activity
20152021
most citeddeltaBLEU: A Discriminative Metric for Generation Tasks with Intrinsically Diverse Targets

95 citations · 332 across the 11 of their papers we have counts for

collaborators

21 papers

cs.CL2021

Automatic Document Sketching: Generating Drafts from Analogous Texts

Zeqiu Wu, Michel Galley, Chris Brockett +2

The advent of large pre-trained language models has made it possible to make high-quality predictions on how to add or change a sentence in a document. However, the high branching…

cs.CL2020

Text Editing by Command

Felix Faltings, Michel Galley, Gerold Hintz +4

A prevailing paradigm in neural text generation is one-shot generation, where text is produced in a single step. The one-shot setting is inadequate, however, when the constraints t…

cs.CL20206 cited

Dialogue Response Ranking Training with Large-Scale Human Feedback Data

Xiang Gao, Yizhe Zhang, Michel Galley +2

Existing open-domain dialog models are generally trained to minimize the perplexity of target human responses. However, some human replies are more engaging than others, spawning m…

cs.CL2020

Contextualized Perturbation for Textual Adversarial Attack

Dianqi Li, Yizhe Zhang, Hao Peng +4

Adversarial examples expose the vulnerabilities of natural language processing (NLP) models, and can be used to evaluate and improve their robustness. Existing techniques of genera…

cs.CL2020

A Recipe for Creating Multimodal Aligned Datasets for Sequential Tasks

Angela S. Lin, Sudha Rao, Asli Celikyilmaz +4

Many high-level procedural tasks can be decomposed into sequences of instructions that vary in their order and choice of tools. In the cooking domain, the web offers many partially…

cs.CL202010 cited

POINTER: Constrained Progressive Text Generation via Insertion-based Generative Pre-training

Yizhe Zhang, Guoyin Wang, Chunyuan Li +3

Large-scale pre-trained language models, such as BERT and GPT-2, have achieved excellent performance in language representation learning and free-form text generation. However, the…