• Publications
  • Influence
MUTANT: A Training Paradigm for Out-of-Distribution Generalization in Visual Question Answering
TLDR
This work presents MUTANT, a training paradigm that exposes the model to perceptually similar, yet semantically distinct mutations of the input, to improve OOD generalization, such as the VQA-CP challenge. Expand
VQA-LOL: Visual Question Answering under the Lens of Logic
TLDR
This paper proposes a model which uses question-attention and logic-att attention to understand logical connectives in the question, and a novel Frechet-Compatibility Loss, which ensures that the answers of the component questions and the composed question are consistent with the inferred logical operation. Expand
Video2Commonsense: Generating Commonsense Descriptions to Enrich Video Captioning
TLDR
This work presents the first work on generating commonsense captions directly from videos, in order to describe latent aspects such as intentions, attributes, and effects, and finetune their commonsense generation models on the V2C-QA task where they ask questions about the latent aspects in the video. Expand
Careful Selection of Knowledge to Solve Open Book Question Answering
TLDR
This paper addresses QA with respect to the OpenBookQA dataset and combines state of the art language models with abductive information retrieval (IR), information gain based re-ranking, passage selection and weighted scoring to achieve 72.0% accuracy. Expand
Exploring ways to incorporate additional knowledge to improve Natural Language Commonsense Question Answering
TLDR
This work identifies external knowledge sources, and shows that the performance further improves when a set of facts retrieved through IR is prepended to each MCQ question during both training and test phase, and presents three different modes of passing knowledge and five different models of using knowledge including the standard BERT MCQ model. Expand
Knowledge Fusion and Semantic Knowledge Ranking for Open Domain Question Answering
TLDR
This work learns a semantic knowledge ranking model to re-rank knowledge retrieved through Lucene based information retrieval systems and proposes a "knowledge fusion model" which leverages knowledge in BERT-based language models with externally retrieved knowledge and improves the knowledge understanding of the BERT based language models. Expand
How Additional Knowledge can Improve Natural Language Commonsense Question Answering
TLDR
This work first categorizes external knowledge sources, and shows performance does improve on using such sources, then explores three different strategies for knowledge incorporation and four different models for question-answering using external commonsense knowledge. Expand
ASU at TextGraphs 2019 Shared Task: Explanation ReGeneration using Language Models and Iterative Re-Ranking
TLDR
This work uses an iterative reranking based approach to further improve the rankings of the explanation regeneration task as a learning to rank problem, for which state-of-the-art language models are used and dataset preparation techniques are explored. Expand
Self-Supervised VQA: Answering Visual Questions using Images and Captions
TLDR
This work presents a method to train models with procedurally generated Q-A pairs from captions using techniques, such as templates and annotation frameworks like QASRL, which surpass prior supervised methods on VQA-CP and are competitive with methods without object features in fully supervised setting. Expand
Self-Supervised Knowledge Triplet Learning for Zero-shot Question Answering
TLDR
This work proposes Knowledge Triplet Learning (KTL), a self-supervised task over knowledge graphs that proposes heuristics to create synthetic graphs for commonsense and scientific knowledge and shows considerable improvements over large pre-trained transformer models. Expand
...
1
2
3
...