Compares LIME, input perturbation and attention for explaining QA on KB+text; proposes automatic evaluation paradigm and finds input perturbation superior in both automatic and human studies.
Compositional Attention Networks for Interpretability in Natural Language Question Answering
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
MAC Net is a compositional attention network designed for Visual Question Answering. We propose a modified MAC net architecture for Natural Language Question Answering. Question Answering typically requires Language Understanding and multi-step Reasoning. MAC net's unique architecture - the separation between memory and control, facilitates data-driven iterative reasoning. This makes it an ideal candidate for solving tasks that involve logical reasoning. Our experiments with 20 bAbI tasks demonstrate the value of MAC net as a data-efficient and interpretable architecture for Natural Language Question Answering. The transparent nature of MAC net provides a highly granular view of the reasoning steps taken by the network in answering a query.
fields
cs.CL 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Interpretable Question Answering on Knowledge Bases and Text
Compares LIME, input perturbation and attention for explaining QA on KB+text; proposes automatic evaluation paradigm and finds input perturbation superior in both automatic and human studies.