Papers by Gerasimos Spanakis
Finding the Law: Enhancing Statutory Article Retrieval via Graph Neural Networks (2023.eacl-main)
Copied to clipboard
| Challenge: | Statutory article retrieval (SAR) is a promising application of legal text processing. |
| Approach: | They propose a graph-augmented dense statute retriever model that incorporates the structure of legislation via a neural network to improve density retrieval performance. |
| Outcome: | The proposed model outperforms baselines on a real-world expert-annotated dataset. |
Triple-Encoders: Representations That Fire Together, Wire Together (2024.acl-long)
Copied to clipboard
| Challenge: | Existing search-based dialog models re-encode the dialog history at every turn, causing high cost. |
| Approach: | They propose a method that encodes relative distances between utterances via a bi-encoder . they use a hebbian-inspired co-occurrence learning objective to compute distributed utterrance mixtures . |
| Outcome: | The proposed method improves on bi-encoded utterances and even better generalization . it can encode 2020 and Erker et al. (2023) with the same results. |
A Statutory Article Retrieval Dataset in French (2022.acl-long)
Copied to clipboard
| Challenge: | Statutory article retrieval is the task of automatically retrieving law articles relevant to a legal question. |
| Approach: | They propose to use a Belgian Statutory Article Retrieval Dataset to test various retrieval approaches including lexical and dense architectures to achieve a 74.8% R@100. |
| Outcome: | The proposed dataset outperforms existing systems in both zero-shot and supervised setups. |
Regulation and NLP (RegNLP): Taming Large Language Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | polarization in AI safety and ethics debates are swaying political agendas on AI regulation and governance . regulation studies are rich source of knowledge on how to systematically deal with risk and uncertainty . |
| Approach: | They argue that NLP research can benefit from proximity to regulatory studies . they argue that regulation studies should focus on linking scientific knowledge to regulatory processes . |
| Outcome: | The proposed research space should focus on linking scientific knowledge to regulatory processes based on systematic methodologies. |
Know When to Fuse: Investigating Non-English Hybrid Retrieval in the Legal Domain (2025.coling-main)
Copied to clipboard
| Challenge: | Existing research focuses on a limited set of retrieval methods, evaluated in pairs on domain-general datasets exclusively in English. |
| Approach: | They evaluate the efficacy of hybrid search across a variety of retrieval models in the french language . they find that fusion of different domain-general models consistently enhances performance . |
| Outcome: | The proposed model improves in-domain performance compared to a single model in a zero-shot context . the proposed model also improves when the models are trained in- domain . |
A Representation Level Analysis of NMT Model Robustness to Grammatical Errors (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing work on robustness failures or improving robustness has focused on documenting failures . however, there has been limited analysis of model representations in response to noise. |
| Approach: | They perform Grammatical Error Detection probing and representational similarity analysis to examine model representations of ungrammatical inputs and how they evolve through model layers. |
| Outcome: | The proposed model detects and corrects the grammatical error by moving its representation toward the correct form. |
MATCHED: Multimodal Authorship-Attribution To Combat Human Trafficking in Escort-Advertisement Data (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for human trafficking detection ignore the multimodal nature of online ads . sex trafficking is a pervasive crime exploiting individuals of all ages and genders . |
| Approach: | They propose to use multimodal authorship attributes to identify suspicious ads that combine text and images to improve vendor identification and verification tasks. |
| Outcome: | The proposed model outperforms existing methods for vendor identification and verification tasks using text-only, vision-only and multimodal training objectives. |
You Are What You Train: Effects of Data Composition on Training Context-aware Machine Translation Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Using sparse contextually rich examples, we demonstrate a strong association between training data sparsity and model performance. |
| Approach: | They propose two training strategies to leverage contextually rich examples in training data . they demonstrate strong association between sparsity and model performance . |
| Outcome: | The proposed training strategies improve translation accuracy by 6 and 8 percentage points on the ctxPro evaluation. |
Sequence Shortening for Context-Aware Machine Translation (2024.findings-eacl)
Copied to clipboard
| Challenge: | Context-aware Machine Translation aims to improve translations of sentences by incorporating surrounding sentences as context. |
| Approach: | They propose to use latent representation of source sentence as context in a multi-encoder architecture to achieve higher accuracy on contrastive datasets. |
| Outcome: | The proposed architectures achieve comparable BLEU and COMET scores on contrastive datasets and comparable accuracies on the single- and multi-encoder approaches. |
IDTraffickers: An Authorship Attribution Dataset to link and connect Potential Human-Trafficking Operations on Text Escort Advertisements (2023.emnlp-main)
Copied to clipboard
| Challenge: | a significant number of human trafficking cases are associated with online advertisements . identification of HT vendors is challenging for law enforcement agencies . |
| Approach: | IDTraffickers uses 87,595 text ads and 5,244 vendor labels to link HT vendors . a macro-F1 score is achieved in a closed-set classification environment . |
| Outcome: | IDTraffickers is a dataset that enables verification and identification of HT vendors . the model achieves a macro-F1 score in a closed-set classification environment . |
VendorLink: An NLP approach for Identifying & Linking Vendor Migrants & Potential Aliases on Darknet Markets (2023.acl-long)
Copied to clipboard
| Challenge: | Anonymity on the Darknet allows vendors to stay undetected by using multiple vendor aliases or frequently migrating between markets. |
| Approach: | They propose an NLP-based approach that examines writing patterns to verify, identify, and link unique vendor accounts across text advertisements on seven public Darknet markets. |
| Outcome: | The proposed approach can help law enforcement agencies make more informed decisions by verifying and identifying migrating vendors and their potential aliases on existing and Low-Resource (LR) emerging Darknet markets. |
SeqAttack: On Adversarial Attacks for Named Entity Recognition (2021.emnlp-demo)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) is a task of recognizing named entities in a chunk of text. |
| Approach: | They investigate the portability of adversarial attacks from text classification to named entity recognition and the ability of adversary training to counteract these attacks. |
| Outcome: | The proposed framework and web application can be used to cherry pick adversarial examples and perform character-level and word-level attacks. |
Imagination is All You Need! Curved Contrastive Learning for Abstract Sequence Modeling Utilized on Long Short-Term Dialogue Planning (2023.findings-acl)
Copied to clipboard
| Challenge: | Curved Contrastive Learning is a new approach for learning the relative turn distance between utterance pairs in multi-turn dialogues. |
| Approach: | They propose a technique for learning the relative turn distance between utterance pairs in multi-turn dialogues by projecting goal utterence and reply candidates into a latent space. |
| Outcome: | The proposed technique can guide transformers towards a goal in a zero-shot fashion . it can be used to estimate the likelihood of sequences by the entailment strength . |
ColBERT-XM: A Modular Multi-Vector Representation Model for Zero-Shot Multilingual Information Retrieval (2025.coling-main)
Copied to clipboard
| Challenge: | Existing approaches to improve retrieval effectiveness in high-resource languages are limited due to the lack of high-quality labeled data in non-English languages. |
| Approach: | They propose a modular dense retrieval model that learns from the rich data of a single high-resource language and effectively zero-shot transfers to a wide array of languages. |
| Outcome: | The proposed model performs well against state-of-the-art multilingual retrieval models trained on more extensive datasets in various languages. |
Analyzing the Attention Heads for Pronoun Disambiguation in Context-aware Machine Translation Models (2025.coling-main)
Copied to clipboard
| Challenge: | In Context-aware Machine Translation, the context sentences are available to the system and can be used to maintain coherence of translation and resolve ambiguities. |
| Approach: | They investigate the role of attention heads in Context-aware Machine Translation models for pronoun disambiguation in the English-to-German and English- to-French directions. |
| Outcome: | The attention heads influence the models' ability to disambiguate pronouns in the English-to-German and English- to-French directions. |