activity
20172021
most citedXLDA: Cross-Lingual Data Augmentation for Natural Language Inference and Question Answering

61 citations · 161 across the 5 of their papers we have counts for

collaborators
Showing cs.CLShow all

14 papers · 1 filter

cs.CL20212 cited

Joint Energy-based Model Training for Better Calibrated Natural Language Understanding Models

Tianxing He, Bryan McCann, Caiming Xiong +1

In this work, we explore joint energy-based model (EBM) training during the finetuning of pretrained text encoders (e.g., Roberta) for natural language understanding (NLU) tasks. O…

cs.CL202050 cited

CTRLsum: Towards Generic Controllable Text Summarization

Junxian He, Wojciech Kryściński, Bryan McCann +2

Current summarization systems yield generic summaries that are disconnected from users' preferences and expectations. To address this limitation, we present CTRLsum, a novel framew…

cs.CL20205 cited

What's New? Summarizing Contributions in Scientific Literature

Hiroaki Hayashi, Wojciech Kryściński, Bryan McCann +2

With thousands of academic articles shared on a daily basis, it has become increasingly difficult to keep up with the latest scientific findings. To overcome this problem, we intro…

cs.CL2020

GeDi: Generative Discriminator Guided Sequence Generation

Ben Krause, Akhilesh Deepak Gotmare, Bryan McCann +4

While large-scale language models (LMs) are able to imitate the distribution of natural language well enough to generate realistic text, it is difficult to control which regions of…

cs.CL2020

Char2Subword: Extending the Subword Embedding Space Using Robust Character Compositionality

Gustavo Aguilar, Bryan McCann, Tong Niu +3

Byte-pair encoding (BPE) is a ubiquitous algorithm in the subword tokenization process of language models as it provides multiple benefits. However, this process is solely based on…

cs.CL2020

SummEval: Re-evaluating Summarization Evaluation

Alexander R. Fabbri, Wojciech Kryściński, Bryan McCann +3

The scarcity of comprehensive up-to-date studies on evaluation metrics for text summarization and the lack of consensus regarding evaluation protocols continue to inhibit progress.…