Log In Sign Up

XTQA: Span-Level Explanations of the Textbook Question Answering

by   Jie Ma, et al.

Textbook Question Answering (TQA) is a task that one should answer a diagram/non-diagram question given a large multi-modal context consisting of abundant essays and diagrams. We argue that the explainability of this task should place students as a key aspect to be considered. To address this issue, we devise a novel architecture towards span-level eXplanations of the TQA (XTQA) based on our proposed coarse-to-fine grained algorithm, which can provide not only the answers but also the span-level evidences to choose them for students. This algorithm first coarsely chooses top M paragraphs relevant to questions using the TF-IDF method, and then chooses top K evidence spans finely from all candidate spans within these paragraphs by computing the information gain of each span to questions. Experimental results shows that XTQA significantly improves the state-of-the-art performance compared with baselines. The source code is available at


TutorialVQA: Question Answering Dataset for Tutorial Videos

Despite the number of currently available datasets on video question ans...

Visconde: Multi-document QA with GPT-3 and Neural Reranking

This paper proposes a question-answering system that can answer question...

Multi-modal Factorized Bilinear Pooling with Co-Attention Learning for Visual Question Answering

Visual question answering (VQA) is challenging because it requires a sim...

ListReader: Extracting List-form Answers for Opinion Questions

Question answering (QA) is a high-level ability of natural language proc...

Mucko: Multi-Layer Cross-Modal Knowledge Reasoning for Fact-based VisualQuestion Answering

Fact-based Visual Question Answering (FVQA) requires external knowledge ...

DyREx: Dynamic Query Representation for Extractive Question Answering

Extractive question answering (ExQA) is an essential task for Natural La...