Trevor Cohn

Trevor Cohn
University of Melbourne | MSD · Department of Computing and Information Systems

PhD

About

237
Publications
23,574
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
6,592
Citations
Citations since 2017
133 Research Items
4931 Citations
201720182019202020212022202302004006008001,000
201720182019202020212022202302004006008001,000
201720182019202020212022202302004006008001,000
201720182019202020212022202302004006008001,000
Additional affiliations
September 2009 - March 2014
The University of Sheffield
Position
  • Professor (Associate)

Publications

Publications (237)
Preprint
Full-text available
While pre-trained language models can generate individually fluent sentences for automatic story generation, they struggle to generate stories that are coherent, sensible and interesting. Current state-of-the-art (SOTA) story generation models explore using higher-level features such as plots or commonsense knowledge to improve the quality of gener...
Preprint
Open domain question answering (ODQA) is a longstanding task aimed at answering factual questions from a large knowledge corpus without any explicit evidence in natural language processing (NLP). Recent works have predominantly focused on improving the answering accuracy and achieved promising progress. However, higher accuracy often comes with mor...
Preprint
Mitigating bias in training on biased datasets is an important open problem. Several techniques have been proposed, however the typical evaluation regime is very limited, considering very narrow data conditions. For instance, the effect of target class imbalance and stereotyping is under-studied. To address this gap, we examine the performance of v...
Preprint
Full-text available
Negation is poorly captured by current language models, although the extent of this problem is not widely understood. We introduce a natural language inference (NLI) test suite to enable probing the capabilities of NLP methods, with the aim of understanding sub-clausal negation. The test suite contains premise--hypothesis pairs where the premise co...
Preprint
Full-text available
In this paper we report on our submission to the Multidocument Summarisation for Literature Review (MSLR) shared task. Specifically, we adapt PRIMERA (Xiao et al., 2022) to the biomedical domain by placing global attention on important biomedical entities in several ways. We analyse the outputs of the 23 resulting models, and report patterns in the...
Preprint
Full-text available
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. Recent work has shown that state-of-the-art NLP models underperform on samples containing negation in various tasks, and that negation detection models do not tran...
Preprint
Real-world datasets often encode stereotypes and societal biases. Such biases can be implicitly captured by trained models, leading to biased predictions and exacerbating existing societal preconceptions. Existing debiasing methods, such as adversarial training and removing protected information from representations, have been shown to reduce bias....
Preprint
This paper presents fairlib, an open-source framework for assessing and improving classification fairness. It provides a systematic framework for quickly reproducing existing baseline models, developing new methods, evaluating models with different metrics, and visualizing their results. Its modularity and extensibility enable the framework to be u...
Preprint
Adversarial training is a common approach for bias mitigation in natural language processing. Although most work on debiasing is motivated by equal opportunity, it is not explicitly captured in standard adversarial training. In this paper, we propose an augmented discriminator for adversarial training, which takes the target class as input to creat...
Preprint
Full-text available
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. The task focuses on the problem of matching eligible clinical trials to topics constituting a...
Chapter
The discovery of new chemical compounds is a key driver of the chemistry and pharmaceutical industries, and many other industrial sectors. Patents serve as a critical source of information about new chemical compounds. The ChEMU (Cheminformatics Elsevier Melbourne Universities) lab addresses information extraction over chemical patents and aims to...
Article
Full-text available
Chemical patents are a commonly used channel for disclosing novel compounds and reactions, and hence represent important resources for chemical and pharmaceutical research. Key chemical data in patents is often presented in tables. Both the number and the size of tables can be very large in patent documents. In addition, various types of informatio...
Preprint
Full-text available
GPT-2 has been frequently adapted in story generation models as it provides powerful generative capability. However, it still fails to generate consistent stories and lacks diversity. Current story generation models leverage additional information such as plots or commonsense into GPT-2 to guide the generation process. These approaches focus on imp...
Preprint
Most existing simultaneous machine translation (SiMT) systems are trained and evaluated on offline translation corpora. We argue that SiMT systems should be trained and tested on real interpretation data. To illustrate this argument, we propose an interpretation test set and conduct a realistic evaluation of SiMT trained on offline translations. Ou...
Preprint
Full-text available
Providing technologies to communities or domains where training data is scarce or protected e.g., for privacy reasons, is becoming increasingly important. To that end, we generalise methods for unsupervised transfer from multiple input models for structured prediction. We show that the means of aggregating over the input models is critical, and tha...
Preprint
Trained classification models can unintentionally lead to biased representations and predictions, which can reinforce societal preconceptions and stereotypes. Existing debiasing methods for classification models, such as adversarial training, are often expensive to train and difficult to optimise. In this paper, we propose a method for mitigating b...
Preprint
Full-text available
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. However there has traditionally been a disconnect between research on class-imbalanced learning and mitigating bias, and only recently have th...
Preprint
Full-text available
Bias is pervasive in NLP models, motivating the development of automatic debiasing techniques. Evaluation of NLP debiasing methods has largely been limited to binary attributes in isolation, e.g., debiasing with respect to binary gender or race, however many corpora involve multiple such attributes, possibly with higher cardinality. In this paper w...
Preprint
Humans use countless basic, shared facts about the world to efficiently navigate in their environment. This commonsense knowledge is rarely communicated explicitly, however, understanding how commonsense knowledge is represented in different paradigms is important for both deeper understanding of human cognition and for augmenting automatic reasoni...
Preprint
Bias in natural language processing arises primarily from models learning characteristics of the author such as gender and race when modelling tasks such as sentiment and syntactic parsing. This problem manifests as disparities in error rates across author demographics, typically disadvantaging minority groups. Existing methods for mitigating and m...
Preprint
Full-text available
Text generation from semantic graphs is traditionally performed with deterministic methods, which generate a unique description given an input graph. However, the generation problem admits a range of acceptable textual outputs, exhibiting lexical, syntactic and semantic variation. To address this disconnect, we present two main contributions. First...
Preprint
Full-text available
Mistranslated numbers have the potential to cause serious effects, such as financial loss or medical misinformation. In this work we develop comprehensive assessments of the robustness of neural machine translation systems to numerical text via behavioural testing. We explore a variety of numerical translation capabilities a system is expected to e...
Preprint
Full-text available
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. Specifically, we propose a poisoning attack in which a malicious adversary inserts a small poisoned sample of monolingual text into the training set of a system trained u...
Preprint
Full-text available
Understanding how news media frame political issues is important due to its impact on public attitudes, yet hard to automate. Computational approaches have largely focused on classifying the frame of a full news article while framing signals are often subtle and local. Furthermore, automatic news analysis is a sensitive domain, and existing classif...
Chapter
Chemical patents serve as an indispensable source of information about new discoveries of chemical compounds. The ChEMU (Cheminformatics Elsevier Melbourne University) lab addresses information extraction over chemical patents, and aims to advance the state of the art on this topic. ChEMU lab 2021, as part of the 12th Conference and Labs of the Eva...
Article
Full-text available
Chemical patents represent a valuable source of information about new chemical compounds, which is critical to the drug discovery process. Automated information extraction over chemical patents is, however, a challenging task due to the large volume of existing patents and the complex linguistic properties of chemical patents. The Cheminformatics E...
Preprint
Full-text available
Cross-lingual transfer is a leading technique for parsing low-resource languages in the absence of explicit supervision. Simple `direct transfer' of a learned model based on a multilingual input encoding has provided a strong benchmark. This paper presents a method for unsupervised cross-lingual transfer that improves over direct transfer systems b...
Preprint
Adversarial learning can learn fairer and less biased models of language than standard methods. However, current adversarial techniques only partially mitigate model bias, added to which their training procedures are often unstable. In this paper, we propose a novel approach to adversarial learning based on the use of multiple diverse discriminator...
Preprint
Full-text available
Chemical patents are a commonly used channel for disclosing novel compounds and reactions, and hence represent important resources for chemical and pharmaceutical research. Key chemical data in patents is often presented in tables. Both the number and the size of tables can be very large in patent documents. In addition, various types of informatio...
Preprint
Full-text available
Chemical patents are a commonly used channel for disclosing novel compounds and reactions, and hence represent important resources for chemical and pharmaceutical research. Key chemical data in patents is often presented in tables. Both the number and the size of tables can be very large in patent documents. In addition, various types of informatio...
Preprint
As modern neural machine translation (NMT) systems have been widely deployed, their security vulnerabilities require close scrutiny. Most recently, NMT systems have been shown to be vulnerable to targeted attacks which cause them to produce specific, unsolicited, and even harmful translations. These attacks are usually exploited in a white-box sett...
Chapter
In this paper, we provide an overview of the Cheminformatics Elsevier Melbourne University (ChEMU) evaluation lab 2020, part of the Conference and Labs of the Evaluation Forum 2020 (CLEF2020). The ChEMU evaluation lab focuses on information extraction over chemical reactions from patent texts. Using the ChEMU corpus of 1500 “snippets” (text segment...
Preprint
Automatic metrics are fundamental for the development and evaluation of machine translation systems. Judging whether, and to what extent, automatic metrics concur with the gold standard of human evaluation is not a straightforward problem. We show that current methods for judging metrics are highly sensitive to the translations used for assessment,...
Article
Deep-speare's creation is nonsensical when you read it closely, but it certainly "scans well," as an English teacher would say-its rhythm, rhyme scheme, and the basic grammar of its individual lines all seem fine at first glance. As our research team discovered when we showed our Al's poetry to the world, that's enough to fool quite a lot of people...
Chapter
We introduce a new evaluation lab named ChEMU (Cheminformatics Elsevier Melbourne University), part of the 11th Conference and Labs of the Evaluation Forum (CLEF-2020). ChEMU involves two key information extraction tasks over chemical reactions from patents. Task 1—Named entity recognition—involves identifying chemical compounds as well as their ty...
Preprint
In simultaneous machine translation, the system needs to incrementally generate the output translation before the input sentence ends. This is a coupled decision process consisting of a programmer and interpreter. The programmer's policy decides about when to WRITE the next output or READ the next input, and the interpreter's policy decides what wo...
Preprint
Grounding is crucial for natural language understanding. An important subtask is to understand modified color expressions, such as 'dirty blue'. We present a model of color modifiers that, compared with previous additive models in RGB space, learns more complex transformations. In addition, we present a model that operates in the HSV color space. W...
Preprint
Many pledges are made in the course of an election campaign, forming important corpora for political analysis of campaign strategy and governmental accountability. At present, there are no publicly available annotated datasets of pledges, and most political analyses rely on manual analysis. In this paper we collate a novel dataset of manifestos fro...
Preprint
Chemical patents are an important resource for chemical information. However, few chemical Named Entity Recognition (NER) systems have been evaluated on patent documents, due in part to their structural and linguistic complexity. In this paper, we explore the NER performance of a BiLSTM-CRF model utilising pre-trained word embeddings, character-lev...
Preprint
Supervised models of NLP rely on large collections of text which closely resemble the intended testing setting. Unfortunately matching text is often not available in sufficient quantity, and moreover, within any domain of text, data is often highly heterogenous. In this paper we propose a method to distill the important domain signal as part of a m...
Preprint
We study pragmatics in political campaign text, through analysis of speech acts and the target of each utterance. We propose a new annotation schema incorporating domain-specific speech acts, such as commissive-action, and present a novel annotated corpus of media releases and speech transcripts from the 2016 Australian election cycle. We show how...
Conference Paper
Crowd-sourcing is a cheap and popular means of creating training and evaluation datasets for machine learning, however it poses the problem of 'truth inference', as individual workers cannot be wholly trusted to provide reliable annotations. Research into models of annotation aggregation attempts to infer a latent 'true' annotation, which has been...
Preprint
Full-text available
Critical to natural language generation is the production of correctly inflected text. In this paper, we isolate the task of predicting a fully inflected sentence from its partially lemmatized version. Unlike traditional morphological inflection or surface realization, our task input does not provide ``gold'' tags that specify what morphological fe...
Preprint
Within Music Information Retrieval (MIR), prominent tasks -- including pitch-tracking, source-separation, super-resolution, and synthesis -- typically call for specialised methods, despite their similarities. Conditional Generative Adversarial Networks (cGANs) have been shown to be highly versatile in learning general image-to-image translations, b...
Preprint
Crowd-sourcing is a cheap and popular means of creating training and evaluation datasets for machine learning, however it poses the problem of `truth inference', as individual workers cannot be wholly trusted to provide reliable annotations. Research into models of annotation aggregation attempts to infer a latent `true' annotation, which has been...
Preprint
In massively multilingual transfer NLP models over many source languages are applied to a low-resource target language. In contrast to most prior work, which use a single model or a small handful, we consider many such models, which raises the critical problem of poor transfer, particularly from distant languages. We propose two techniques for modu...
Article
Full-text available
Automatic speech recognition tools have potential for facilitating language documentation, but in practice these tools remain little-used by linguists for a variety of reasons, such as that the technology is still new (and evolving rapidly), user-friendly interfaces are still under development, and case studies demonstrating the practical usefulnes...
Preprint
Conventional wisdom is that hand-crafted features are redundant for deep learning models, as they already learn adequate representations of text automatically from corpora. In this work, we test this claim by proposing a new method for exploiting handcrafted features as part of a novel hybrid learning approach, incorporating a feature auto-encoder...
Preprint
In this paper, we propose a joint architecture that captures language, rhyme and meter for sonnet modelling. We assess the quality of generated poems using crowd and expert judgements. The stress and rhyme models perform very well, as generated poems are largely indistinguishable from human-written poems. Expert evaluation, however, reveals that a...
Preprint
Many NLP applications can be framed as a graph-to-sequence learning problem. Previous work proposing neural architectures on this setting obtained promising results compared to grammar-based approaches but still rely on linearisation heuristics and/or standard recurrent networks to achieve the best performance. In this work, we propose a new model...
Preprint
The process of translation is ambiguous, in that there are typically many valid trans- lations for a given sentence. This gives rise to significant variation in parallel cor- pora, however, most current models of machine translation do not account for this variation, instead treating the prob- lem as a deterministic process. To this end, we present...
Preprint
Story comprehension requires a deep semantic understanding of the narrative, making it a challenging task. Inspired by previous studies on ROC Story Cloze Test, we propose a novel method, tracking various semantic aspects with external neural memory chains while encouraging each to focus on a particular semantic aspect. Evaluated on the task of sto...
Preprint
Full-text available
Online petitions are a cost-effective way for citizens to collectively engage with policy-makers in a democracy. Predicting the popularity of a petition --- commonly measured by its signature count --- based on its textual content has utility for policy-makers as well as those posting the petition. In this work, we model this task using CNN regress...
Preprint
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. This requires learning an underlying task, while not learning irrelevant signals and biases specific to indi...
Preprint
Written text often provides sufficient clues to identify the author, their gender, age, and other important attributes. Consequently, the authorship of training and evaluation corpora can have unforeseen impacts, including differing model performance for different user groups, as well as privacy implications. In this paper, we propose an approach t...
Preprint
Full-text available
Election manifestos document the intentions, motives, and views of political parties. They are often used for analysing a party's fine-grained position on a particular issue, as well as for coarse-grained positioning of a party on the left--right spectrum. In this paper we propose a two-stage model for automatically performing both levels of analys...
Preprint
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. a pre-defined set of aspects --- remains a difficult task. Motivated by recent advances in memory-augmented models for machine reading, we...
Article
Full-text available
Social media user geolocation is vital to many applications such as event detection. In this paper, we propose GCN, a multiview geolocation model based on Graph Con- volutional Networks, that uses both text and network context. We compare GCN to the state-of-the-art, and to two base- lines we propose, and show that our model achieves or is competit...
Article
Full-text available
Background: Relation extraction from biomedical publications is an important task in the area of semantic mining of text. Kernel methods for supervised relation extraction are often preferred over manual feature engineering methods, when classifying highly ordered structures such as trees and graphs obtained from syntactic parsing of a sentence. T...