b'Trevor Cohn'

research

∙ 06/14/2023

Language models are not naysayers: An analysis of language models on negation benchmarks

Negation has been shown to be a major bottleneck for masked language mod...

0 Thinh Hung Truong, et al. ∙

research

∙ 05/26/2023

A Reminder of its Brittleness: Language Reward Shaping May Hinder Learning for Instruction Following Agents

Teaching agents to follow complex written instructions has been an impor...

0 Sukai Huang, et al. ∙

research

∙ 05/25/2023

IMBERT: Making BERT Immune to Insertion-based Backdoor Attacks

Backdoor attacks are an insidious security threat against machine learni...

0 Xuanli He, et al. ∙

research

∙ 05/19/2023

Mitigating Backdoor Poisoning Attacks through the Lens of Spurious Correlation

Modern NLP models are often trained over large untrusted datasets, raisi...

0 Xuanli He, et al. ∙

research

∙ 03/15/2023

DeltaScore: Evaluating Story Generation with Differentiating Perturbations

Various evaluation metrics exist for natural language generation tasks, ...

0 Zhuohan Xie, et al. ∙

research

∙ 02/11/2023

Fair Enough: Standardizing Evaluation and Model Selection for Fairness Research in NLP

Modern NLP systems exhibit a range of biases, which a growing literature...

0 Xudong Han, et al. ∙

research

∙ 01/24/2023

Can Very Large Pretrained Language Models Learn Storytelling With A Few Examples?

While pre-trained language models can generate individually fluent sente...

0 Zhuohan Xie, et al. ∙

research

∙ 11/15/2022

A Survey for Efficient Open Domain Question Answering

Open domain question answering (ODQA) is a longstanding task aimed at an...

16 Qin Zhang, et al. ∙

research

∙ 10/17/2022

Systematic Evaluation of Predictive Fairness

Mitigating bias in training on biased datasets is an important open prob...

0 Xudong Han, et al. ∙

research

∙ 10/11/2022

Detecting Backdoors in Deep Text Classifiers

Deep neural networks are vulnerable to adversarial attacks, such as back...

0 You Guo, et al. ∙

research

∙ 10/06/2022

Not another Negation Benchmark: The NaN-NLI Test Suite for Sub-clausal Negation

Negation is poorly captured by current language models, although the ext...

0 Hung Thinh Truong, et al. ∙

research

∙ 09/19/2022

LED down the rabbit hole: exploring the potential of global attention for biomedical multi-document summarisation

In this paper we report on our submission to the Multidocument Summarisa...

0 Yulia Otmakhova, et al. ∙

research

∙ 09/15/2022

Rethinking Round-trip Translation for Automatic Machine Translation Evaluation

A parallel corpus is generally required to automatically evaluate the tr...

11 Terry Yue Zhuo, et al. ∙

research

∙ 05/09/2022

Improving negation detection with negation-focused pre-training

Negation is a common linguistic feature that is crucial in many language...

0 Thinh Hung Truong, et al. ∙

research

∙ 05/05/2022

Optimising Equal Opportunity Fairness in Model Training

Real-world datasets often encode stereotypes and societal biases. Such b...

0 Aili Shen, et al. ∙

research

∙ 05/04/2022

fairlib: A Unified Framework for Assessing and Improving Classification Fairness

This paper presents fairlib, an open-source framework for assessing and ...

0 Xudong Han, et al. ∙

research

∙ 03/12/2022

Towards Equal Opportunity Fairness through Adversarial Learning

Adversarial training is a common approach for bias mitigation in natural...

0 Xudong Han, et al. ∙

research

∙ 02/16/2022

ITTC @ TREC 2021 Clinical Trials Track

This paper describes the submissions of the Natural Language Processing ...

0 Thinh Hung Truong, et al. ∙

research

∙ 11/15/2021

Exploring Story Generation with Multi-task Objectives in Variational Autoencoders

GPT-2 has been frequently adapted in story generation models as it provi...

0 Zhuohan Xie, et al. ∙

research

∙ 10/11/2021

It is Not as Good as You Think! Evaluating Simultaneous Machine Translation on Interpretation Data

Most existing simultaneous machine translation (SiMT) systems are traine...

0 Jinming Zhao, et al. ∙

research

∙ 10/08/2021

Unsupervised Cross-Lingual Transfer of Structured Predictors without Source Data

Providing technologies to communities or domains where training data is ...

0 Kemal Kurniawan, et al. ∙

research

∙ 09/22/2021

Contrastive Learning for Fair Representations

Trained classification models can unintentionally lead to biased represe...

0 Aili Shen, et al. ∙

research

∙ 09/21/2021

Fairness-aware Class Imbalanced Learning

Class imbalance is a common challenge in many NLP tasks, and has clear c...

0 Shivashankar Subramanian, et al. ∙

research

∙ 09/21/2021

Evaluating Debiasing Techniques for Intersectional Biases

Bias is pervasive in NLP models, motivating the development of automatic...

0 Shivashankar Subramanian, et al. ∙

research

∙ 09/20/2021

Commonsense Knowledge in Word Associations and ConceptNet

Humans use countless basic, shared facts about the world to efficiently ...

0 Chunhua Liu, et al. ∙

research

∙ 09/16/2021

Balancing out Bias: Achieving Fairness Through Training Reweighting

Bias in natural language processing arises primarily from models learnin...

0 Xudong Han, et al. ∙

research

∙ 08/12/2021

Generating Diverse Descriptions from Semantic Graphs

Text generation from semantic graphs is traditionally performed with det...

0 Jiuzhou Han, et al. ∙

research

∙ 07/18/2021

As Easy as 1, 2, 3: Behavioural Testing of NMT Systems for Numerical Translation

Mistranslated numbers have the potential to cause serious effects, such ...

12 Jun Wang, et al. ∙

research

∙ 07/12/2021

Putting words into the system's mouth: A targeted attack on neural machine translation using monolingual data poisoning

Neural machine translation systems are known to be vulnerable to adversa...

3 Jun Wang, et al. ∙

research

∙ 04/22/2021

Framing Unpacked: A Semi-Supervised Interpretable Multi-View Model of Media Frames

Understanding how news media frame political issues is important due to ...

0 Shima Khanehzar, et al. ∙

research

∙ 01/27/2021

PPT: Parsimonious Parser Transfer for Unsupervised Cross-Lingual Adaptation

Cross-lingual transfer is a leading technique for parsing low-resource l...

0 Kemal Kurniawan, et al. ∙

research

∙ 01/25/2021

Diverse Adversaries for Mitigating Bias in Training

Adversarial learning can learn fairer and less biased models of language...

0 Xudong Han, et al. ∙

research

∙ 11/02/2020

Targeted Poisoning Attacks on Black-Box Neural Machine Translation

As modern neural machine translation (NMT) systems have been widely depl...

28 Chang Xu, et al. ∙

research

∙ 06/11/2020

Tangled up in BLEU: Reevaluating the Evaluation of Automatic Machine Translation Evaluation Metrics

Automatic metrics are fundamental for the development and evaluation of ...

0 Nitika Mathur, et al. ∙

research

∙ 02/11/2020

Learning Coupled Policies for Simultaneous Machine Translation

In simultaneous machine translation, the system needs to incrementally g...

15 Philip Arthur, et al. ∙

research

∙ 09/17/2019

Grounding learning of modifier dynamics: An application to color naming

Grounding is crucial for natural language understanding. An important su...

0 Xudong Han, et al. ∙

research

∙ 08/31/2019

Deep Ordinal Regression for Pledge Specificity Prediction

Many pledges are made in the course of an election campaign, forming imp...

0 Shivashankar Subramanian, et al. ∙

research

∙ 07/05/2019

Improving Chemical Named Entity Recognition in Patents with Contextualized Word Embeddings

Chemical patents are an important resource for chemical information. How...

0 Zenan Zhai, et al. ∙

research

∙ 06/07/2019

Semi-supervised Stochastic Multi-Domain Learning using Variational Inference

Supervised models of NLP rely on large collections of text which closely...

0 Yitong Li, et al. ∙

research

∙ 05/20/2019

Target Based Speech Act Classification in Political Campaign Text

We study pragmatics in political campaign text, through analysis of spee...

0 Shivashankar Subramanian, et al. ∙

research

∙ 05/04/2019

Contextualization of Morphological Inflection

Critical to natural language generation is the production of correctly i...

0 Ekaterina Vylomova, et al. ∙

research

∙ 03/01/2019

A Unified Neural Architecture for Instrumental Audio Tasks

Within Music Information Retrieval (MIR), prominent tasks -- including p...

0 Steven Spratley, et al. ∙

research

∙ 02/24/2019

Truth Inference at Scale: A Bayesian Model for Adjudicating Highly Redundant Crowd Annotations

Crowd-sourcing is a cheap and popular means of creating training and eva...

0 Yuan Li, et al. ∙

research

∙ 02/01/2019

Multilingual NER Transfer for Low-resource Languages

In massively multilingual transfer NLP models over many source languages...

0 Afshin Rahimi, et al. ∙

research

∙ 08/28/2018

Evaluating the Utility of Hand-crafted Features in Sequence Labelling

Conventional wisdom is that hand-crafted features are redundant for deep...

0 Minghao Wu, et al. ∙

research

∙ 07/10/2018

Deep-speare: A Joint Neural Model of Poetic Language, Meter and Rhyme

In this paper, we propose a joint architecture that captures language, r...

0 Jey Han Lau, et al. ∙

research

∙ 06/26/2018

Graph-to-Sequence Learning using Gated Graph Neural Networks

Many NLP applications can be framed as a graph-to-sequence learning prob...

0 Daniel Beck, et al. ∙

research

∙ 05/28/2018

A Stochastic Decoder for Neural Machine Translation

The process of translation is ambiguous, in that there are typically man...

0 Philip Schulz, et al. ∙

research

∙ 05/17/2018

Content-based Popularity Prediction of Online Petitions Using a Deep Regression Model

Online petitions are a cost-effective way for citizens to collectively e...

0 Shivashankar Subramanian, et al. ∙

research

∙ 05/16/2018

Narrative Modeling with Memory Chains and Semantic Supervision

Story comprehension requires a deep semantic understanding of the narrat...

0 Fei Liu, et al. ∙

Trevor Cohn

Featured Co-authors