b'Mohit Bansal'

Robustness Gym: Unifying the NLP Evaluation Landscape

Despite impressive performance on standard benchmarks, deep neural netwo...
01/13/2021 ∙ by Karan Goel, et al. ∙ 2 ∙ share

read it
FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging

Influence functions approximate the 'influences' of training data-points...
12/31/2020 ∙ by Han Guo, et al. ∙ 9 ∙ share

read it
I like fish, especially dolphins: Addressing Contradictions in Dialogue Modeling

To quantify how well natural language understanding models can capture c...
12/24/2020 ∙ by Yixin Nie, et al. ∙ 7 ∙ share

read it
To what extent do human explanations of model behavior align with actual model behavior?

Given the increasingly prominent role NLP models (will) play in our live...
12/24/2020 ∙ by Grusha Prasad, et al. ∙ 9 ∙ share

read it
ArraMon: A Joint Navigation-Assembly Instruction Interpretation Task in Dynamic Environments

For embodied agents, navigation is an important ability but not an isola...
11/15/2020 ∙ by Hyounghun Kim, et al. ∙ 3 ∙ share

read it
DORB: Dynamically Optimizing Multiple Rewards with Bandits

Policy gradients-based reinforcement learning has proven to be a promisi...
11/15/2020 ∙ by Ramakanth Pasunuru, et al. ∙ 4 ∙ share

read it
HoVer: A Dataset for Many-Hop Fact Extraction And Claim Verification

We introduce HoVer (HOppy VERification), a dataset for many-hop evidence...
11/05/2020 ∙ by Yichen Jiang, et al. ∙ 4 ∙ share

read it
ConjNLI: Natural Language Inference Over Conjunctive Sentences

Reasoning about conjuncts in conjunctive sentences is important for a de...
10/20/2020 ∙ by Swarnadeep Saha, et al. ∙ 15 ∙ share

read it
What is More Likely to Happen Next? Video-and-Language Future Event Prediction

Given a video with aligned dialogue, people can often infer what is more...
10/15/2020 ∙ by Jie Lei, et al. ∙ 3 ∙ share

read it
Vokenization: Improving Language Understanding with Contextualized, Visual-Grounded Supervision

Humans learn language by listening, speaking, writing, reading, and also...
10/14/2020 ∙ by Hao Tan, et al. ∙ 3 ∙ share

read it
ChrEn: Cherokee-English Machine Translation for Endangered Language Revitalization

Cherokee is a highly endangered Native American language spoken by the C...
10/09/2020 ∙ by Shiyue Zhang, et al. ∙ 8 ∙ share

read it
Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?

Data collection for natural language (NL) understanding tasks has increa...
10/08/2020 ∙ by Peter Hase, et al. ∙ 7 ∙ share

read it
What Can We Learn from Collective Human Opinions on Natural Language Inference Data?

Despite the subjective nature of many NLP tasks, most NLU evaluations ha...
10/07/2020 ∙ by Yixin Nie, et al. ∙ 4 ∙ share

read it
Evaluating Interactive Summarization: an Expansion-Based Framework

Allowing users to interact with multi-document summarizers is a promisin...
09/17/2020 ∙ by Ori Shapira, et al. ∙ 0 ∙ share

read it
SuperPAL: Supervised Proposition ALignment for Multi-Document Summarization and Derivative Sub-Tasks

Multi-document summarization (MDS) is a challenging task, often decompos...
09/01/2020 ∙ by Ori Ernst, et al. ∙ 0 ∙ share

read it
Dense-Caption Matching and Frame-Selection Gating for Temporal Localization in VideoQA

Videos convey rich information. Dynamic spatio-temporal relationships be...
05/13/2020 ∙ by Hyounghun Kim, et al. ∙ 24 ∙ share

read it
MART: Memory-Augmented Recurrent Transformer for Coherent Video Paragraph Captioning

Generating multi-sentence descriptions for videos is one of the most cha...
05/11/2020 ∙ by Jie Lei, et al. ∙ 1 ∙ share

read it
Towards Robustifying NLI Models Against Lexical Dataset Biases

While deep learning models are making fast progress on the task of Natur...
05/10/2020 ∙ by Xiang Zhou, et al. ∙ 0 ∙ share

read it
Diagnosing the Environment Bias in Vision-and-Language Navigation

Vision-and-Language Navigation (VLN) requires an agent to follow natural...
05/06/2020 ∙ by Yubo Zhang, et al. ∙ 4 ∙ share

read it
Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?

Algorithmic approaches to interpreting machine learning models have prol...
05/04/2020 ∙ by Peter Hase, et al. ∙ 98 ∙ share

read it
The Curse of Performance Instability in Analysis Datasets: Consequences, Source, and Suggestions

We find that the performance of state-of-the-art models on Natural Langu...
04/28/2020 ∙ by Xiang Zhou, et al. ∙ 0 ∙ share

read it
Adversarial Augmentation Policy Search for Domain and Cross-Lingual Generalization in Reading Comprehension

Reading comprehension models often overfit to nuances of training datase...
04/13/2020 ∙ by Adyasha Maharana, et al. ∙ 25 ∙ share

read it
TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval

We introduce a new multimodal retrieval task - TV show Retrieval (TVR), ...
01/24/2020 ∙ by Jie Lei, et al. ∙ 8 ∙ share

read it
ManyModalQA: Modality Disambiguation and QA over Diverse Inputs

We present a new multimodal question answering challenge, ManyModalQA, i...
01/22/2020 ∙ by Darryl Hannan, et al. ∙ 18 ∙ share

read it
Modality-Balanced Models for Visual Dialogue

The Visual Dialog task requires a model to exploit both image and conver...
01/17/2020 ∙ by Hyounghun Kim, et al. ∙ 22 ∙ share

read it
AvgOut: A Simple Output-Probability Measure to Eliminate Dull Responses

Many sequence-to-sequence dialogue models tend to generate safe, uninfor...
01/15/2020 ∙ by Tong Niu, et al. ∙ 0 ∙ share

read it
Multi-Source Domain Adaptation for Text Classification via DistanceNet-Bandits

Domain adaptation performance of a learning algorithm on a target domain...
01/13/2020 ∙ by Han Guo, et al. ∙ 10 ∙ share

read it
Adversarial NLI: A New Benchmark for Natural Language Understanding

We introduce a new large-scale NLI benchmark dataset, collected via an i...
10/31/2019 ∙ by Yixin Nie, et al. ∙ 0 ∙ share

read it
Automatically Learning Data Augmentation Policies for Dialogue Tasks

Automatic data augmentation (AutoAugment) (Cubuk et al., 2019) searches ...
09/27/2019 ∙ by Tong Niu, et al. ∙ 25 ∙ share

read it
Revealing the Importance of Semantic Retrieval for Machine Reading at Scale

Machine Reading at Scale (MRS) is a challenging task in which a system i...
09/17/2019 ∙ by Yixin Nie, et al. ∙ 0 ∙ share

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

Text-based Question Generation (QG) aims at generating natural and relev...
09/13/2019 ∙ by Shiyue Zhang, et al. ∙ 0 ∙ share

read it
Self-Assembling Modular Networks for Interpretable Multi-Hop Reasoning

Multi-hop QA requires a model to connect multiple pieces of evidence sca...
09/12/2019 ∙ by Yichen Jiang, et al. ∙ 0 ∙ share

read it
LXMERT: Learning Cross-Modality Encoder Representations from Transformers

Vision-and-language reasoning requires an understanding of visual concep...
08/20/2019 ∙ by Hao Tan, et al. ∙ 0 ∙ share

read it
Expressing Visual Relationships via Language

Describing images with text is a fundamental problem in vision-language ...
06/18/2019 ∙ by Hao Tan, et al. ∙ 8 ∙ share

read it
Avoiding Reasoning Shortcuts: Adversarial Evaluation, Training, and Model Development for Multi-Hop QA

Multi-hop question answering requires a model to connect multiple pieces...
06/17/2019 ∙ by Yichen Jiang, et al. ∙ 0 ∙ share

read it
Improving Visual Question Answering by Referring to Generated Paragraph Captions

Paragraph-style image captions describe diverse aspects of an image as o...
06/14/2019 ∙ by Hyounghun Kim, et al. ∙ 0 ∙ share

read it
Continual and Multi-Task Architecture Search

Architecture search is the process of automatically learning the neural ...
06/12/2019 ∙ by Ramakanth Pasunuru, et al. ∙ 0 ∙ share

read it
Explore, Propose, and Assemble: An Interpretable Model for Multi-Hop Reading Comprehension

Multi-hop reading comprehension requires the model to explore and connec...
06/12/2019 ∙ by Yichen Jiang, et al. ∙ 0 ∙ share

read it
PaperRobot: Incremental Draft Generation of Scientific Ideas

We present a PaperRobot who performs as an automatic research assistant ...
05/20/2019 ∙ by Qingyun Wang, et al. ∙ 0 ∙ share

read it
Enabling Robots to Understand Incomplete Natural Language Instructions Using Commonsense Reasoning

Enabling robots to understand instructions provided via spoken natural l...
04/29/2019 ∙ by Haonan Chen, et al. ∙ 0 ∙ share

read it
TVQA+: Spatio-Temporal Grounding for Video Question Answering

We present the task of Spatio-Temporal Video Question Answering, which r...
04/25/2019 ∙ by Jie Lei, et al. ∙ 0 ∙ share

read it
Crowdsourcing Lightweight Pyramids for Manual Summary Evaluation

Conducting a manual evaluation is considered an essential part of summar...
04/11/2019 ∙ by Ori Shapira, et al. ∙ 0 ∙ share

read it
Multi-Target Embodied Question Answering

Embodied Question Answering (EQA) is a relatively new task where an agen...
04/09/2019 ∙ by Licheng Yu, et al. ∙ 6 ∙ share

read it
Learning to Navigate Unseen Environments: Back Translation with Environmental Dropout

A grand goal in AI is to build a robot that can accurately navigate base...
04/08/2019 ∙ by Hao Tan, et al. ∙ 0 ∙ share

read it
AutoSeM: Automatic Task Selection and Mixing in Multi-Task Learning

Multi-task learning (MTL) has achieved success over a wide range of prob...
04/08/2019 ∙ by Han Guo, et al. ∙ 0 ∙ share

read it
Combining Fact Extraction and Verification with Neural Semantic Matching Networks

The increasing concern with misinformation has stimulated research effor...
11/16/2018 ∙ by Yixin Nie, et al. ∙ 0 ∙ share

read it
Analyzing Compositionality-Sensitivity of NLI Models

Success in natural language inference (NLI) should require a model to un...
11/16/2018 ∙ by Yixin Nie, et al. ∙ 0 ∙ share

read it
Commonsense for Generative Multi-Hop Question Answering Tasks

Reading comprehension QA tasks have seen a recent surge in popularity, y...
09/17/2018 ∙ by Lisa Bauer, et al. ∙ 2 ∙ share

read it
SafeCity: Understanding Diverse Forms of Sexual Harassment Personal Stories

With the recent rise of #MeToo, an increasing number of personal stories...
09/13/2018 ∙ by Sweta Karlekar, et al. ∙ 0 ∙ share

read it
Closed-Book Training to Improve Summarization Encoder Memory

A good neural sequence-to-sequence summarization model should have a str...
09/12/2018 ∙ by Yichen Jiang, et al. ∙ 0 ∙ share

read it

Mohit Bansal

Featured Co-authors