activity
20152022
most citedWhat do you learn from context? Probing for sentence structure in contextualized word representations

139 citations · 237 across the 27 of their papers we have counts for

collaborators
Showing cs.CLShow all

54 papers · 1 filter

cs.CL20221 cited

Automatic Document Selection for Efficient Encoder Pretraining

Yukun Feng, Patrick Xia, Benjamin Van Durme +1

Building pretrained language models is considered expensive and data-intensive, but must we increase dataset size to achieve better performance? We propose an alternative to larger…

cs.CL2022

An Empirical Study on Finding Spans

Weiwei Gu, Boyuan Zheng, Yunmo Chen +2

We present an empirical study on methods for span finding, the selection of consecutive tokens in text for some downstream tasks. We focus on approaches that can be employed in tra…

cs.CL2022

Asking the Right Questions in Low Resource Template Extraction

Nils Holzenberger, Yunmo Chen, Benjamin Van Durme

Information Extraction (IE) researchers are mapping tasks to Question Answering (QA) in order to leverage existing large QA resources, and thereby improve data efficiency. Especial…

cs.CL20221 cited

Addressing Resource and Privacy Constraints in Semantic Parsing Through Data Augmentation

Kevin Yang, Olivia Deng, Charles Chen +3

We introduce a novel setup for low-resource task-oriented semantic parsing which incorporates several constraints that may arise in real-world scenarios: (1) lack of similar datase…

cs.CL2022

Visual Commonsense in Pretrained Unimodal and Multimodal Models

Chenyu Zhang, Benjamin Van Durme, Zhuowan Li +1

Our commonsense knowledge about objects includes their typical visual attributes; we know that bananas are typically yellow or green, and not purple. Text and image corpora, being…

cs.CL20222 cited

One-Shot Learning from a Demonstration with Hierarchical Latent Language

Nathaniel Weir, Xingdi Yuan, Marc-Alexandre Côté +5

Humans have the capability, aided by the expressive compositionality of their language, to learn quickly by demonstration. They are able to describe unseen task-performing procedur…