Search Results for author: Maria Liakata

Found 73 papers, 17 papers with code

Automatic Identification of Ruptures in Transcribed Psychotherapy Sessions

no code implementations NAACL (CLPsych) 2021 Adam Tsakalidis, Dana Atzil-Slonim, Asaf Polakovski, Natalie Shapira, Rivka Tuval-Mashiach, Maria Liakata

We present the first work on automatically capturing alliance rupture in transcribed therapy sessions, trained on the text and self-reported rupture scores from both therapists and clients.

Overview of the CLPsych 2022 Shared Task: Capturing Moments of Change in Longitudinal User Posts

no code implementations NAACL (CLPsych) 2022 Adam Tsakalidis, Jenny Chim, Iman Munire Bilal, Ayah Zirikly, Dana Atzil-Slonim, Federico Nanni, Philip Resnik, Manas Gaur, Kaushik Roy, Becky Inkster, Jeff Leintz, Maria Liakata

We provide an overview of the CLPsych 2022 Shared Task, which focusses on the automatic identification of ‘Moments of Change’ in lon- gitudinal posts by individuals on social media and its connection with information regarding mental health .

TempoFormer: A Transformer for Temporally-aware Representations in Change Detection

no code implementations28 Aug 2024 Talia Tseriotou, Adam Tsakalidis, Maria Liakata

Dynamic representation learning plays a pivotal role in understanding the evolution of linguistic content over time.

Change Detection Representation Learning

Assessing the Reasoning Abilities of ChatGPT in the Context of Claim Verification

no code implementations16 Feb 2024 John Dougrez-Lewis, Mahmud Elahi Akhter, Yulan He, Maria Liakata

Our study contributes to the growing body of research suggesting that ChatGPT's reasoning processes are unlikely to mirror human-like reasoning, and that LLMs need to be more rigorously evaluated to distinguish between hype and actual capabilities, especially in high-stakes real-world tasks such as claim verification.

Claim Verification Logical Reasoning +1

Combining Hierachical VAEs with LLMs for clinically meaningful timeline summarisation in social media

no code implementations29 Jan 2024 Jiayu Song, Jenny Chim, Adam Tsakalidis, Julia Ive, Dana Atzil-Slonim, Maria Liakata

We introduce a hybrid abstractive summarisation approach combining hierarchical VAE with LLMs (LlaMA-2) to produce clinically meaningful summaries from social media user timelines, appropriate for mental health monitoring.

Generating Zero-shot Abstractive Explanations for Rumour Verification

1 code implementation23 Jan 2024 Iman Munire Bilal, Preslav Nakov, Rob Procter, Maria Liakata

The task of rumour verification in social media concerns assessing the veracity of a claim on the basis of conversation threads that result from it.

Few-Shot Learning Informativeness +2

Sig-Networks Toolkit: Signature Networks for Longitudinal Language Modelling

2 code implementations6 Dec 2023 Talia Tseriotou, Ryan Sze-Yin Chan, Adam Tsakalidis, Iman Munire Bilal, Elena Kochkina, Terry Lyons, Maria Liakata

We present an open-source, pip installable toolkit, Sig-Networks, the first of its kind for longitudinal language modelling.

Language Modelling

Reformulating NLP tasks to Capture Longitudinal Manifestation of Language Disorders in People with Dementia

no code implementations15 Oct 2023 Dimitris Gkoumas, Matthew Purver, Maria Liakata

Here, we automatically learn linguistic disorder patterns by making use of a moderately-sized pre-trained language model and forcing it to focus on reformulated natural language processing (NLP) tasks and associated linguistic patterns.

Language Modelling

A Digital Language Coherence Marker for Monitoring Dementia

no code implementations14 Oct 2023 Dimitris Gkoumas, Adam Tsakalidis, Maria Liakata

The use of spontaneous language to derive appropriate digital markers has become an emergent, promising and non-intrusive method to diagnose and monitor dementia.

Automated clinical coding using off-the-shelf large language models

no code implementations10 Oct 2023 Joseph S. Boyle, Antanas Kascenas, Pat Lok, Maria Liakata, Alison Q. O'Neil

The task of assigning diagnostic ICD codes to patient hospital admissions is typically performed by expert human coders.

Unsupervised Pre-training

Creation and evaluation of timelines for longitudinal user posts

1 code implementation10 Mar 2023 Anthony Hills, Adam Tsakalidis, Federico Nanni, Ioannis Zachos, Maria Liakata

There is increasing interest to work with user generated content in social media, especially textual posts over time.

PANACEA: An Automated Misinformation Detection System on COVID-19

no code implementations28 Feb 2023 Runcong Zhao, Miguel Arana-Catania, Lixing Zhu, Elena Kochkina, Lin Gui, Arkaitz Zubiaga, Rob Procter, Maria Liakata, Yulan He

In this demo, we introduce a web-based misinformation detection system PANACEA on COVID-19 related claims, which has two modules, fact-checking and rumour detection.

Fact Checking Misinformation +2

A Pipeline for Generating, Annotating and Employing Synthetic Data for Real World Question Answering

1 code implementation30 Nov 2022 Matthew Maufe, James Ravenscroft, Rob Procter, Maria Liakata

Question Answering (QA) is a growing area of research, often used to facilitate the extraction of information from within documents.

Question Answering

Unsupervised Opinion Summarisation in the Wasserstein Space

no code implementations27 Nov 2022 Jiayu Song, Iman Munire Bilal, Adam Tsakalidis, Rob Procter, Maria Liakata

A Variational Autoencoder is used to get the distribution of documents/posts, and the distributions are disentangled into separate semantic and syntactic spaces.

Abstractive Text Summarization Decoder

Template-based Abstractive Microblog Opinion Summarisation

no code implementations8 Aug 2022 Iman Munire Bilal, Bo wang, Adam Tsakalidis, Dong Nguyen, Rob Procter, Maria Liakata

We introduce the task of microblog opinion summarisation (MOS) and share a dataset of 3100 gold-standard opinion summaries to facilitate research in this domain.

Personalised recommendations of sleep behaviour with neural networks using sleep diaries captured in Sleepio

no code implementations29 Jul 2022 Alejo Nevado-Holgado, Colin Espie, Maria Liakata, Alasdair Henry, Jenny Gu, Niall Taylor, Kate Saunders, Tom Walker, Chris Miller

In collaboration with Big Health, the therapeutics company that created and utilizes Sleepio, we have analysed data from a random sample of 401, 174 sleep diaries and built a neural network to model sleep behaviour and sleep quality of each individual in a personalised manner.

Sleep Quality

Identifying Moments of Change from Longitudinal User Text

no code implementations ACL 2022 Adam Tsakalidis, Federico Nanni, Anthony Hills, Jenny Chim, Jiayu Song, Maria Liakata

Identifying changes in individuals' behaviour and mood, as observed via content shared on online platforms, is increasingly gaining importance.

A Longitudinal Multi-modal Dataset for Dementia Monitoring and Diagnosis

no code implementations3 Sep 2021 Dimitris Gkoumas, Bo wang, Adam Tsakalidis, Maria Wolters, Arkaitz Zubiaga, Matthew Purver, Maria Liakata

The corpus consists of spoken conversations, a subset of which are transcribed, as well as typed and written thoughts and associated extra-linguistic information such as pen strokes and keystrokes.

Evaluation of Thematic Coherence in Microblogs

no code implementations ACL 2021 Iman Munire Bilal, Bo wang, Maria Liakata, Rob Procter, Adam Tsakalidis

Here we create a corpus of microblog clusters from three different domains and time windows and define the task of evaluating thematic coherence.

Text Generation

CD\^2CR: Co-reference resolution across documents and domains

no code implementations EACL 2021 James Ravenscroft, Amanda Clare, Arie Cattan, Ido Dagan, Maria Liakata

Cross-document co-reference resolution (CDCR) is the task of identifying and linking mentions to entities and concepts across many text documents.

Citizen Participation and Machine Learning for a Better Democracy

no code implementations28 Feb 2021 M. Arana-Catania, F. A. Van Lier, Rob Procter, Nataliya Tkachenko, Yulan He, Arkaitz Zubiaga, Maria Liakata

The development of democratic systems is a crucial task as confirmed by its selection as one of the Millennium Sustainable Development Goals by the United Nations.

BIG-bench Machine Learning Decision Making

Modelling Paralinguistic Properties in Conversational Speech to Detect Bipolar Disorder and Borderline Personality Disorder

no code implementations18 Feb 2021 Bo wang, Yue Wu, Nemanja Vaci, Maria Liakata, Terry Lyons, Kate E A Saunders

Bipolar disorder (BD) and borderline personality disorder (BPD) are two chronic mental health conditions that clinicians find challenging to distinguish based on clinical interviews, due to their overlapping symptoms.

Boosting Low-Resource Biomedical QA via Entity-Aware Masking Strategies

no code implementations EACL 2021 Gabriele Pergola, Elena Kochkina, Lin Gui, Maria Liakata, Yulan He

Biomedical question-answering (QA) has gained increased attention for its capability to provide users with high-quality information from a vast scientific literature.

Domain Adaptation Question Answering +1

CD2CR: Co-reference Resolution Across Documents and Domains

1 code implementation29 Jan 2021 James Ravenscroft, Arie Cattan, Amanda Clare, Ido Dagan, Maria Liakata

Cross-document co-reference resolution (CDCR) is the task of identifying and linking mentions to entities and concepts across many text documents.

Measuring prominence of scientific work in online news as a proxy for impact

no code implementations28 Jul 2020 James Ravenscroft, Amanda Clare, Maria Liakata

We find that Impact Case studies submitted to the UK Research Excellence Framework (REF) 2014 that refer to scientific papers mentioned in newspaper articles were awarded a higher score in the REF assessment.

Semantic Similarity Semantic Textual Similarity

Better Early than Late: Fusing Topics with Word Embeddings for Neural Question Paraphrase Identification

no code implementations22 Jul 2020 Nicole Peinelt, Dong Nguyen, Maria Liakata

Question paraphrase identification is a key task in Community Question Answering (CQA) to determine if an incoming question has been previously asked.

Community Question Answering Paraphrase Identification +2

Estimating predictive uncertainty for rumour verification models

1 code implementation ACL 2020 Elena Kochkina, Maria Liakata

The inability to correctly resolve rumours circulating online can have harmful real-world consequences.

Rumour Detection

Autoencoding Word Representations through Time for Semantic Change Detection

no code implementations28 Apr 2020 Adam Tsakalidis, Maria Liakata

Semantic change detection concerns the task of identifying words whose meaning has changed over time.

Change Detection

Aiming beyond the Obvious: Identifying Non-Obvious Cases in Semantic Similarity Datasets

1 code implementation ACL 2019 Nicole Peinelt, Maria Liakata, Dong Nguyen

Existing datasets for scoring text pairs in terms of semantic similarity contain instances whose resolution differs according to the degree of difficulty.

Semantic Similarity Semantic Textual Similarity

Nowcasting the Stance of Social Media Users in a Sudden Vote: The Case of the Greek Referendum

no code implementations26 Aug 2018 Adam Tsakalidis, Nikolaos Aletras, Alexandra I. Cristea, Maria Liakata

Modelling user voting intention in social media is an important research area, with applications in analysing electorate behaviour, online political campaigning and advertising.

Can We Assess Mental Health through Social Media and Smart Devices? Addressing Bias in Methodology and Evaluation

no code implementations19 Jul 2018 Adam Tsakalidis, Maria Liakata, Theo Damoulas, Alexandra I. Cristea

Predicting mental health from smartphone and social media data on a longitudinal basis has recently attracted great interest, with very promising results being reported across many studies.

HarriGT: A Tool for Linking News to Science

no code implementations ACL 2018 James Ravenscroft, Am Clare, a, Maria Liakata

Being able to reliably link scientific works to the newspaper articles that discuss them could provide a breakthrough in the way we rationalise and measure the impact of science on our society.

Document Classification Entity Extraction using GAN +2

All-in-one: Multi-task Learning for Rumour Verification

no code implementations COLING 2018 Elena Kochkina, Maria Liakata, Arkaitz Zubiaga

We propose a multi-task learning approach that allows joint training of the main and auxiliary tasks, improving the performance of rumour verification.

General Classification Multi-Task Learning +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

ClassifierGuesser: A Context-based Classifier Prediction System for Chinese Language Learners

1 code implementation IJCNLP 2017 Nicole Peinelt, Maria Liakata, Shu-Kai Hsieh

Classifiers are function words that are used to express quantities in Chinese and are especially difficult for language learners.

BIG-bench Machine Learning

Incongruent Headlines: Yet Another Way to Mislead Your Readers

no code implementations WS 2017 Sophie Chesney, Maria Liakata, Massimo Poesio, Matthew Purver

This paper discusses the problem of incongruent headlines: those which do not accurately represent the information contained in the article with which they occur.

Turing at SemEval-2017 Task 8: Sequential Approach to Rumour Stance Classification with Branch-LSTM

1 code implementation SEMEVAL 2017 Elena Kochkina, Maria Liakata, Isabelle Augenstein

This paper describes team Turing's submission to SemEval 2017 RumourEval: Determining rumour veracity and support for rumours (SemEval 2017 Task 8, Subtask A).

General Classification Rumour Detection +2

Detection and Resolution of Rumours in Social Media: A Survey

no code implementations3 Apr 2017 Arkaitz Zubiaga, Ahmet Aker, Kalina Bontcheva, Maria Liakata, Rob Procter

Despite the increasing use of social media platforms for information and news gathering, its unmoderated nature often leads to the emergence and spread of rumours, i. e. pieces of information that are unverified at the time of posting.

Classification General Classification +4

TDParse: Multi-target-specific sentiment recognition on Twitter

no code implementations EACL 2017 Bo Wang, Maria Liakata, Arkaitz Zubiaga, Rob Procter

Existing target-specific sentiment recognition methods consider only a single target per tweet, and have been shown to miss nearly half of the actual targets mentioned.

Dependency Parsing Opinion Mining +1

Political Homophily in Independence Movements: Analysing and Classifying Social Media Users by National Identity

no code implementations27 Feb 2017 Arkaitz Zubiaga, Bo wang, Maria Liakata, Rob Procter

Independence movements occur in territories whose citizens have conflicting national identities; users with opposing national identities will then support or oppose the sense of being part of an independent nation that differs from the officially recognised country.

General Classification

Combining Heterogeneous User Generated Data to Sense Well-being

no code implementations COLING 2016 Adam Tsakalidis, Maria Liakata, Theo Damoulas, Brigitte Jellinek, Weisi Guo, Alex Cristea, ra

In this paper we address a new problem of predicting affect and well-being scales in a real-world setting of heterogeneous, longitudinal and non-synchronous textual as well as non-linguistic data that can be harvested from on-line media and mobile phones.

Emotion Recognition

Learning Reporting Dynamics during Breaking News for Rumour Detection in Social Media

2 code implementations24 Oct 2016 Arkaitz Zubiaga, Maria Liakata, Rob Procter

In this paper we introduce a novel approach to rumour detection that learns from the sequential dynamics of reporting during breaking news in social media to detect rumours in new stories.

Rumour Detection

Stance Classification in Rumours as a Sequential Task Exploiting the Tree Structure of Social Media Conversations

no code implementations COLING 2016 Arkaitz Zubiaga, Elena Kochkina, Maria Liakata, Rob Procter, Michal Lukasik

Rumour stance classification, the task that determines if each tweet in a collection discussing a rumour is supporting, denying, questioning or simply commenting on the rumour, has been attracting substantial interest.

General Classification Rumour Detection +1

Multi-label Annotation in Scientific Articles - The Multi-label Cancer Risk Assessment Corpus

no code implementations LREC 2016 James Ravenscroft, Anika Oellrich, Shyamasree Saha, Maria Liakata

Here, we present the Multi-CoreSC CRA corpus, a text corpus specific to the domain of cancer risk assessment (CRA), consisting of 50 full text papers, each of which contains sentences annotated with one or more CoreSCs.

Sentence

Towards Real-Time, Country-Level Location Classification of Worldwide Tweets

1 code implementation25 Apr 2016 Arkaitz Zubiaga, Alex Voss, Rob Procter, Maria Liakata, Bo wang, Adam Tsakalidis

In contrast to much previous work that has focused on location classification of tweets restricted to a specific country, here we undertake the task in a broader context by classifying global tweets at the country level, which is so far unexplored in a real-time scenario.

Classification General Classification

Leveraging Textual Features for Best Answer Prediction in Community-based Question Answering

no code implementations9 Jun 2015 George Gkotsis, Maria Liakata, Carlos Pedrinaci, John Domingue

In particular, we present a system, ACQUA [http://acqua. kmi. open. ac. uk], that can be installed onto the majority of browsers as a plugin.

Question Answering

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