activity
20152022
most citedHow Much Can CLIP Benefit Vision-and-Language Tasks?

153 citations · 601 across the 67 of their papers we have counts for

collaborators
Showing 2019Show all

18 papers · 1 filter

cs.CL20194 cited

Self-Assembling Modular Networks for Interpretable Multi-Hop Reasoning

Yichen Jiang, Mohit Bansal

Multi-hop QA requires a model to connect multiple pieces of evidence scattered in a long context to answer the question. The recently proposed HotpotQA (Yang et al., 2018) dataset…

cs.CL2019

Adversarial NLI: A New Benchmark for Natural Language Understanding

Yixin Nie, Adina Williams, Emily Dinan +3

We introduce a new large-scale NLI benchmark dataset, collected via an iterative, adversarial human-and-model-in-the-loop procedure. We show that training models on this new datase…

cs.CL20192 cited

Automatically Learning Data Augmentation Policies for Dialogue Tasks

Tong Niu, Mohit Bansal

Automatic data augmentation (AutoAugment) (Cubuk et al., 2019) searches for optimal perturbation policies via a controller trained using performance rewards of a sampled policy on…

cs.CL2019

Revealing the Importance of Semantic Retrieval for Machine Reading at Scale

Yixin Nie, Songhe Wang, Mohit Bansal

Machine Reading at Scale (MRS) is a challenging task in which a system is given an input query and is asked to produce a precise output by "reading" information from a large knowle…

cs.CL2019

Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answering

Shiyue Zhang, Mohit Bansal

Text-based Question Generation (QG) aims at generating natural and relevant questions that can be answered by a given answer in some context. Existing QG models suffer from a "sema…

cs.CL2019

LXMERT: Learning Cross-Modality Encoder Representations from Transformers

Hao Tan, Mohit Bansal

Vision-and-language reasoning requires an understanding of visual concepts, language semantics, and, most importantly, the alignment and relationships between these two modalities.…