activity
20182022
most citedBeyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Bases

112 citations · 138 across the 7 of their papers we have counts for

collaborators

13 papers

cs.CL2021

ReasonBERT: Pre-trained to Reason with Distant Supervision

Xiang Deng, Yu Su, Alyssa Lees +3

We present ReasonBert, a pre-training method that augments language models with the ability to reason over long-range relations and multiple, possibly hybrid contexts. Unlike exist…

cs.CL2021

A Systematic Investigation of KB-Text Embedding Alignment at Scale

Vardaan Pahuja, Yu Gu, Wenhu Chen +4

Knowledge bases (KBs) and text often contain complementary knowledge: KBs store structured knowledge that can support long range reasoning, while text stores more comprehensive and…

cs.CL2020

An Investigation of Language Model Interpretability via Sentence Editing

Samuel Stevens, Yu Su

Pre-trained language models (PLMs) like BERT are being used for almost all language-related tasks, but interpreting their behavior still remains a significant challenge and many im…

cs.CL2020112 cited

Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Bases

Yu Gu, Sue Kase, Michelle Vanni +4

Existing studies on question answering on knowledge bases (KBQA) mainly operate with the standard i.i.d assumption, i.e., training distribution over questions is the same as the te…

cs.CL2020

KGPT: Knowledge-Grounded Pre-Training for Data-to-Text Generation

Wenhu Chen, Yu Su, Xifeng Yan +1

Data-to-text generation has recently attracted substantial interests due to its wide applications. Existing methods have shown impressive performance on an array of tasks. However,…

cs.CL2020

Task-Oriented Dialogue as Dataflow Synthesis

Semantic Machines, Jacob Andreas, John Bufe +43

We describe an approach to task-oriented dialogue in which dialogue state is represented as a dataflow graph. A dialogue agent maps each user utterance to a program that extends th…