Search Results for author: Dipanjan Das

Found 38 papers, 14 papers with code

Speech-driven Facial Animation using Cascaded GANs for Learning of Motion and Texture

no code implementations ECCV 2020 Dipanjan Das, Sandika Biswas, Sanjana Sinha, Brojeshwar Bhowmick

Current state-of-the-art methods fail to generate realistic animation from any speech on unknown faces due to their poor gen-eralization over different facial characteristics, languages, and accents.

Meta-Learning

A Well-Composed Text is Half Done! Composition Sampling for Diverse Conditional Generation

1 code implementation ACL 2022 Shashi Narayan, Gonçalo Simões, Yao Zhao, Joshua Maynez, Dipanjan Das, Michael Collins, Mirella Lapata

We propose Composition Sampling, a simple but effective method to generate diverse outputs for conditional generation of higher quality compared to previous stochastic decoding strategies.

Question Generation

Measuring Attribution in Natural Language Generation Models

no code implementations23 Dec 2021 Hannah Rashkin, Vitaly Nikolaev, Matthew Lamm, Michael Collins, Dipanjan Das, Slav Petrov, Gaurav Singh Tomar, Iulia Turc, David Reitter

With recent improvements in natural language generation (NLG) models for various applications, it has become imperative to have the means to identify and evaluate whether NLG output is only sharing verifiable information about the external world.

Text Generation

Decontextualization: Making Sentences Stand-Alone

no code implementations9 Feb 2021 Eunsol Choi, Jennimaria Palomaki, Matthew Lamm, Tom Kwiatkowski, Dipanjan Das, Michael Collins

Models for question answering, dialogue agents, and summarization often interpret the meaning of a sentence in a rich context and use that meaning in a new context.

Question Answering

Variational Clustering: Leveraging Variational Autoencoders for Image Clustering

no code implementations10 May 2020 Vignesh Prasad, Dipanjan Das, Brojeshwar Bhowmick

Since we wish to efficiently discriminate between different clusters in the data, we propose a method based on VAEs where we use a Gaussian Mixture prior to help cluster the images accurately.

Image Clustering

ToTTo: A Controlled Table-To-Text Generation Dataset

1 code implementation EMNLP 2020 Ankur P. Parikh, Xuezhi Wang, Sebastian Gehrmann, Manaal Faruqui, Bhuwan Dhingra, Diyi Yang, Dipanjan Das

We present ToTTo, an open-domain English table-to-text dataset with over 120, 000 training examples that proposes a controlled generation task: given a Wikipedia table and a set of highlighted table cells, produce a one-sentence description.

Conditional Text Generation Data-to-Text Generation +1

Syntactic Data Augmentation Increases Robustness to Inference Heuristics

1 code implementation ACL 2020 Junghyun Min, R. Thomas McCoy, Dipanjan Das, Emily Pitler, Tal Linzen

Pretrained neural models such as BERT, when fine-tuned to perform natural language inference (NLI), often show high accuracy on standard datasets, but display a surprising lack of sensitivity to word order on controlled challenge sets.

Data Augmentation Natural Language Inference

BLEURT: Learning Robust Metrics for Text Generation

3 code implementations ACL 2020 Thibault Sellam, Dipanjan Das, Ankur P. Parikh

We propose BLEURT, a learned evaluation metric based on BERT that can model human judgments with a few thousand possibly biased training examples.

Text Generation

Handling Divergent Reference Texts when Evaluating Table-to-Text Generation

1 code implementation ACL 2019 Bhuwan Dhingra, Manaal Faruqui, Ankur Parikh, Ming-Wei Chang, Dipanjan Das, William W. Cohen

Automatically constructed datasets for generating text from semi-structured data (tables), such as WikiBio, often contain reference texts that diverge from the information in the corresponding semi-structured data.

Table-to-Text Generation

Deep Representation Learning Characterized by Inter-class Separation for Image Clustering

no code implementations19 Jan 2019 Dipanjan Das, Ratul Ghosh, Brojeshwar Bhowmick

Despite significant advances in clustering methods in recent years, the outcome of clustering of a natural image dataset is still unsatisfactory due to two important drawbacks.

Image Clustering Representation Learning

Epipolar Geometry based Learning of Multi-view Depth and Ego-Motion from Monocular Sequences

no code implementations23 Dec 2018 Vignesh Prasad, Dipanjan Das, Brojeshwar Bhowmick

The proposed method results in better depth images and pose estimates, which capture the scene structure and motion in a better way.

Visual Odometry

Learning To Split and Rephrase From Wikipedia Edit History

1 code implementation EMNLP 2018 Jan A. Botha, Manaal Faruqui, John Alex, Jason Baldridge, Dipanjan Das

Split and rephrase is the task of breaking down a sentence into shorter ones that together convey the same meaning.

Split and Rephrase

Identifying Well-formed Natural Language Questions

1 code implementation EMNLP 2018 Manaal Faruqui, Dipanjan Das

Understanding search queries is a hard problem as it involves dealing with "word salad" text ubiquitously issued by users.

Query Wellformedness

Learning Recurrent Span Representations for Extractive Question Answering

2 code implementations4 Nov 2016 Kenton Lee, Shimi Salant, Tom Kwiatkowski, Ankur Parikh, Dipanjan Das, Jonathan Berant

In this paper, we focus on this answer extraction task, presenting a novel model architecture that efficiently builds fixed length representations of all spans in the evidence document with a recurrent network.

Answer Selection Natural Language Understanding +1

Transforming Dependency Structures to Logical Forms for Semantic Parsing

1 code implementation TACL 2016 Siva Reddy, Oscar T{\"a}ckstr{\"o}m, Michael Collins, Tom Kwiatkowski, Dipanjan Das, Mark Steedman, Mirella Lapata

In contrast{---}partly due to the lack of a strong type system{---}dependency structures are easy to annotate and have become a widely used form of syntactic analysis for many languages.

Question Answering Semantic Parsing +1

A Universal Part-of-Speech Tagset

1 code implementation LREC 2012 Slav Petrov, Dipanjan Das, Ryan Mcdonald

To facilitate future research in unsupervised induction of syntactic structure and to standardize best-practices, we propose a tagset that consists of twelve universal part-of-speech categories.

Cannot find the paper you are looking for? You can Submit a new open access paper.