activity
20172021
most citedCrowdsourcing Lightweight Pyramids for Manual Summary Evaluation

4 citations · 12 across the 7 of their papers we have counts for

collaborators
Showing cs.CLShow all

13 papers · 1 filter

cs.CL2021

Dual Reinforcement-Based Specification Generation for Image De-Rendering

Ramakanth Pasunuru, David Rosenberg, Gideon Mann +1

Advances in deep learning have led to promising progress in inferring graphics programs by de-rendering computer-generated images. However, current methods do not explore which dec…

cs.CL2021

Data Augmentation for Abstractive Query-Focused Multi-Document Summarization

Ramakanth Pasunuru, Asli Celikyilmaz, Michel Galley +4

The progress in Query-focused Multi-Document Summarization (QMDS) has been limited by the lack of sufficient largescale high-quality training datasets. We present two QMDS training…

cs.CL2020

DORB: Dynamically Optimizing Multiple Rewards with Bandits

Ramakanth Pasunuru, Han Guo, Mohit Bansal

Policy gradients-based reinforcement learning has proven to be a promising approach for directly optimizing non-differentiable evaluation metrics for language generation tasks. How…

cs.CL20201 cited

Evaluating Interactive Summarization: an Expansion-Based Framework

Ori Shapira, Ramakanth Pasunuru, Hadar Ronen +3

Allowing users to interact with multi-document summarizers is a promising direction towards improving and customizing summary results. Different ideas for interactive summarization…

cs.CL20203 cited

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…

cs.CL2019

Continual and Multi-Task Architecture Search

Ramakanth Pasunuru, Mohit Bansal

Architecture search is the process of automatically learning the neural model or cell structure that best suits the given task. Recently, this approach has shown promising performa…