supervised and in the few-shot settings.