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...
share
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...
research
∙
05/25/2023
IMBERT: Making BERT Immune to Insertion-based Backdoor Attacks
Backdoor attacks are an insidious security threat against machine learni...
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...
research
∙
03/15/2023
DeltaScore: Evaluating Story Generation with Differentiating Perturbations
Various evaluation metrics exist for natural language generation tasks, ...
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...
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...
research
∙
11/15/2022
A Survey for Efficient Open Domain Question Answering
Open domain question answering (ODQA) is a longstanding task aimed at an...
research
∙
10/17/2022
Systematic Evaluation of Predictive Fairness
Mitigating bias in training on biased datasets is an important open prob...
research
∙
10/11/2022
Detecting Backdoors in Deep Text Classifiers
Deep neural networks are vulnerable to adversarial attacks, such as back...
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...
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...
research
∙
09/15/2022
Rethinking Round-trip Translation for Automatic Machine Translation Evaluation
A parallel corpus is generally required to automatically evaluate the tr...
research
∙
05/09/2022
Improving negation detection with negation-focused pre-training
Negation is a common linguistic feature that is crucial in many language...
research
∙
05/05/2022
Optimising Equal Opportunity Fairness in Model Training
Real-world datasets often encode stereotypes and societal biases. Such b...
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 ...
research
∙
03/12/2022
Towards Equal Opportunity Fairness through Adversarial Learning
Adversarial training is a common approach for bias mitigation in natural...
research
∙
02/16/2022
ITTC @ TREC 2021 Clinical Trials Track
This paper describes the submissions of the Natural Language Processing ...
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...
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...
research
∙
10/08/2021
Unsupervised Cross-Lingual Transfer of Structured Predictors without Source Data
Providing technologies to communities or domains where training data is ...
research
∙
09/22/2021
Contrastive Learning for Fair Representations
Trained classification models can unintentionally lead to biased represe...
research
∙
09/21/2021
Fairness-aware Class Imbalanced Learning
Class imbalance is a common challenge in many NLP tasks, and has clear c...
research
∙
09/21/2021
Evaluating Debiasing Techniques for Intersectional Biases
Bias is pervasive in NLP models, motivating the development of automatic...
research
∙
09/20/2021
Commonsense Knowledge in Word Associations and ConceptNet
Humans use countless basic, shared facts about the world to efficiently ...
research
∙
09/16/2021
Balancing out Bias: Achieving Fairness Through Training Reweighting
Bias in natural language processing arises primarily from models learnin...
research
∙
08/12/2021
Generating Diverse Descriptions from Semantic Graphs
Text generation from semantic graphs is traditionally performed with det...
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 ...
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...
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 ...
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...
research
∙
01/25/2021
Diverse Adversaries for Mitigating Bias in Training
Adversarial learning can learn fairer and less biased models of language...
research
∙
11/02/2020
Targeted Poisoning Attacks on Black-Box Neural Machine Translation
As modern neural machine translation (NMT) systems have been widely depl...
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 ...
research
∙
02/11/2020
Learning Coupled Policies for Simultaneous Machine Translation
In simultaneous machine translation, the system needs to incrementally g...
research
∙
09/17/2019
Grounding learning of modifier dynamics: An application to color naming
Grounding is crucial for natural language understanding. An important su...
research
∙
08/31/2019
Deep Ordinal Regression for Pledge Specificity Prediction
Many pledges are made in the course of an election campaign, forming imp...
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...
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...
research
∙
05/20/2019
Target Based Speech Act Classification in Political Campaign Text
We study pragmatics in political campaign text, through analysis of spee...
research
∙
05/04/2019
Contextualization of Morphological Inflection
Critical to natural language generation is the production of correctly i...
research
∙
03/01/2019
A Unified Neural Architecture for Instrumental Audio Tasks
Within Music Information Retrieval (MIR), prominent tasks -- including p...
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...
research
∙
02/01/2019
Multilingual NER Transfer for Low-resource Languages
In massively multilingual transfer NLP models over many source languages...
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...
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...
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...
research
∙
05/28/2018
A Stochastic Decoder for Neural Machine Translation
The process of translation is ambiguous, in that there are typically man...
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...
research
∙
05/16/2018
