research
∙
01/18/2021
Joint Energy-based Model Training for Better Calibrated Natural Language Understanding Models
In this work, we explore joint energy-based model (EBM) training during ...
share
research
∙
12/08/2020
CTRLsum: Towards Generic Controllable Text Summarization
Current summarization systems yield generic summaries that are disconnec...
research
∙
11/06/2020
What's New? Summarizing Contributions in Scientific Literature
With thousands of academic articles shared on a daily basis, it has beco...
research
∙
10/24/2020
Char2Subword: Extending the Subword Embedding Space from Pre-trained Models Using Robust Character Compositionality
Byte-pair encoding (BPE) is a ubiquitous algorithm in the subword tokeni...
research
∙
09/14/2020
GeDi: Generative Discriminator Guided Sequence Generation
Class-conditional language models (CC-LMs) can be used to generate natur...
research
∙
07/24/2020
SummEval: Re-evaluating Summarization Evaluation
The scarcity of comprehensive up-to-date studies on evaluation metrics f...
research
∙
05/03/2020
Double-Hard Debias: Tailoring Word Embeddings for Gender Bias Mitigation
Word embeddings derived from human-generated corpora inherit strong gend...
research
∙
05/02/2020
A Simple Language Model for Task-Oriented Dialogue
Task-oriented dialogue is often decomposed into three tasks: understandi...
research
∙
10/28/2019
Evaluating the Factual Consistency of Abstractive Text Summarization
Currently used metrics for assessing summarization algorithms do not acc...
research
∙
09/11/2019
CTRL: A Conditional Transformer Language Model for Controllable Generation
Large-scale language models show promising text generation capabilities,...
research
∙
08/23/2019
Neural Text Summarization: A Critical Evaluation
Text summarization aims at compressing long documents into a shorter for...
research
∙
06/06/2019
Explain Yourself! Leveraging Language Models for Commonsense Reasoning
Deep learning models perform poorly on tasks that require commonsense re...
research
∙
05/27/2019
XLDA: Cross-Lingual Data Augmentation for Natural Language Inference and Question Answering
While natural language processing systems often focus on a single langua...
research
∙
04/19/2019
Unifying Question Answering and Text Classification via Span Extraction
Even as pre-trained language encoders such as BERT are shared across man...
research
∙
06/20/2018
The Natural Language Decathlon: Multitask Learning as Question Answering
Deep learning has improved performance on many natural language processi...
research
∙
08/03/2017
Revisiting Activation Regularization for Language RNNs
Recurrent neural networks (RNNs) serve as a fundamental building block f...
research
∙
08/01/2017