activity
20162019
most citedMulti-Task Learning for Speaker-Role Adaptation in Neural Conversation Models

65 citations · 316 across the 11 of their papers we have counts for

collaborators

11 papers

cs.CL2019★ 14 cited

Entity, Relation, and Event Extraction with Contextualized Span Representations

David Wadden, Ulme Wennberg, Yi Luan +1

We examine the capabilities of a unified, multi-task framework for three information extraction tasks: named entity recognition, relation extraction, and event extraction. Our fram…

cs.CL2019★ 44 cited

PaperRobot: Incremental Draft Generation of Scientific Ideas

Qingyun Wang, Lifu Huang, Zhiying Jiang +4

We present a PaperRobot who performs as an automatic research assistant by (1) conducting deep understanding of a large collection of human-written papers in a target domain and co…

cs.CL2019★ 38 cited

A General Framework for Information Extraction using Dynamic Span Graphs

Yi Luan, Dave Wadden, Luheng He +3

We introduce a general framework for several information extraction tasks that share span representations using dynamically constructed span graphs. The graphs are constructed by s…

cs.CL2019★ 44 cited

Text Generation from Knowledge Graphs with Graph Transformers

Rik Koncel-Kedziorski, Dhanush Bekal, Yi Luan +2

Generating texts which express complex ideas spanning multiple sentences requires a structured representation of their content (document plan), but these representations are prohib…

cs.IR2018★ 2 cited

Information Extraction from Scientific Literature for Method Recommendation

Yi Luan

As a research community grows, more and more papers are published each year. As a result there is increasing demand for improved methods for finding relevant papers, automatically…

cs.CL2018★ 1 cited

Monolingual sentence matching for text simplification

Yonghui Huang, Yunhui Li, Yi Luan

This work improves monolingual sentence alignment for text simplification, specifically for text in standard and simple Wikipedia. We introduce a convolutional neural network struc…