Publications

Google Scholar
ACL Anthology
DBLP

1. A. Yamaguchi, A. Villavicencio and N. Aletras (2025). How Can We Effectively Expand the Vocabulary of LLMs with 0.01GB of Target Language Text?. CL
   [pdf]
2. A. Yamaguchi, T. Morishita, A. Villavicencio and N. Aletras (2025). Adapting Chat Language Models Using Only Target Unlabeled Language Data. TMLR
   [pdf]
3. S. Lewis-Lim, X. Tan, Z. Zhao and N. Aletras (2025). Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation?. EMNLP
   [pdf]
4. X. Tan, M. Valentino, M. Akhter, M. Liakata and N. Aletras (2025). Enhancing Logical Reasoning in Language Models via Symbolically-Guided Monte Carlo Process Supervision. EMNLP
   [pdf]
5. A. Hughes, N. Ma and N. Aletras (2025). How Private are Language Models in Abstractive Summarization?. EMNLP
   [pdf]
6. O. Chlapanis, D. Galanis, N. Aletras and I Androutsopoulos (2025). GreekBarBench: A Challenging Benchmark for Free-Text Legal Reasoning and Citations. EMNLP Findings
   [pdf]
7. C. Meng, F. Tonolini, F. Mo, N. Aletras, E. Yilmaz and G. Kazai (2025). Bridging the Gap: From Ad-hoc to Proactive Search in Conversations. SIGIR
   [pdf]
8. M. Williams, G. Chrysostomou and N. Aletras (2025). Self-calibration for Language Model Quantization and Pruning. NAACL
   [pdf]
9. M. Williams and N. Aletras (2025). Vocabulary-level Memory Efficiency for Language Model Fine-tuning. Representation Learning for NLP Workshop (NAACL)
   [pdf]
10. Y. Mu, M. Jin, X. Song and N. Aletras (2024). Enhancing Data Quality through Simple De-duplication: Navigating Responsible Computational Social Science Research. EMNLP
    [pdf]
11. A. Yamaguchi, A. Villavicencio and N. Aletras (2024). An Empirical Study on Cross-lingual Vocabulary Adaptation for Efficient Language Model Inference. EMNLP Findings
    [pdf]
12. G. Chrysostomou, Z. Zhao, M. Williams and N. Aletras (2024). Investigating Hallucinations in Pruned Large Language Models for Abstractive Summarization. TACL
    [pdf]
13. M. Williams and N. Aletras (2024). On the Impact of Calibration Data in Post-training Quantization and Pruning. ACL
    [pdf]
14. F. Tonolini, N. Aletras, J. Massiah and G. Kazai (2024). Bayesian Prompt Ensembles: Model Uncertainty Estimation for Black-Box Large Language Models. ACL Findings
    [pdf]
15. Z. Zhao and N. Aletras (2024). Comparing Explanation Faithfulness between Multilingual and Monolingual Fine-tuned Language Models. NAACL
    [pdf]
16. M. Jin, D. Preoţiuc-Pietro, A. S. Doğruöz and N. Aletras (2024). Who is bragging more online? A large scale analysis of bragging in social media. LREC-COLING
    [pdf]
17. Y. Mu, X. Song K. Bontcheva and N. Aletras (2024). Examining the Limitations of Computational Rumor Detection Models Trained on Static Datasets. LREC-COLING
    [pdf]
18. Y. Mu, B. P. Wu, W. Thorne, A. Robinson, N. Aletras, C. Scarton, K. Bontcheva and X. Song (2024). Navigating Prompt Complexity for Zero-Shot Classification: A Study of Large Language Models in Computational Social Science. LREC-COLING
    [pdf]
19. R. Soun, A. Neerkaje, R. Sawhney, N. Aletras and P. Nakov (2024). RISE: Robust Early-exiting Internal Classifiers for Suicide Risk Evaluation. LREC-COLING
    [pdf]
20. D. Sanchez Villegas, D. Preoţiuc-Pietro and N. Aletras (2024). Improving Multimodal Classification of Social Media Posts by Leveraging Image-Text Auxiliary tasks. EACL Findings
    [pdf]
21. Y. Mu, P. Niu, K. Bontcheva and N. Aletras (2024). Predicting and Analyzing the Popularity of False Rumors in Weibo. Expert Systems with Applications
    [pdf]
22. A. Alajrami, K. Margatina and N. Aletras (2023). Understanding the Role of Input Token Characters in Language Models: How Does Information Loss Affect Performance?. EMNLP
    [pdf]
23. C. Goanta, N. Aletras, I. Chalkidis, S. Ranchordás, G. Spanakis (2023). Regulation and NLP (RegNLP): Taming Large Language Models. EMNLP
    [pdf]
24. H. Xue and N. Aletras (2023). Pit One Against Many: Leveraging Attention-head Embeddings for Parameter-efficient Multi-head Attention. EMNLP Findings
    [pdf]
25. K. Margatina, T. Schick, N. Aletras, J. Dwivedi-Yu (2023). Active Learning Principles for In-Context Learning with Large Language Models. EMNLP Findings
    [pdf]
26. D. Sanchez Villegas, C. Goanta and N. Aletras (2023). A Multimodal Analysis of Influencer Content on Twitter. AACL
    🏆 Area Chair Award: Society and NLP
    [pdf]
27. P. Vickers, L. Barrault, E. Monti and N. Aletras (2023). We Need to Talk About Classification Evaluation Metrics in NLP. AACL
    [pdf]
28. Z. Zhao and N. Aletras (2023). Incorporating Attribution Importance for Improving Faithfulness Metrics. ACL
    [pdf]
29. S. Mensah, K. Sun and N. Aletras (2023). Trading Syntax Trees for Wordpieces: Target-oriented Opinion Words Extraction with Wordpieces and Aspect Enhancement. ACL
    [pdf]
30. Y. Feng, Y. Jiao, A. Prasad, N. Aletras, E. Yilmaz and G. Kazai (2023). Schema-guided User Satisfaction Modeling for Task-oriented Dialogues. ACL
    [pdf]
31. K. Margatina and N. Aletras (2023). On the Limitations of Simulating Active Learning. ACL Findings
    [pdf]
32. Z. Shi, F. Tonolini, N. Aletras, E. Yilmaz, G. Kazai and Y. Jiao (2023). Rethinking Semi-supervised Learning with Language Models. ACL Findings
    [pdf]
33. F. Tonolini, N. Aletras, Y. Jiao and G. Kazai (2023). Robust Weak Supervision with Variational Auto-Encoders. ICML
    [pdf]
34. K. Dommett, S. Mensah, J. Zhu, T. Stafford and N. Aletras (2023). Is there a permanent campaign for online political advertising? Investigating partisan and non-party campaign activity in the UK between 2018-2021. Journal of Political Marketing
    [pdf]
35. K. Sun, R. Zhang, S. Mensah, N. Aletras, Y. Mao and X. Liu (2023). Self-training through Classifier Disagreement for Cross-Domain Opinion Target Extraction. WWW
    [pdf]
36. Y. Mu, K. Bontcheva and N. Aletras (2023). It’s about Time: Rethinking Evaluation on Rumor Detection Benchmarks using Chronological Splits. EACL Findings
    [pdf]
37. H. Xue and N. Aletras (2022). HashFormers: Towards Vocabulary-independent Pre-trained Transformers. EMNLP
    [pdf]
38. Z. Zhao, G. Chrysostomou, K. Bontcheva and N. Aletras (2022). On the Impact of Temporal Concept Drift on Model Explanations. EMNLP Findings
    [pdf]
39. M. Li, J. Chen, S. Mensah, N. Aletras, X. Yang and Y. Ye (2022). A Hierarchical N-Gram Framework for Zero-Shot Link Prediction. EMNLP Findings
    [pdf]
40. W. Li and N. Aletras (2022). Improving Graph-Based Text Representations with Character and Word Level N-grams. AACL
    [pdf]
41. T. Bose, N. Aletras, I. Illina and D. Fohr (2022). Domain Classification-based Source-specific Term Penalization for Domain Adaptation in Hate-speech Detection. COLING
    [pdf]
42. X. Ao, D. Sanchez Villegas, D. Preoţiuc-Pietro and N. Aletras (2022). Combining Humor and Sarcasm for Improving Political Parody Detection. NAACL
    [pdf]
43. R. Sawhney, S. Agarwal, A. T. Neerkaje, N. Aletras, P. Nakov and L. Flek (2022). Towards Suicide Ideation Detection Through Online Conversational Context. SIGIR
    [pdf]
44. Y. Mu, P. Niu and N. Aletras (2022). Identifying and Characterizing Active Citizens who Refute Misinformation in Social Media. ACM WebSci
    [pdf]
45. L. Zhang, H. Song, N. Aletras and H. Lu (2022). Node-Feature Convolution for Graph Convolutional Networks. Pattern Recognition
    [pdf]
46. M. Jin, D. Preoţiuc-Pietro, A. S. Doğruöz and N. Aletras (2022). Automatic Identification and Classification of Bragging in Social Media. ACL
    [pdf]
47. G. Chrysostomou and N. Aletras (2022). An Empirical Study on Explanations in Out-of-Domain Settings. ACL
    [pdf]
48. K. Margatina, L. Barrault and N. Aletras (2022). On the Importance of Effectively Adapting Pretrained Language Models for Active Learning. ACL
    [pdf]
49. A. Alajrami and N. Aletras (2022). How does the pre-training objective affect what large language models learn about linguistic properties?. ACL
    [pdf]
50. I. Chalkidis, A. Jana, D. Hartung, M. Bommarito, I. Androutsopoulos, D. M. Katz and N. Aletras (2022). LexGLUE: A Benchmark Dataset for Legal Language Understanding in English. ACL
    [pdf]
51. M. Fomicheva, L. Specia and N. Aletras (2022). Translation Error Detection as Rationale Extraction. ACL Findings
    [pdf]
52. T. Bose, N. Aletras, I. Illina and D. Fohr (2022). Dynamically Refined Regularization for Improving Cross-corpora Hate Speech Detection. ACL Findings
    [pdf]
53. G. Chrysostomou and N. Aletras (2022). Flexible Instance-specific Rationalization of NLP Models. AAAI
    [pdf]
54. K. Margatina, G. Vernikos, L. Barrault and N. Aletras (2021). Active Learning by Acquiring Contrastive Examples. EMNLP
    [pdf]
55. D. Sanchez Villegas and N. Aletras (2021). Point-of-Interest Type Prediction using Text and Images. EMNLP
    [pdf]
56. G. Chrysostomou and N. Aletras (2021). Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Salience. EMNLP
    [pdf]
57. S. Mensah, K. Sun and N. Aletras (2021). An Empirical Study on Leveraging Position Embeddings for Target-oriented Opinion Words Extraction. EMNLP
    [pdf]
58. A. Yamaguchi, G. Chrysostomou, K. Margatina and N. Aletras (2021). Frustratingly Simple Pretraining Alternatives to Masked Language Modeling. EMNLP
    [pdf]
59. G. Chrysostomou and N. Aletras (2021). Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classification. ACL
    [pdf]
60. P. Vickers, N. Aletras, E. Monti and L. Barrault (2021). In Factuality: Efficient Integration of Relevant Facts for Visual Question Answering. ACL
    [pdf]
61. D. Tsarapatsanis and N. Aletras (2021). On the Ethical Limits of Natural Language Processing on Legal Text. ACL Findings
    [pdf]
62. D. Sanchez Villegas, S. Mokaram and N. Aletras (2021). Analyzing Online Political Advertisements. ACL Findings
    [pdf]
63. A. Gajbhiye, M. Fomicheva, F. Alva-Manchego, F. Blain, A. Obamuyide, N. Aletras and L. Specia (2021). Knowledge Distillation for Quality Estimation. ACL Findings
    [pdf]
64. M. Jin and N. Aletras (2021). Modeling the Severity of Complaints in Social Media. NAACL
    [pdf]
65. I. Chalkidis, M. Fregadiotis, D. Tsarapatsanis, N. Aletras, I. Androutsopoulos and P. Malakatsiotis (2021). Paragraph-level Rationale Extraction through Regularization: A case study on European Court of Human Rights Cases. NAACL
    [pdf]
66. M. Fomicheva, S. Sun, L. Yankovskaya, F. Blain, F. Guzman, M. Fishel, N. Aletras, V. Chaudhary and L. Specia (2020). Unsupervised Quality Estimation for Neural Machine Translation. TACL
    [pdf]
67. M. Jin and N. Aletras (2020). Complaint Identification in Social Media with Transformer Networks. COLING
    [pdf]
68. I. Chalkidis, M. Fregadiotis, S. Kotitsas, P. Malakatsiotis, N. Aletras and I. Androutsopoulos (2020). An Empirical Study on Large-Scale Multi-Label Text Classification including Few and Zero-Shot Labels. EMNLP
    [pdf]
69. I. Chalkidis, M. Fregadiotis, P. Malakatsiotis, N. Aletras and I. Androutsopoulos (2020). LEGAL-BERT: The Muppets straight out of Law School. EMNLP Findings
    [pdf][pre-trained models]
70. D. Sanchez Villegas, D. Preoţiuc-Pietro and N. Aletras (2020). Point-of-Interest Type Inference from Social Media Text. AACL
    [pdf]
71. A. Maronikolakis, D. Sanchez Villegas, D. Preoţiuc-Pietro and N. Aletras (2020). Analyzing Political Parody in Social Media. ACL
    [pdf][data]
72. A. Alokaili, N. Aletras and M. Stevenson (2020). Automatic Generation of Topic Labels. SIGIR
    [pdf][data and code]
73. Y. Mu and N. Aletras (2020). Identifying Twitter Users who Repost Unreliable News Sources with Linguistic Information. PeerJ Computer Science
    [pdf]
74. F. Blain, N. Aletras and L. Specia (2020). Quality In, Quality Out: Learning from Actual Mistakes. EAMT
    [pdf]
75. T. Karmakharm, N. Aletras and K. Bontcheva (2019). Journalist-in-the-Loop: Continuous Learning as a Service for Rumour Analysis. EMNLP (demo)
    [pdf][demo]
76. I. Chalkidis, I. Androutsopoulos and N. Aletras (2019). Neural Legal Judgment Prediction in English. ACL
    [pdf]
77. D. Preoţiuc-Pietro, M. Gaman and N. Aletras (2019). Automatically Identifying Complaints in Social Media. ACL
    [pdf]
78. A. Alokaili, N. Aletras and M. Stevenson (2019). Re-Ranking Words to Improve Interpretability of Automatically Generated Topics. IWCS
    [pdf]
79. I. Chalkidis, M. Fregadiotis, P. Malakatsiotis, N. Aletras and I. Androutsopoulos (2019). Extreme Multi-Label Legal Text Classification: A case study in EU Legislation. Natural Legal Language Processing Workshop (NAACL)
    [pdf]
80. A. Tsakalidis, N. Aletras, M. Liakata and A. Cristea (2018). Nowcasting the Stance of Social Media Users in a Sudden Vote: The Case of the Greek Referendum. ACM CIKM
    [pdf]
81. N. Aletras,  B. P. Chamberlain (2018). Predicting Twitter User Socioeconomic Attributes with Network and Language Information ACM HyperText
    [pdf]
82. I. Soroduc, J. H. Lau, N. Aletras,  T. Baldwin (2017). Multimodal Topic Labelling. EACL
    [pdf]
83. N. Aletras and A. Mittal (2017). Labeling Topics with Images using Neural Networks. ECIR
    [pdf]
84. N. Aletras, T. Baldwin, J. H. Lau and M. Stevenson (2017). Evaluating Topic Representations for Exploring Document Collections. JASIST
    [pdf]
85. N. Aletras, D. Tsarapatsanis, D. Preoţiuc-Pietro and V. Lampos (2016). Predicting Judicial Decisions of the European Court of Human Rights: A Natural Language Processing Perspective, PeerJ Computer Science
    [pdf][html][data]
86. A. Gonzalez-Agirre, G. Rigau, E. Agirre, N. Aletras and M. Stevenson (2016). Why are these similar? Investigating item similarity types in a large Digital Library. JASIST
    [pdf]
87. V. Lampos, N. Aletras, J. K. Geyti, B. Zou, I. J. Cox (2016). Inferring the Socioeconomic Status of Social Media Users based on Behaviour and Language. ECIR
    [pdf]
88. D. Preoţiuc-Pietro, V. Lampos and N. Aletras (2015). An Analysis of the User Occupational Class through Twitter Content. ACL
    [pdf]
89. D. Preoţiuc-Pietro, S. Volkova, V. Lampos, Y. Bachrach, N. Aletras (2015). Studying User Income through Language, Behaviour and Affect in Social Media. PLOS ONE
    [pdf][data]
90. N. Aletras, J. H. Lau, T. Baldwin, M. Stevenson (2015). TM 2015 – Topic Models: Post-Processing and Applications Workshop. ACM CIKM
    [pdf]
91. N. Aletras and M. Stevenson (2015). A Hybrid Distributional and Knowledge-based Model of Lexical Semantics. *SEM
    [pdf]
92. N. Aletras, T. Baldwin, J. H. Lau and M. Stevenson (2014). Representing Topics Labels for Exploring Digital Libraries. IEEE/ACM JCDL
    [pdf]
93. N. Aletras and M. Stevenson (2014). Labelling Topics using Unsupervised Graph-based Methods. ACL
    [pdf]
94. V. Lampos, N. Aletras, D. Preoţiuc-Pietro and T. Cohn (2014). Predicting and Characterising User Impact on Twitter. EACL
    [pdf]
95. N. Aletras and M. Stevenson (2014). Measuring the Similarity between Automatically Generated Topics. EACL
    [pdf][data]
96. N. Aletras and M. Stevenson (2013). Representing Topics Using Images. NAACL-HLT
    [pdf][data]
97. N. Aletras and M. Stevenson (2013). Evaluating Topic Coherence Using Distributional Semantics. IWCS
    [pdf][data]
98. E. Agirre, N. Aletras, A. Gonzalez-Agirre, G. Rigau, M. Stevenson (2013). UBC UOS-TYPED: Regression for typed-similarity. *SEM
    [pdf]
99. E. Agirre, N. Aletras, P. Clough, S. Fernando, P. Goodale, M. Hall, A. Soroa, M. Stevenson (2013). PATHS: A System for Accessing Cultural Heritage Collections. ACL (demo)
    [pdf]
100. N. Aletras, M. Stevenson and P. Clough (2012). Computing Similarity between Items in a Digital Library of Cultural Heritage. ACM JOCCH.
     [pdf]
101. M. Hall, E. Agirre, N. Aletras, R. Bergheim, K. Chandrinos, P. Clough, S. Fernando, K. Fernie, P. Goodale, J. Griffiths, O. Lopez de Lacalle, A. de Polo, A. Soroa and M. Stevenson (2012). PATHS - Exploring Digital Cultural Heritage Spaces. TPDL (demo)
     [pdf]
102. N. Aletras and M. Stevenson (2012). Computing similarity between cultural heritage items using multimodal features. LaTeCH Workshop (ACL)
     [pdf]
103. P. Goodale, P. Clough, N. Ford, M. Hall, M. Stevenson, S. Fernando, N. Aletras, K. Fernie, P. Archer and A. de Polo (2012). User-Centred Design to Support Exploration and Path Creation in Cultural Heritage Collections. EuroHCIR2012 Workshop [pdf]

Thesis

• N. Aletras (2014). Interpreting Document Collections with Topic Models. PhD Thesis, University of Sheffield [pdf]