Papers by Simon Clematide

17 papers
Improving Occupational ISCO Classification of Multilingual Swiss Job Postings with LLM-Refined Training Data (2025.findings-acl)

Copied to clipboard

Challenge: 80% of job postings are German, 11% French, 8% English, and under 1% Italian.
Approach: They propose a method that refines silver-standard ISCO labels by consolidating them with predictions from pre-fine-tuned models to resolve discrepancies.
Outcome: The proposed method raises Top-1 accuracy on silver data to 58.3% and reaches 80% precision on held-out data.
Evaluation of HTR models without Ground Truth Material (2022.lrec-1)

Copied to clipboard

Challenge: Optical Character Recognition (OCR) is a well-established technique for digitising historical printed collections in libraries and archives.
Approach: They propose to use masked language models to evaluate handwritten text recognition models . they propose to introduce GT-free metrics to evaluate models to ensure best results .
Outcome: The proposed model evaluations are based on lexicon-based and masked language models.
Information Representation Fairness in Long-Document Embeddings: The Peculiar Interaction of Positional and Language Bias (2026.findings-acl)

Copied to clipboard

Challenge: Existing studies show that embedding models exhibit systematic positional and language biases when documents are longer and consist of multiple segments.
Approach: They propose a permutation-based evaluation framework to quantify embedding biases . they propose an inference-time attention calibration method that redistributes attention more evenly across document positions .
Outcome: The proposed framework reduces the positional and language biases in embedding models . the proposed framework improves the discoverability of later segments .
Similar, but why? A Toolkit for Explaining Text Similarity (2026.eacl-demo)

Copied to clipboard

Challenge: XPLAINSIM is a Python package that explains textual similarity in an easy-to-use way.
Approach: They propose a Python package that unifies three approaches to explain text similarity . they demonstrate the value of the package through intuitive examples and empirical research .
Outcome: XPLAINSIM is a Python package that unifies three approaches to explain text similarity . the authors show that the package is useful for explaining text similarities in a simple way .
Semi-supervised Contextual Historical Text Normalization (2020.acl-main)

Copied to clipboard

Challenge: Historical text normalization is the task of mapping historical word forms to their modern counterparts.
Approach: They propose to use a generative normalization model to obtain contextualization from the target-side language model.
Outcome: et al., 2018) show that the most effective approach reduces manual normalization time and manual training costs.
Neural Transition-based String Transduction for Limited-Resource Setting in Morphology (C18-1)

Copied to clipboard

Challenge: Morphological string transduction involves mapping one word form into another, possibly given a feature specification for the mapping.
Approach: They propose a neural transition-based model that uses a simple set of edit actions for morphological transduction tasks such as reinflection and reinflation.
Outcome: The proposed model outperforms state-of-the-art systems on low and medium training-set sizes and is competitive in the high-resource setting.
PARAPHRASUS: A Comprehensive Benchmark for Evaluating Paraphrase Detection Models (2025.coling-main)

Copied to clipboard

Challenge: prevailing notion of paraphrase is simplistic, offering only limited view of vast spectrum of paraphrasing phenomena.
Approach: They propose a benchmarking tool for paraphrase detection that provides a fine-grained evaluation lens.
Outcome: The proposed benchmark enables rapid calibration of models to specific strictness levels.
Interpretable Text Embeddings and Text Similarity Explanation: A Survey (2025.emnlp-main)

Copied to clipboard

Challenge: Text embeddings are a fundamental component in many NLP tasks, but their interpretation and explanation remain challenging.
Approach: They propose a framework for interpretable text embeddings and text similarity explanation . they characterize the main ideas, approaches, and trade-offs and discuss lessons learned .
Outcome: The proposed methods are compared with existing models and compare them with existing ones.
Strategies and Challenges for Crowdsourcing Regional Dialect Perception Data for Swiss German and Swiss French (L18-1)

Copied to clipboard

Challenge: a crowdsourcing project in the field of Swiss German dialects and Swiss French accents collects linguistic data.
Approach: a gamified crowdsourcing platform was set up to collect linguistic data on Swiss German and Swiss French accents.
Outcome: a gamified crowdsourcing platform collects linguistic data on Swiss German and Swiss French accents . the platform has provided 470,000 localizations, with 7,500 registered users and 30,000 anonymous visitors .
Language Resources for Historical Newspapers: the Impresso Collection (2020.lrec-1)

Copied to clipboard

Challenge: digitization efforts are slowly but steadily contributing an increasing amount of facsimiles of cultural heritage documents.
Approach: They propose to use a collection of newspaper data sets composed of text and image resources, curated and published within the context of the ‘impresso - Media Monitoring of the Past’ project.
Outcome: The aim of the impresso resource collection is to contribute to historical language resources, and strengthen approaches to non-standard inputs and foster efficient processing of historical documents.
Imitation Learning for Neural Morphological String Transduction (D18-1)

Copied to clipboard

Challenge: Recent studies have shown that neural transition-based models can be used for morphological tasks such as inflection generation and lemmatization without a character aligner or warm start.
Approach: They propose to use imitation learning to train a neural transition-based string transducer for morphological tasks such as inflection generation and lemmatization.
Outcome: The proposed model eliminates the need for a character aligner or warm start and achieves state-of-the-art performance on several datasets.
How Much Data Do You Need? About the Creation of a Ground Truth for Black Letter and the Effectiveness of Neural OCR (2020.lrec-1)

Copied to clipboard

Challenge: Recent advances in Optical Character Recognition and Handwritten Text Recognition have led to more accurate text recognition of historical documents.
Approach: They propose to build a ground truth for a German-language newspaper published in black letter . they also evaluate the performance of different OCR engines and estimate how much data is needed to achieve high-quality OCR results.
Outcome: The proposed model can recognise black letter text and performs well on data they have not seen during training.
Examining Multilingual Embedding Models Cross-Lingually Through LLM-Generated Adversarial Examples (2025.findings-emnlp)

Copied to clipboard

Challenge: Cross-Lingual Semantic Discrimination (CLSD) is a lightweight evaluation task that requires only parallel sentences and a Large Language Model (LLM) to generate adversarial distractors.
Approach: They propose a lightweight task that requires only parallel sentences and a Large Language Model (LLM) to generate adversarial distractors.
Outcome: The proposed task requires only parallel sentences and a Large Language Model (LLM) to generate adversarial distractors.
Cheap Character Noise for OCR-Robust Multilingual Embeddings (2025.findings-acl)

Copied to clipboard

Challenge: Optical character recognition (OCR) is a key component of the digitization of historical documents.
Approach: They propose a method that fine-tunes existing multilingual models using noisy texts and a contrastive loss.
Outcome: The proposed model improves on the training data of existing models using noisy texts and a contrastive loss.
Evaluation of Transfer Learning and Domain Adaptation for Analyzing German-Speaking Job Advertisements (2022.lrec-1)

Copied to clipboard

Challenge: a paper presents text mining approaches on German-speaking job advertisements . transfer learning and domain adaptation are used to build text mining applications .
Approach: They propose text mining approaches on German-speaking job advertisements . they use transfer learning and domain adaptation to build language models adapted to job ads .
Outcome: The proposed approaches outperform general-domain language models pre-trained on ten times more data.
Sentence Smith: Controllable Edits for Evaluating Text Embeddings (2025.emnlp-main)

Copied to clipboard

Challenge: Controllable and transparent text generation has been a long-standing goal in NLP . but previous approaches were hindered by parsing and generation insufficiencies .
Approach: They propose a framework for English that has three steps: 1. Parsing a sentence into a semantic graph. 2. Applying human-designed semantic manipulation rules. 3. Generating text from the manipulated graph.
Outcome: The proposed framework for English is based on a neural network and parsers.
Mapping Work Task Descriptions from German Job Ads on the O*NET Work Activities Ontology (2024.lrec-main)

Copied to clipboard

Challenge: a new method for mapping job tasks to labor market ontologies is proposed . a top configuration of the method achieved a notable performance improvement .
Approach: They use ontological data with Multiple Negatives Ranking loss to extract job tasks from job postings . they integrate labeled job advertisement data into training to improve their mapping .
Outcome: The proposed method improves on the German job ads and their ontology . it can be used to map job tasks to established labor market ontologies or taxonomies .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations