activity
20172022
most citedLearning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks

26 citations · 117 across the 27 of their papers we have counts for

collaborators

47 papers

cs.CL20224 cited

Salience Allocation as Guidance for Abstractive Summarization

Fei Wang, Kaiqiang Song, Hongming Zhang +6

Abstractive summarization models typically learn to capture the salient information from scratch implicitly. Recent literature adds extractive summaries as guidance for abstractive…

cs.CL2022

SpaBERT: A Pretrained Language Model from Geographic Data for Geo-Entity Representation

Zekun Li, Jina Kim, Yao-Yi Chiang +1

Named geographic entities (geo-entities for short) are the building blocks of many geographic datasets. Characterizing geo-entities is integral to various application domains, such…

cs.CL2022

Extracting or Guessing? Improving Faithfulness of Event Temporal Relation Extraction

Haoyu Wang, Hongming Zhang, Yuqian Deng +3

In this paper, we seek to improve the faithfulness of TempRel extraction models from two perspectives. The first perspective is to extract genuinely based on contextual description…

cs.CL2022

VIPHY: Probing "Visible" Physical Commonsense Knowledge

Shikhar Singh, Ehsan Qasemi, Muhao Chen

In recent years, vision-language models (VLMs) have shown remarkable performance on visual reasoning tasks (e.g. attributes, location). While such tasks measure the requisite knowl…

cs.LG2022

Bending the Future: Autoregressive Modeling of Temporal Knowledge Graphs in Curvature-Variable Hyperbolic Spaces

Jihoon Sohn, Mingyu Derek Ma, Muhao Chen

Recently there is an increasing scholarly interest in time-varying knowledge graphs, or temporal knowledge graphs (TKG). Previous research suggests diverse approaches to TKG reason…

cs.CL20221 cited

Robust (Controlled) Table-to-Text Generation with Structure-Aware Equivariance Learning

Fei Wang, Zhewei Xu, Pedro Szekely +1

Controlled table-to-text generation seeks to generate natural language descriptions for highlighted subparts of a table. Previous SOTA systems still employ a sequence-to-sequence g…