Search Results for author: Trevor Cohn

Found 156 papers, 66 papers with code

Document Level Hierarchical Transformer

no code implementations ALTA 2021 Najam Zaidi, Trevor Cohn, Gholamreza Haffari

In this paper, we present a novel semi-autoregressive document generation model capable of revising and editing the generated text.

Document Level Machine Translation Imitation Learning +3

Measuring and Mitigating Name Biases in Neural Machine Translation

no code implementations ACL 2022 Jun Wang, Benjamin Rubinstein, Trevor Cohn

In this paper we describe a new source of bias prevalent in NMT systems, relating to translations of sentences containing person names.

Data Augmentation Machine Translation +2

Simpson's Paradox and the Accuracy-Fluency Tradeoff in Translation

no code implementations20 Feb 2024 Zheng Wei Lim, Ekaterina Vylomova, Trevor Cohn, Charles Kemp

On one hand, intuition and some prior work suggest that accuracy and fluency should trade off against each other, and that capturing every detail of the source can only be achieved at the cost of fluency.

Sentence Translation

Predicting Human Translation Difficulty with Neural Machine Translation

no code implementations19 Dec 2023 Zheng Wei Lim, Ekaterina Vylomova, Charles Kemp, Trevor Cohn

Human translators linger on some words and phrases more than others, and predicting this variation is a step towards explaining the underlying cognitive processes.

Machine Translation NMT +1

Noisy Self-Training with Synthetic Queries for Dense Retrieval

1 code implementation27 Nov 2023 Fan Jiang, Tom Drummond, Trevor Cohn

Although existing neural retrieval models reveal promising results when training data is abundant and the performance keeps improving as training data increases, collecting high-quality annotated data is prohibitively costly.

Retrieval

Boot and Switch: Alternating Distillation for Zero-Shot Dense Retrieval

1 code implementation27 Nov 2023 Fan Jiang, Qiongkai Xu, Tom Drummond, Trevor Cohn

Experimental results demonstrate that our unsupervised $\texttt{ABEL}$ model outperforms both leading supervised and unsupervised retrievers on the BEIR benchmark.

Passage Retrieval Retrieval

Fingerprint Attack: Client De-Anonymization in Federated Learning

1 code implementation12 Sep 2023 Qiongkai Xu, Trevor Cohn, Olga Ohrimenko

Federated Learning allows collaborative training without data sharing in settings where participants do not trust the central server and one another.

Clustering Federated Learning

IMBERT: Making BERT Immune to Insertion-based Backdoor Attacks

1 code implementation25 May 2023 Xuanli He, Jun Wang, Benjamin Rubinstein, Trevor Cohn

Backdoor attacks are an insidious security threat against machine learning models.

Mitigating Backdoor Poisoning Attacks through the Lens of Spurious Correlation

1 code implementation19 May 2023 Xuanli He, Qiongkai Xu, Jun Wang, Benjamin Rubinstein, Trevor Cohn

Modern NLP models are often trained over large untrusted datasets, raising the potential for a malicious adversary to compromise model behaviour.

DeltaScore: Fine-Grained Story Evaluation with Perturbations

1 code implementation15 Mar 2023 Zhuohan Xie, Miao Li, Trevor Cohn, Jey Han Lau

Numerous evaluation metrics have been developed for natural language generation tasks, but their effectiveness in evaluating stories is limited as they are not specifically tailored to assess intricate aspects of storytelling, such as fluency and interestingness.

Language Modelling Story Generation

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

1 code implementation11 Feb 2023 Xudong Han, Timothy Baldwin, Trevor Cohn

Modern NLP systems exhibit a range of biases, which a growing literature on model debiasing attempts to correct.

Fairness Model Selection +1

The Next Chapter: A Study of Large Language Models in Storytelling

no code implementations24 Jan 2023 Zhuohan Xie, Trevor Cohn, Jey Han Lau

To enhance the quality of generated stories, recent story generation models have been investigating the utilization of higher-level attributes like plots or commonsense knowledge.

Story Generation World Knowledge

Detecting Backdoors in Deep Text Classifiers

no code implementations11 Oct 2022 You Guo, Jun Wang, Trevor Cohn

Deep neural networks are vulnerable to adversarial attacks, such as backdoor attacks in which a malicious adversary compromises a model during training such that specific behaviour can be triggered at test time by attaching a specific word or phrase to an input.

Data Poisoning text-classification +1

Rethinking Round-Trip Translation for Machine Translation Evaluation

1 code implementation15 Sep 2022 Terry Yue Zhuo, Qiongkai Xu, Xuanli He, Trevor Cohn

Round-trip translation could be served as a clever and straightforward technique to alleviate the requirement of the parallel evaluation corpus.

Machine Translation Translation

Improving negation detection with negation-focused pre-training

no code implementations NAACL 2022 Thinh Hung Truong, Timothy Baldwin, Trevor Cohn, Karin Verspoor

Negation is a common linguistic feature that is crucial in many language understanding tasks, yet it remains a hard problem due to diversity in its expression in different types of text.

Data Augmentation Negation +1

Towards Equal Opportunity Fairness through Adversarial Learning

1 code implementation12 Mar 2022 Xudong Han, Timothy Baldwin, Trevor Cohn

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

Fairness

Incorporating Constituent Syntax for Coreference Resolution

1 code implementation22 Feb 2022 Fan Jiang, Trevor Cohn

Moreover, we also explore to utilise higher-order neighbourhood information to encode rich structures in constituent trees.

coreference-resolution

ITTC @ TREC 2021 Clinical Trials Track

no code implementations16 Feb 2022 Thinh Hung Truong, Yulia Otmakhova, Rahmad Mahendra, Timothy Baldwin, Jey Han Lau, Trevor Cohn, Lawrence Cavedon, Damiano Spina, Karin Verspoor

This paper describes the submissions of the Natural Language Processing (NLP) team from the Australian Research Council Industrial Transformation Training Centre (ITTC) for Cognitive Computing in Medical Technologies to the TREC 2021 Clinical Trials Track.

Retrieval

Unsupervised Cross-Lingual Transfer of Structured Predictors without Source Data

1 code implementation NAACL 2022 Kemal Kurniawan, Lea Frermann, Philip Schulz, Trevor Cohn

Providing technologies to communities or domains where training data is scarce or protected e. g., for privacy reasons, is becoming increasingly important.

Cross-Lingual Transfer Dependency Parsing +1

Contrastive Learning for Fair Representations

no code implementations22 Sep 2021 Aili Shen, Xudong Han, Trevor Cohn, Timothy Baldwin, Lea Frermann

Trained classification models can unintentionally lead to biased representations and predictions, which can reinforce societal preconceptions and stereotypes.

Attribute Contrastive Learning

Fairness-aware Class Imbalanced Learning

no code implementations EMNLP 2021 Shivashankar Subramanian, Afshin Rahimi, Timothy Baldwin, Trevor Cohn, Lea Frermann

Class imbalance is a common challenge in many NLP tasks, and has clear connections to bias, in that bias in training data often leads to higher accuracy for majority groups at the expense of minority groups.

Fairness Long-tail Learning

Balancing out Bias: Achieving Fairness Through Balanced Training

no code implementations16 Sep 2021 Xudong Han, Timothy Baldwin, Trevor Cohn

Group bias in natural language processing tasks manifests as disparities in system error rates across texts authorized by different demographic groups, typically disadvantaging minority groups.

Fairness

Generating Diverse Descriptions from Semantic Graphs

1 code implementation INLG (ACL) 2021 Jiuzhou Han, Daniel Beck, Trevor Cohn

Text generation from semantic graphs is traditionally performed with deterministic methods, which generate a unique description given an input graph.

Text Generation

PTST-UoM at SemEval-2021 Task 10: Parsimonious Transfer for Sequence Tagging

no code implementations SEMEVAL 2021 Kemal Kurniawan, Lea Frermann, Philip Schulz, Trevor Cohn

This paper describes PTST, a source-free unsupervised domain adaptation technique for sequence tagging, and its application to the SemEval-2021 Task 10 on time expression recognition.

Unsupervised Domain Adaptation

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

1 code implementation12 Jul 2021 Jun Wang, Chang Xu, Francisco Guzman, Ahmed El-Kishky, Yuqing Tang, Benjamin I. P. Rubinstein, Trevor Cohn

Neural machine translation systems are known to be vulnerable to adversarial test inputs, however, as we show in this paper, these systems are also vulnerable to training attacks.

Data Poisoning Machine Translation +3

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

1 code implementation NAACL 2021 Shima Khanehzar, Trevor Cohn, Gosia Mikolajczak, Andrew Turpin, Lea Frermann

Understanding how news media frame political issues is important due to its impact on public attitudes, yet hard to automate.

PPT: Parsimonious Parser Transfer for Unsupervised Cross-Lingual Adaptation

1 code implementation EACL 2021 Kemal Kurniawan, Lea Frermann, Philip Schulz, Trevor Cohn

Cross-lingual transfer is a leading technique for parsing low-resource languages in the absence of explicit supervision.

Cross-Lingual Transfer

Diverse Adversaries for Mitigating Bias in Training

1 code implementation EACL 2021 Xudong Han, Timothy Baldwin, Trevor Cohn

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

A Targeted Attack on Black-Box Neural Machine Translation with Parallel Data Poisoning

no code implementations2 Nov 2020 Chang Xu, Jun Wang, Yuqing Tang, Francisco Guzman, Benjamin I. P. Rubinstein, Trevor Cohn

In this paper, we show that targeted attacks on black-box NMT systems are feasible, based on poisoning a small fraction of their parallel training data.

Data Poisoning Machine Translation +2

Decoding As Dynamic Programming For Recurrent Autoregressive Models

no code implementations ICLR 2020 Najam Zaidi, Trevor Cohn, Gholamreza Haffari

Decoding in autoregressive models (ARMs) consists of searching for a high scoring output sequence under the trained model.

Text Infilling

Neural Speech Translation using Lattice Transformations and Graph Networks

no code implementations WS 2019 Daniel Beck, Trevor Cohn, Gholamreza Haffari

Speech translation systems usually follow a pipeline approach, using word lattices as an intermediate representation.

Translation

On the Role of Scene Graphs in Image Captioning

no code implementations WS 2019 Dalin Wang, Daniel Beck, Trevor Cohn

Scene graphs represent semantic information in images, which can help image captioning system to produce more descriptive outputs versus using only the image as context.

Descriptive Image Captioning

Deep Ordinal Regression for Pledge Specificity Prediction

1 code implementation IJCNLP 2019 Shivashankar Subramanian, Trevor Cohn, Timothy Baldwin

Many pledges are made in the course of an election campaign, forming important corpora for political analysis of campaign strategy and governmental accountability.

regression Specificity

Improving Chemical Named Entity Recognition in Patents with Contextualized Word Embeddings

1 code implementation WS 2019 Zenan Zhai, Dat Quoc Nguyen, Saber A. Akhondi, Camilo Thorne, Christian Druckenbrodt, Trevor Cohn, Michelle Gregory, Karin Verspoor

In this paper, we explore the NER performance of a BiLSTM-CRF model utilising pre-trained word embeddings, character-level word representations and contextualized ELMo word representations for chemical patents.

named-entity-recognition Named Entity Recognition +2

From Shakespeare to Li-Bai: Adapting a Sonnet Model to Chinese Poetry

no code implementations ALTA 2019 Zhuohan Xie, Jey Han Lau, Trevor Cohn

In this paper, we adapt Deep-speare, a joint neural network model for English sonnets, to Chinese poetry.

A Unified Neural Architecture for Instrumental Audio Tasks

1 code implementation1 Mar 2019 Steven Spratley, Daniel Beck, Trevor Cohn

Within Music Information Retrieval (MIR), prominent tasks -- including pitch-tracking, source-separation, super-resolution, and synthesis -- typically call for specialised methods, despite their similarities.

Information Retrieval Music Information Retrieval +3

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

no code implementations24 Feb 2019 Yuan Li, Benjamin I. P. Rubinstein, Trevor Cohn

As we show, datasets produced by crowd-sourcing are often not of this type: the data is highly redundantly annotated ($\ge 5$ annotations per instance), and the vast majority of workers produce high quality outputs.

Massively Multilingual Transfer for NER

1 code implementation ACL 2019 Afshin Rahimi, Yuan Li, Trevor Cohn

In cross-lingual transfer, NLP models over one or more source languages are applied to a low-resource target language.

Cross-Lingual Transfer Few-Shot Learning +4

Towards Efficient Machine Translation Evaluation by Modelling Annotators

no code implementations ALTA 2018 Nitika Mathur, Timothy Baldwin, Trevor Cohn

In this paper we show that the quality control mechanism is overly conservative, which increases the time and expense of the evaluation.

Machine Translation Translation

Twitter Geolocation using Knowledge-Based Methods

no code implementations WS 2018 Taro Miyazaki, Afshin Rahimi, Trevor Cohn, Timothy Baldwin

Automatic geolocation of microblog posts from their text content is particularly difficult because many location-indicative terms are rare terms, notably entity names such as locations, people or local organisations.

Entity Linking Graph Embedding +1

Evaluating the Utility of Hand-crafted Features in Sequence Labelling

1 code implementation EMNLP 2018 Minghao Wu, Fei Liu, Trevor Cohn

Conventional wisdom is that hand-crafted features are redundant for deep learning models, as they already learn adequate representations of text automatically from corpora.

named-entity-recognition Named Entity Recognition +2

Iterative Back-Translation for Neural Machine Translation

no code implementations WS 2018 Vu Cong Duy Hoang, Philipp Koehn, Gholamreza Haffari, Trevor Cohn

We present iterative back-translation, a method for generating increasingly better synthetic parallel data from monolingual data to train neural machine translation systems.

Machine Translation Translation

A Stochastic Decoder for Neural Machine Translation

1 code implementation ACL 2018 Philip Schulz, Wilker Aziz, Trevor Cohn

The process of translation is ambiguous, in that there are typically many valid trans- lations for a given sentence.

Machine Translation Sentence +3

Narrative Modeling with Memory Chains and Semantic Supervision

1 code implementation ACL 2018 Fei Liu, Trevor Cohn, Timothy Baldwin

Story comprehension requires a deep semantic understanding of the narrative, making it a challenging task.

Cloze Test Test

Towards Robust and Privacy-preserving Text Representations

3 code implementations ACL 2018 Yitong Li, Timothy Baldwin, Trevor Cohn

Written text often provides sufficient clues to identify the author, their gender, age, and other important attributes.

Privacy Preserving

What's in a Domain? Learning Domain-Robust Text Representations using Adversarial Training

1 code implementation NAACL 2018 Yitong Li, Timothy Baldwin, Trevor Cohn

Most real world language problems require learning from heterogenous corpora, raising the problem of learning robust models which generalise well to both similar (in domain) and dissimilar (out of domain) instances to those seen in training.

Domain Adaptation Language Identification +1

Recurrent Entity Networks with Delayed Memory Update for Targeted Aspect-based Sentiment Analysis

1 code implementation NAACL 2018 Fei Liu, Trevor Cohn, Timothy Baldwin

While neural networks have been shown to achieve impressive results for sentence-level sentiment analysis, targeted aspect-based sentiment analysis (TABSA) --- extraction of fine-grained opinion polarity w. r. t.

Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +2

Discourse-Aware Rumour Stance Classification in Social Media Using Sequential Classifiers

no code implementations6 Dec 2017 Arkaitz Zubiaga, Elena Kochkina, Maria Liakata, Rob Procter, Michal Lukasik, Kalina Bontcheva, Trevor Cohn, Isabelle Augenstein

We show that sequential classifiers that exploit the use of discourse properties in social media conversations while using only local features, outperform non-sequential classifiers.

General Classification Stance Classification

Capturing Long-range Contextual Dependencies with Memory-enhanced Conditional Random Fields

1 code implementation IJCNLP 2017 Fei Liu, Timothy Baldwin, Trevor Cohn

Despite successful applications across a broad range of NLP tasks, conditional random fields ("CRFs"), in particular the linear-chain variant, are only able to model local features.

BIBI System Description: Building with CNNs and Breaking with Deep Reinforcement Learning

no code implementations WS 2017 Yitong Li, Trevor Cohn, Timothy Baldwin

This paper describes our submission to the sentiment analysis sub-task of {``}Build It, Break It: The Language Edition (BIBI){''}, on both the builder and breaker sides.

Q-Learning reinforcement-learning +4

Continuous Representation of Location for Geolocation and Lexical Dialectology using Mixture Density Networks

1 code implementation EMNLP 2017 Afshin Rahimi, Timothy Baldwin, Trevor Cohn

We propose a method for embedding two-dimensional locations in a continuous vector space using a neural network-based model incorporating mixtures of Gaussian distributions, presenting two model variants for text-based geolocation and lexical dialectology.

regression

Learning how to Active Learn: A Deep Reinforcement Learning Approach

1 code implementation EMNLP 2017 Meng Fang, Yuan Li, Trevor Cohn

Active learning aims to select a small subset of data for annotation such that a classifier learned on the data is highly accurate.

Active Learning named-entity-recognition +4

Model Transfer for Tagging Low-resource Languages using a Bilingual Dictionary

1 code implementation ACL 2017 Meng Fang, Trevor Cohn

Cross-lingual model transfer is a compelling and popular method for predicting annotations in a low-resource language, whereby parallel corpora provide a bridge to a high-resource language and its associated annotated corpora.

Active Learning Cross-Lingual Word Embeddings +1

Topically Driven Neural Language Model

1 code implementation ACL 2017 Jey Han Lau, Timothy Baldwin, Trevor Cohn

Language models are typically applied at the sentence level, without access to the broader document context.

Language Modelling Sentence

A Neural Model for User Geolocation and Lexical Dialectology

no code implementations ACL 2017 Afshin Rahimi, Trevor Cohn, Timothy Baldwin

We propose a simple yet effective text- based user geolocation model based on a neural network with one hidden layer, which achieves state of the art performance over three Twitter benchmark geolocation datasets, in addition to producing word and phrase embeddings in the hidden layer that we show to be useful for detecting dialectal terms.

Robust Training under Linguistic Adversity

1 code implementation EACL 2017 Yitong Li, Trevor Cohn, Timothy Baldwin

Deep neural networks have achieved remarkable results across many language processing tasks, however they have been shown to be susceptible to overfitting and highly sensitive to noise, including adversarial attacks.

Sentiment Analysis Speech Recognition +1

Cross-Lingual Word Embeddings for Low-Resource Language Modeling

no code implementations EACL 2017 Oliver Adams, Adam Makarucha, Graham Neubig, Steven Bird, Trevor Cohn

We investigate the use of such lexicons to improve language models when textual training data is limited to as few as a thousand sentences.

Cross-Lingual Word Embeddings Language Modelling +3

Multilingual Training of Crosslingual Word Embeddings

no code implementations EACL 2017 Long Duong, Hiroshi Kanayama, Tengfei Ma, Steven Bird, Trevor Cohn

Crosslingual word embeddings represent lexical items from different languages using the same vector space, enabling crosslingual transfer.

Bilingual Lexicon Induction Dependency Parsing +6

DyNet: The Dynamic Neural Network Toolkit

4 code implementations15 Jan 2017 Graham Neubig, Chris Dyer, Yoav Goldberg, Austin Matthews, Waleed Ammar, Antonios Anastasopoulos, Miguel Ballesteros, David Chiang, Daniel Clothiaux, Trevor Cohn, Kevin Duh, Manaal Faruqui, Cynthia Gan, Dan Garrette, Yangfeng Ji, Lingpeng Kong, Adhiguna Kuncoro, Gaurav Kumar, Chaitanya Malaviya, Paul Michel, Yusuke Oda, Matthew Richardson, Naomi Saphra, Swabha Swayamdipta, Pengcheng Yin

In the static declaration strategy that is used in toolkits like Theano, CNTK, and TensorFlow, the user first defines a computation graph (a symbolic representation of the computation), and then examples are fed into an engine that executes this computation and computes its derivatives.

graph construction

Towards Decoding as Continuous Optimization in Neural Machine Translation

no code implementations11 Jan 2017 Cong Duy Vu Hoang, Gholamreza Haffari, Trevor Cohn

We propose a novel decoding approach for neural machine translation (NMT) based on continuous optimisation.

Machine Translation NMT +1

Succinct Data Structures for NLP-at-Scale

no code implementations COLING 2016 Matthias Petri, Trevor Cohn

Succinct data structures involve the use of novel data structures, compression technologies, and other mechanisms to allow data to be stored in extremely small memory or disk footprints, while still allowing for efficient access to the underlying data.

Information Retrieval Language Modelling +1

Learning Robust Representations of Text

1 code implementation EMNLP 2016 Yitong Li, Trevor Cohn, Timothy Baldwin

Deep neural networks have achieved remarkable results across many language processing tasks, however these methods are highly sensitive to noise and adversarial attacks.

Learning when to trust distant supervision: An application to low-resource POS tagging using cross-lingual projection

no code implementations CONLL 2016 Meng Fang, Trevor Cohn

Cross lingual projection of linguistic annotation suffers from many sources of bias and noise, leading to unreliable annotations that cannot be used directly.

POS POS Tagging

Exploring Prediction Uncertainty in Machine Translation Quality Estimation

no code implementations CONLL 2016 Daniel Beck, Lucia Specia, Trevor Cohn

Machine Translation Quality Estimation is a notoriously difficult task, which lessens its usefulness in real-world translation environments.

Machine Translation Translation

Word Representation Models for Morphologically Rich Languages in Neural Machine Translation

no code implementations WS 2017 Ekaterina Vylomova, Trevor Cohn, Xuanli He, Gholamreza Haffari

Dealing with the complex word forms in morphologically rich languages is an open problem in language processing, and is particularly important in translation.

Hard Attention Machine Translation +1

Document Context Language Models

1 code implementation12 Nov 2015 Yangfeng Ji, Trevor Cohn, Lingpeng Kong, Chris Dyer, Jacob Eisenstein

Text documents are structured on multiple levels of detail: individual words are related by syntax, but larger units of text are related by discourse structure.

Sentence

Take and Took, Gaggle and Goose, Book and Read: Evaluating the Utility of Vector Differences for Lexical Relation Learning

1 code implementation ACL 2016 Ekaterina Vylomova, Laura Rimell, Trevor Cohn, Timothy Baldwin

Recent work on word embeddings has shown that simple vector subtraction over pre-trained embeddings is surprisingly effective at capturing different lexical relations, despite lacking explicit supervision.

Clustering Relation +1

Depth-Gated LSTM

no code implementations16 Aug 2015 Kaisheng Yao, Trevor Cohn, Katerina Vylomova, Kevin Duh, Chris Dyer

This gate is a function of the lower layer memory cell, the input to and the past memory cell of this layer.

Language Modelling Machine Translation +1

Twitter User Geolocation Using a Unified Text and Network Prediction Model

no code implementations IJCNLP 2015 Afshin Rahimi, Trevor Cohn, Timothy Baldwin

We propose a label propagation approach to geolocation prediction based on Modified Adsorption, with two enhancements:(1) the removal of "celebrity" nodes to increase location homophily and boost tractability, and (2) he incorporation of text-based geolocation priors for test users.

Test

Exploiting Text and Network Context for Geolocation of Social Media Users

no code implementations HLT 2015 Afshin Rahimi, Duy Vu, Trevor Cohn, Timothy Baldwin

Research on automatically geolocating social media users has conventionally been based on the text content of posts from a given user or the social network of the user, with very little crossover between the two, and no bench-marking of the two approaches over compara- ble datasets.

Structured Prediction of Sequences and Trees using Infinite Contexts

no code implementations9 Mar 2015 Ehsan Shareghi, Gholamreza Haffari, Trevor Cohn, Ann Nicholson

Linguistic structures exhibit a rich array of global phenomena, however commonly used Markov models are unable to adequately describe these phenomena due to their strong locality assumptions.

Part-Of-Speech Tagging Structured Prediction

Bayesian Synchronous Grammar Induction

no code implementations NeurIPS 2008 Phil Blunsom, Trevor Cohn, Miles Osborne

We present a novel method for inducing synchronous context free grammars (SCFGs) from a corpus of parallel string pairs.

Machine Translation Translation

Cannot find the paper you are looking for? You can Submit a new open access paper.