Abstract Existing table question answering datasets contain abundant factual questions that primarily evaluate a QA system’s comprehension of query and tabular data. However, restricted by their short-form answers, these fail to include question–answer interactions represent more advanced naturally occurring information needs: ask for reasoning integration pieces retrieved from structured knowl...

Medical Visual Question Answering~(VQA) is a combination of medical artificial intelligence and popular VQA challenges. Given image clinically relevant question in natural language, the system expected to predict plausible convincing answer. Although general-domain has been extensively studied, still needs specific investigation exploration due its task features. In first part this survey, we c...

Question Answering has been a well-researched NLP area over recent years. It become necessary for users to be able query through the variety of information available - it structured or unstructured. In this paper, we propose module which a) can consume data formats heterogeneous pipeline, ingests from product manuals, technical forums, internal discussion groups, etc. b) addresses practical cha...

Despite tremendous progress in the field of Visual Question Answering, models today still tend to be inconsistent and brittle. Thus, we propose a model-independent cyclic framework which increases consistency robustness any VQA architecture. We train our answer original question, generate an implication based on then learn generated correctly. As part framework, novel generator generates implie...