activity
20182022
most citedBiToD: A Bilingual Multi-Domain Dataset For Task-Oriented Dialogue Modeling

35 citations · 78 across the 12 of their papers we have counts for

collaborators

19 papers

cs.CL2022

Evaluating Parameter Efficient Learning for Generation

Peng Xu, Mostofa Patwary, Shrimai Prabhumoye +6

Parameter efficient learning methods (PERMs) have recently gained significant attention as they provide an efficient way for pre-trained language models (PLMs) to adapt to a downst…

cs.CL20221 cited

QA4QG: Using Question Answering to Constrain Multi-Hop Question Generation

Dan Su, Peng Xu, Pascale Fung

Multi-hop question generation (MQG) aims to generate complex questions which require reasoning over multiple pieces of information of the input passage. Most existing work on MQG h…

cs.CL2021

CAiRE in DialDoc21: Data Augmentation for Information-Seeking Dialogue System

Etsuko Ishii, Yan Xu, Genta Indra Winata +5

Information-seeking dialogue systems, including knowledge identification and response generation, aim to respond to users with fluent, coherent, and informative responses based on…

cs.CL20211 cited

X2Parser: Cross-Lingual and Cross-Domain Framework for Task-Oriented Compositional Semantic Parsing

Zihan Liu, Genta Indra Winata, Peng Xu +1

Task-oriented compositional semantic parsing (TCSP) handles complex nested user queries and serves as an essential component of virtual assistants. Current TCSP models rely on nume…

cs.CL202135 cited

BiToD: A Bilingual Multi-Domain Dataset For Task-Oriented Dialogue Modeling

Zhaojiang Lin, Andrea Madotto, Genta Indra Winata +5

Task-oriented dialogue (ToD) benchmarks provide an important avenue to measure progress and develop better conversational agents. However, existing datasets for end-to-end ToD mode…

cs.CL202012 cited

MEGATRON-CNTRL: Controllable Story Generation with External Knowledge Using Large-Scale Language Models

Peng Xu, Mostofa Patwary, Mohammad Shoeybi +4

Existing pre-trained large language models have shown unparalleled generative capabilities. However, they are not controllable. In this paper, we propose MEGATRON-CNTRL, a novel fr…