733 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- University of North Carolina at Chapel HillUS57 papers
- Duke UniversityUS4 papers
- The University of TokyoJP4 papers
- Applied Physical Sciences (United States)US3 papers
- Carnegie Mellon UniversityUS3 papers
- Centre National de la Recherche ScientifiqueFR3 papers
- Massachusetts Institute of TechnologyUS3 papers
- San Diego State UniversityUS3 papers
- Sorbonne UniversitéFR3 papers
- University of SalzburgAT3 papers
- California Institute of TechnologyUS2 papers
- Cornell UniversityUS2 papers
7 papers · 2 filters
I like fish, especially dolphins: Addressing Contradictions in Dialogue Modeling
Yixin Nie, Mary Williamson, Mohit Bansal +2
To quantify how well natural language understanding models can capture consistency in a general conversation, we introduce the DialoguE COntradiction DEtection task (DECODE) and a…
Summary-Source Proposition-level Alignment: Task, Datasets and Supervised Baseline
Ori Ernst, Ori Shapira, Ramakanth Pasunuru +4
Aligning sentences in a reference summary with their counterparts in source documents was shown as a useful auxiliary summarization task, notably for generating training data for s…
Diagnosing the Environment Bias in Vision-and-Language Navigation
Yubo Zhang, Hao Tan, Mohit Bansal
Vision-and-Language Navigation (VLN) requires an agent to follow natural-language instructions, explore the given environments, and reach the desired target locations. These step-b…
Multi-Source Domain Adaptation for Text Classification via DistanceNet-Bandits
Han Guo, Ramakanth Pasunuru, Mohit Bansal
Domain adaptation performance of a learning algorithm on a target domain is a function of its source domain error and a divergence measure between the data distribution of these tw…
ManyModalQA: Modality Disambiguation and QA over Diverse Inputs
Darryl Hannan, Akshay Jain, Mohit Bansal
We present a new multimodal question answering challenge, ManyModalQA, in which an agent must answer a question by considering three distinct modalities: text, images, and tables.…
Modality-Balanced Models for Visual Dialogue
Hyounghun Kim, Hao Tan, Mohit Bansal
The Visual Dialog task requires a model to exploit both image and conversational context information to generate the next response to the dialogue. However, via manual analysis, we…
AvgOut: A Simple Output-Probability Measure to Eliminate Dull Responses
Tong Niu, Mohit Bansal
Many sequence-to-sequence dialogue models tend to generate safe, uninformative responses. There have been various useful efforts on trying to eliminate them. However, these approac…