A selection of our publications – see personal pages for more:
|Rabab Alkhalifa, Elena Kochkina and Arkaitz Zubiaga. Opinions are Made to be Changed: Temporally Adaptive Stance Classification Proceedings of ACM Hypertext workshop on OASIS, 2021|
|Aiqi Jiang and Arkaitz Zubiaga. Cross-lingual Capsule Network for Hate Speech Detection in Social Media Proceedings of ACM Hypertext, 2021|
|Peiling Yi and Arkaitz Zubiaga. Weakly Supervised Cross-platform Teenager Detection with Adversarial BERT Proceedings of ACM Hypertext, 2021|
|Aiqi Jiang and Arkaitz Zubiaga. QMUL-SDS at EXIST: Leveraging Pre-trained Semantics and Lexical Features for Multilingual Sexism Detection in Social Networks Proceedings of IberLEF, 2021|
|Wenjie Yin and Arkaitz Zubiaga. Towards generalisable hate speech detection: a review on obstacles and solutions PeerJ Computer Science, 2021|
|Amani Abumansour and Arkaitz Zubiaga. QMUL-SDS at CheckThat! 2021: Enriching Pre-Trained Language Models for the Estimation of Check-Worthiness of Arabic Tweets Proceedings of CLEF, 2021|
|Yujian Gan, Xinyun Chen, Qiuping Huang, Matthew Purver, John Woodward, Jinxia Xie and Pengsheng Huang.
Towards Robustness of Text-to-SQL Models against Synonym Substitution. ACL-IJCNLP, to appear.
|Andraž Pelicon, Ravi Shekhar, Blaž Škrlj, Matthew Purver and Senja Pollak.
Investigating Cross-Lingual Training for Offensive Language Detection. PeerJ Computer Science, 7:e559, 2021.
|Shamila Nasreen, Morteza Rohanian, Matthew Purver and Julian Hough.
Alzheimer’s Dementia Recognition from Spontaneous Speech using Disfluency and Interactional Features. Frontiers in Computer Science 3:49, 2021.
|Matthew Purver, Mehrnoosh Sadrzadeh, Gijs Wijnholds, Ruth Kempson and Julian Hough.
Incremental Composition in Distributional Semantics. Journal of Logic, Language and Information 10.1007/s10849-021-09337-8, 2021.
|Xia Zeng and Arkaitz Zubiaga. QMUL-SDS at SCIVER: Step-by-Step Binary Classification for Scientific Claim Verification. NAACL Workshop on Scholarly Document Processing, June 2021.|
|Lev Konstantinovskiy, Oliver Price, Mevan Babakar and Arkaitz Zubiaga. Towards Automated Factchecking: Developing an Annotation Schema and Benchmark for Consistent Automated Claim Detection. ACM DTRAP, 2021.|
|Leon Fröhling and Arkaitz Zubiaga.
Feature-based detection of automated language models: tackling GPT-2, GPT-3 and Grover. PeerJ Computer Science Vol 29, 2021.
|Diogo Cortiz and Arkaitz Zubiaga.
Ethical and Technical Challenges of AI in Tackling Hate Speech. International Review of Information Ethics 7:e443, 2021.
|Neeraj Vashistha and Arkaitz Zubiaga.
Online Multilingual Hate Speech Detection: Experimenting with Hindi and English Social Media. Information, 12(1), 5, 2021.
|Andraž Pelicon, Ravi Shekhar, Matej Martinc, Blaž Škrlj, Matthew Purver and Senja Pollak.
Zero-shot Cross-lingual Content Filtering: Offensive Language and Hate Speech Detection. EACL workshop on News Media Content Analysis and Automated Report Generation, Kyiv, April 2021.
|Carlos Armendariz, Matthew Purver, Senja Pollak, Nikola Ljubešić, Matej Ulčar, Ivan Vulić and Mohammad Taher Pilehvar.
SemEval2020 Task3: Graded Word Similarity in Context. Proceedings of SemEval, Barcelona, December 2020.
|Tom Tabak and Matthew Purver.
Temporal Mental Health Dynamics on Social Media. Proc. NLP COVID-19 workshop at EMNLP, November 2020.
|Morteza Rohanian, Julian Hough and Matthew Purver.
Multi-modal Fusion with Gating using Audio, Lexical and Disfluency Features for Alzheimer’s Dementia Recognition from Spontaneous Speech. Proceedings of Interspeech, Shanghai, October 2020.
|George Wright and Matthew Purver.
Creative Language Generation in a Society of Engagement and Reflection. Proceedings of ICCC, Coimbra, Portugal, September 2020.
|Shital Lathiya, J S Dhobi, Arkaitz Zubiaga, Maria Liakata and Rob Procter. Birds of a Feather Check Together: Leveraging Homophily for Sequential Rumour Detection. Online Social Networks and Media, 2020.|
|Rabab Alkhalifa, Theodore Yoong, Elena Kochkina, Arkaitz Zubiaga and Maria Liakata. QMUL-SDS at CheckThat! 2020: Determining COVID-19 Tweet Check-Worthiness Using an Enhanced CT-BERT with Numeric Expressions. Proceedings of CLEF, 2020.|
|Arkaitz Zubiaga and Aiqi Jiang. Early Detection of Social Media Hoaxes at Scale. ACM TWEB, 2020.|
|Arkaitz Zubiaga. Exploiting Class Labels to Boost Performance on Embedding-based Text Classification. Proceedings of CIKM, 2020.|
|Xiaoyu Guo, Jing Ma and Arkaitz Zubiaga. NUAA-QMUL at SemEval 2020 Task 8: Utilizing BERT and DenseNet for Internet Meme Emotion Analysis. Proceedings of SemEval, 2020.|
|Jey Han Lau, Carlos S. Armendariz, Shalom Lappin, Matthew Purver and Chang Shu. How Furiously Can Colourless Green Ideas Sleep? Sentence Acceptability in Context. Transactions of the ACL 8: 296-310, June 2020.|
|Ravi Shekhar, Matthew Purver, Marko Pranjić, Senja Pollak and Andraž Pelicon. Automating Comment Moderation for News Articles in Less-Resourced Languages. Journal for Language Technology and Computational Linguistics (JLCL) 34: 1, 2020.|
|Jorge Del-Bosque-Trevino, Julian Hough and Matthew Purver. Investigating the Semantic Wave in Tutorial Dialogues: An Annotation Scheme and Corpus Study on Analogy Components. To appear in SemDial, Waltham MA, July 2020.|
|Carlos S. Armendariz, Matthew Purver, Matej Ulčar, Senja Pollak, Nikola Ljubešić, Marko Robnik-Šikonja, Mark Granroth-Wilding, Kristiina Vaik. CoSimLex: A Resource for Evaluating Graded Word Similarity in Context. To appear at LREC, Marseille, May 2020.|
|Aiqi Jiang, Arkaitz Zubiaga. Leveraging aspect phrase embeddings for cross-domain review rating prediction. PeerJ Computer Science, October 2019.|
|Arkaitz Zubiaga. Mining social media for newsgathering: A review. Online Social Networks and Media, September 2019.|
|Morteza Rohanian, Julian Hough and Matthew Purver. Detecting Depression with Word-Level Multimodal Fusion. Proceedings of Interspeech, September 2019.|
|Shamila Nasreen, Matthew Purver and Julian Hough. A Corpus Study on Questions, Responses and Misunderstanding Signals in Conversations with Alzheimer’s Patients. Proceedings of SemDial, September 2019.||bib|
|Genevieve Gorrell, Elena Kochkina, Maria Liakata, Ahmet Aker, Arkaitz Zubiaga, Kalina Bontcheva and Leon Derczynski. RumourEval 2019: Determining Rumour Veracity and Support for Rumours. Proceedings of SemEval, June 2019.|
|Massimo Poesio, Jon Chamberlain, Silviu Paun, Juntao Yu, Alexandra Uma and Udo Kruschwitz. A Crowdsourced Corpus of Multiple Judgments and Disagreement on Anaphoric Interpretation. Proceedings of NAACL-HLT, June 2019.|
|Gijs Wijnholds, Mehrnoosh Sadrzadeh. Evaluating Composition Models for Verb Phrase Elliptical Sentence Embeddings. Proceedings of NAACL-HLT, June 2019.|
|Stephen McGregor, Kat Agres, Karolina Rataj, Matthew Purver and Geraint Wiggins. Re-Representing Metaphor: Modelling Metaphor Perception Using Dynamically Contextual Distributional Semantics. Frontiers in Psychology 10:765, 2019.||bib|
|Andrew McParland, Chris Newell, Mehrnoosh Sadrzadeh. Improving entity disambiguation with a vector space semantic tagger. QMUL Technical Report, ISBN 2043-0167, Series EECSRR–18-01.|
|Mehrnoosh Sadrzadeh, Matthew Purver, Julian Hough, Ruth Kempson. Exploring Semantic Incrementality with Dynamic Syntax and Vector Space Semantics. Proceedings of SemDial 2018, and on arXiv https://arxiv.org/abs/1811.00614.||bib|
|Reinhard Muskens and Mehrnoosh Sadrzadeh. Static and Dynamic Vector Semantics for Lambda Calculus Models of Natural Language. Accepted for publication in JLM in September 2018 and on arXiv https://arxiv.org/abs/1810.11351.|
|Gijs Wijnholds and Mehrnoosh Sadrzadeh. Classical Copying versus Quantum Entanglement in Natural Language: The Case of VP-ellipsis. Proceedings CAPNS 2018, and on arXiv https://arxiv.org/abs/1811.03276|
|Mehrnoosh Sadrzadeh, Dimitri Kartsaklis, Esma Balkir. Sentence entailment in compositional distributional semantics. Annals of Mathematics and Artificial Intelligence, April 2018, Volume 82, Issue 4, pp 189–218, and on arXiv https://arxiv.org/abs/1512.04419.|
|Dimitri Kartsaklis, Mehrnoosh Sadrzadeh, Sanjaye Ramgoolam. Linguistic Matrix Theory. Accepted for publication in Annals of Institute Henri Poincare, March 2018, and on arXiv https://arxiv.org/abs/1703.10252.|
|Matthew Purver, Julian Hough and Christine Howes. Computational Models of Miscommunication Phenomena. Topics in Cognitive Science 10(2): 425-451, 2018.||bib|
|Matthew Purver, Aljoša Valentinčič, Marko Pahor and Senja Pollak. Diachronic Lexical Changes In Company Reports: An Initial Investigation. To appear in the 1st Financial Narrative Processing Workshop at LREC, 2018.||bib|
|Maximilian Droog-Hayes, Geraint Wiggins and Matthew Purver. Automatic Detection of Narrative Structure for High-Level Story Representation. To appear in the 5th AISB Symposium on Computational Creativity, 2018.|
|Claire Kelleher, Sherif Clinch and Matthew Purver. Analysing Dialogue to Support Detection of Alzheimer’s Disease. In the 2nd Human Brain Project Student Conference, Ljubljana, 2018.|
|Stephen McGregor, Elisabetta Jezek, Matthew Purver and Geraint Wiggins. A Geometric Method for Detecting Semantic Coercion. In the 12th International Conference on Computational Semantics (IWCS), Montpellier, September 2017.||bib|
|Sophie Chesney, Maria Liakata, Massimo Poesio and Matthew Purver. Incongruent Headlines: Yet Another Way to Mislead Your Readers. In the EMNLP 2017 workshop Natural Language Processing Meets Journalism (NLPJ), Copenhagen, September 2017.||bib|
|Eleni Gregoromichelaki, Chris Howes, Matthew Purver, Ruth Kempson, Arash Eshghi, Ronnie Cann, Patrick Healey and Gregory Mills. Completability vs (In)completeness. In the BICLCE 2017 workshop Approaches to Fragments and Ellipsis in Spoken and Written English, Vigo, September 2017.||bib|
|Mehrnoosh Sadrzadeh. Quantization, Frobenius and Bi Algebras from the Categorical Framework of Quantum Mechanics to Natural Language Semantics. Frontiers in Physics Volume 5, Pages 18, July 2017, https://doi.org/10.3389/fphy.2017.00018.|
|Benjamin Blundell, Mehrnoosh Sadrzadeh, Elizabetta Jezek. Experimental Results on Exploiting Predicate-Argument Structure for Verb Similarity in Distributional Semantics. Proceedings of Logic and Machine Learning in Natural Language (LaML 2017), Gothenburg, June 12–13, 2017, Volume: http://hdl.handle.net/2077/54911.|
|Karin Cvetko-Vah, Mehrnoosh Sadrzadeh, Dimitri Kartsaklis, Benjamin Blundell. Non-commutative Logic for Compositional Distributional Semantics. LNCS proceedings of WOLLIC 2017, Vol. 10388, pp. 110-124.|
|Shauna Concannon, Pat Healey and Matthew Purver. Opening Up and Closing Down Discussion: Experimenting with Epistemic Status in Conversation. In the 39th Annual Meeting of the Cognitive Science Society (CogSci), London, July 2017.||bib|
|Mehrnoosh Sadrzadeh, Matthew Purver and Ruth Kempson. Incremental Distributional Semantics for Dynamic Syntax. In the 1st Dynamic Syntax Conference, London, April 2017.|
|Julian Hough and Matthew Purver. Probabilistic Record Type Lattices for Incremental Reference Processing. In Chatzikyriakidis & Luo (eds.), Modern Perspectives in Type-Theoretical Semantics, Springer, February 2017.||bib|
|Dimitri Kartsaklis and Mehrnoosh Sadrzadeh. Distributional Inclusion Hypothesis for Tensor-based Composition. Proceedings of COLING 2016, Osaka, Japan, December 2016.|
|Dimitri Kartsaklis and Mehrnoosh Sadrzadeh. A Compositional Distributional Inclusion Hypothesis. Proceedings of Conference on Logical Aspects of Computational Linguistics (LACL 2016), Nancy, France, December 2016.|
|Matej Dostal and Mehrnoosh Sadrzadeh. Many Valued Generalised Quantifiers for Natural Language in the DisCoCat Model.QMUL Technical Report, November 2016.|
|Jamie Forth, Kat Agres, Matthew Purver and Geraint Wiggins. Entraining IDyOT: Timing in the Information Dynamics of Thinking. Frontiers in Psychology 7:1575, 2016||bib|
|Stephen McGregor, Matthew Purver and Geraint Wiggins. Process Based Evaluation of Computer Generated Poetry. To appear in the INLG Workshop on Computational Creativity and Natural Language Generation, Edinburgh, UK, September 2016.||bib|
|Dmitrijs Milajevs, Mehrnoosh Sadrzadeh and Matthew Purver. Robust Co-occurrence Quantification for Lexical Distributional Semantics. To appear in the ACL 2016 Student Research Workshop, Berlin, Germany, August 2016.||bib|
|Kat Agres, Stephen McGregor, Karolina Rataj, Matthew Purver and Geraint Wiggins. Modeling Metaphor Perception with Distributional Semantics Vector Space Models. To appear in the C3GI: Computational Creativity, Concept Invention, and General Intelligence workshop at ESSLLI, Bolzano-Bozen, Italy, August 2016.||bib|
|Dimitri Kartsaklis, Matthew Purver and Mehrnoosh Sadrzadeh. Verb Phrase Ellipsis using Frobenius Algebras in Categorical Compositional Distributional Semantics. DSALT: Distributional Semantics and Linguistic Theory workshop at ESSLLI, Bolzano-Bozen, Italy, August 2016.|
|Mehrnoosh Sadrzadeh and Reinhard Muskens.
Lambdas and Vectors. ESSLLI workshop on Distributional Semantics and Linguistics Theory (DSALT), Bolzano, August 2016.
|Mehrnoosh Sadrzadeh and Reinhard Muskens. Context Update for Lambdas and Vectors. NASSLLI workshop on Statistical and Logical Models of Meaning (SaLMoM), Rutgers, NJ, July 2016.|
|Pat Healey, Matthew Purver and Christine Howes. Structural Repetition in Restricted and Unrestricted Dialogue. To appear in the 26th Annual Meeting of the Society for Text and Discourse, Kassel, Germany, July 2016.|
|Mehrnoosh Sadrzadeh. Quantifier Scope in Categorical Compositional Distributional Semantics. Workshop on Semantic Spaces at the Intersection of NLP, Physics and Cognitive Sciene (co-located with QPL 2016), Glasgow, June 2016.|
|Jules Hedges and Mehrnoosh Sadrzadeh. A Generalised Quantifier Theory of Natural Language in Categorical Compositional Distributional Semantics with Bialgebras. Preprint.|
|Dimitri Kartsaklis. Coordination in Categorical Compositional Distributional Semantics. Workshop on Semantic Spaces at the Intersection of NLP, Physics and Cognitive Sciene (co-located with QPL 2016), Glasgow, June 2016.|
|Stephen McGregor, Matthew Purver and Geraint Wiggins. Words, Concepts, and the Geometry of Analogy. To appear in the Workshop on Semantic Spaces at the Intersection of NLP, Physics and Cognitive Science, Glasgow, UK, June 2016.||bib|
|Esma Balkir, Dimitri Kartsaklis and Mehrnoosh Sadrzadeh. Sentence Entailment in Compositional Distributional Semantics. International Symposium on Artificial Intelligence and Mathematics (ISAIM), Florida, USA, January 2016.|
|Stephen McGregor, Kat Agres, Matthew Purver and Geraint Wiggins. From Distributional Semantics to Conceptual Spaces: A Novel Computational Method for Concept Creation. Journal of Artificial General Intelligence 6(1): 52-83, December 2015.||bib|
|Sascha Griffiths, Matthew Purver and Geraint Wiggins. From Phoneme to Morpheme: A Computational Model. In QITL-6, Tübingen, November 2015.||bib|
|Dmitrijs Milajevs, Mehrnoosh Sadrzadeh and Thomas Roelleke. IR Meets NLP: On the Semantic Similarity Between Subject-Verb-Object Phrases. ICTIR 2015, Northampton, Massachusetts, USA, September 2015.||bib|
|Karolina Sylwester and Matthew Purver. Twitter language use reflects psychological differences between Democrats and Republicans. PLoS ONE 10(9): e0137422, September 2015.||bib|
|Jianpeng Cheng and Dimitri Kartsaklis. Syntax-Aware Multi-Sense Word Embeddings for Deep Compositional Models of Meaning. EMNLP 2015, Lisbon, Portugal, September 2015.||bib|
|Sascha Griffiths, Mariano Mora McGinity, Jamie Forth, Matthew Purver and Geraint Wiggins. Information-Theoretic Segmentation of Natural Language. In AIC 2015, Turin, September 2015.||bib|
|Shauna Concannon, Pat Healey and Matthew Purver. Shifting Opinions: Experiments on Agreement and Disagreement in Dialogue. In SemDial 2015 (goDIAL), Gothenburg, August 2015.||bib|
|Shauna Concannon, Pat Healey and Matthew Purver. Taking a Stance: a Corpus Study of Reported Speech. In SemDial 2015 (goDIAL), Gothenburg, August 2015.||bib|
|Dimitri Kartsaklis and Mehrnoosh Sadrzadeh. A Frobenius Model of Information Structure in Categorical Compositional Distributional Semantics. In 14th Meeting on the Mathematics of Language (MoL), Chicago, USA, July 2015.||bib|
|Stephen McGregor, Matthew Purver and Geraint Wiggins. An Emergent Model of Metaphors as Transformations of Vector Spaces. To appear in the 13th International Cognitive Linguistics Conference (ICLC), Newcastle-upon-Tyne, July 2015.|
|Robin Piedeleu, Dimitri Kartsaklis, Bob Coecke and Mehrnoosh Sadrzadeh. Open System Quantum Semantics in Natural Language Processing. In 6th Conference on Algebra and Coalgebra in Computer Science (CALCO), Nijmegen, The Netherlands, June 2015.|
|Kat Agres, Stephen McGregor, Matthew Purver and Geraint Wiggins. Conceptualizing Creativity: From Distributional Semantics to Conceptual Spaces. To appear in the 6th International Conference on Computational Creativity (ICCC), Park City, UT, June 2015.|
|Dimitris Mylonas, Matthew Purver, Mehrnoosh Sadrzadeh, Lindsay MacDonald and Lewis Griffin. The Use of English Colour Terms in Big Data. In Proceedings of the 2015 Meeting of the International Colour Association (AIC), Tokyo, May 2015.|
|Arash Eshghi, Christine Howes, Eleni Gregoromichelaki, Julian Hough and Matthew Purver. Feedback in Conversation as Incremental Semantic Update. In Proceedings of IWCS, London, April 2015.||bib|
|Edward Grefenstette and Mehrnoosh Sadrzadeh. Concrete Models and Empirical Evaluations for the Categorical Compositional Distributional Model of Meaning. Computational Linguistics 41(1):71-118, March 2015.|
|Julian Hough and Matthew Purver. Strongly Incremental Repair Detection. In Proceedings of EMNLP, Doha, Qatar, October 2014.||bib|
|Dmitrijs Milajevs, Dimitri Kartsaklis, Mehrnoosh Sadrzadeh and Matthew Purver. Evaluating Neural Word Representations in Tensor-Based Compositional Settings. In Proceedings of EMNLP, Doha, Qatar, October 2014.||bib|
|Patrick Healey, Matthew Purver and Christine Howes. Divergence in Dialogue. PLoS ONE 9(6): e98598, June 2014.||bib|
|Christine Howes, Julian Hough, Matthew Purver and Rose McCabe. Helping, I Mean Assessing Psychiatric Communication: An Application of Incremental Self-Repair Detection. In Proceedings of SemDial 2014 (DialWatt), Edinburgh, September 2014.||bib|
|(Invited Talk) Matthew Purver. Ask Not What Semantics Can Do For Dialogue, Ask What Dialogue Can Do For Semantics. In Proceedings of SemDial 2014 (DialWatt), Edinburgh, September 2014.|
|Shauna Concannon and Matthew Purver. Inferring Cultural Preference of Arts Audiences Through Twitter Data. In Digital Intelligence, Nantes, September 2014. (best paper award)||bib|
|Julian Hough and Matthew Purver. Lattice Theoretic Relevance in Incremental Reference Processing. In the RefNet Workshop on Psychological and Computational Models of Reference Comprehension and Production, Edinburgh, August 2014.||bib|
|Christine Howes, Matthew Purver and Rose McCabe. Linguistic Indicators of Severity and Progress in Online Text-based Therapy for Depression. In Proceedings of the ACL 2014 workshop on Computational Linguistics and Clinical Psychology (CLCP), Baltimore, MD, June 2014.||bib|
|Stephen McGregor, Geraint Wiggins and Matthew Purver. Computational Creativity: A Philosophical Approach, and an Approach to Philosophy. In Proceedings of the 5th International Conference on Computational Creativity (ICCC), Ljubljana, June 2014.||bib|
|Matthew Purver, Julian Hough and Eleni Gregoromichelaki. Dialogue and Compound Contributions. In A. Stent and S. Bangalore (eds.), Natural Language Generation in Interactive Systems, pages 63-92, Cambridge University Press, June 2014.||bib|
|Shana Dacres, Hamed Haddadi and Matthew Purver. Topic and Sentiment Analysis on OSNs: a Case Study of Advertising Strategies on Twitter. In Proceedings of the 6th ASE International Conference on Social Computing (SocialCom), Stanford, May 2014.||bib|
|Julian Hough and Matthew Purver. Probabilistic Type Theory for Incremental Dialogue Processing. In Proceedings of the EACL 2014 Workshop on Type Theory and Natural Language Semantics (TTNLS), Gothenburg, April 2014.||bib|
|Dmitrijs Milajevs and Matthew Purver. Investigating the Contribution of Distributional Semantic Information for Dialogue Act Classification. In Proceedings of the EACL 2014 Workshop on Continuous Vector Space Models and their Compositionality (CVSC), Gothenburg, April 2014.||bib|