arXiv subjects

Laurent Romary

Publications and source records attributed to Laurent Romary.

At least 19 recordsLinked to original sources

arXiv2026

The INRIA DataLake: A Generic and Scalable Ecosystem of Pipelines for HAL Applied to Software Mentions Tracking

Research repositories contain a large amount of scientific knowledge, but access to structured articles and specialised information, such as datasets or software metadata, remains limited. In this paper, we present the INRIA DataLake project, which provides an ecosystem of scalable and interconnected pipelines for preparing scientific literature, extracting structured information, and applying specialised treatments. Using a large-scale shared infrastructure, Grid'5000/ABACA, we demonstrate our ecosystem through a concrete use case: extracting software mentions from scientific articles deposited daily and visualising them after validation in the HAL research portal. Our results show that the system can efficiently process large volumes of scientific literature while supporting user validation and interoperability with external systems. Designed to grow by integrating additional pipelines and sharing the preparation effort across research groups, this project already contributes to open science through improved visibility and tracking of research software.

cs.DL↗

arXiv2026

Analyzing and Encoding the Al-Mawrid Arabic-English Dictionary with the ISO Language Markup Framework and TEI Lex-0

This paper presents a robust methodology for the systematic digitization and encoding of the Al-Mawrid Arabic-English dictionary, transforming it from a legacy print resource into a standardized computational lexicon. Addressing a significant gap in Arabic lexical infrastructure, the study adopts a dual-standard framing that aligns the ISO Lexical Markup Framework (LMF) with the Text Encoding Initiative TEI Lex-0 guidelines. By applying an editorial view to the dictionary's macro- and microstructure, the research resolves the structural ambiguities and punctuation inconsistencies typical of 20th-century bilingual dictionaries. The methodology is grounded in an empirical analysis of the dictionary's lexical knowledge density. Drawing on a representative sample (the letter Ayn, comprising 4.6% of the total volume), the study provides scientific weight to the encoding process, demonstrating a structural parsing accuracy of 91%. Quantitative evaluation of the information extraction rules reveals high performance, with 85% precision and 98% recall for synonyms, and 88% precision for other morpho-semantic features. Beyond technical description, the paper provides a critical comparison with existing Arabic lexical resources and discusses the limitations of TEI Lex-0 when modelling specific Arabic phenomena, such as implicit "open set" semantic relations and scattered morphological cues. Furthermore, the study explores the potential for Linguistic Linked Open Data (LLOD) integration by establishing a scalable prefix-based referencing system that facilitates the resource's inclusion in the semantic web. The result is an interoperable, machine-tractable resource that provides a reproducible workflow for the retro-digitization of complex legacy bilingual lexicons within the Arabic NLP and Digital Humanities communities.

cs.CL↗

arXiv2026

HALvest-Contrastive: Retrieval-Like Authorship Attribution with Patch-Level Late Interaction

Authorship attribution asks whether two pieces of text share a writer, but topical confound makes the task deceptively easy: two authors covering the same topic may look more alike than one author covering two topics. Scholarly prose offers a natural remedy, academic writers produce multiple papers on related but distinct topics while maintaining consistent stylistic habits. We introduce HALvest, a 17-billion-token multilingual corpus of open-access academic papers, and its English contrastive derivative HALvest-Contrastive, where same-author passages are drawn from distinct papers within a disciplinary field to minimize topical overlap. We validate our benchmark by showing that a strong lexical baseline collapses once topical shortcuts are removed. On this same benchmark, we revisit how authorship is scored. Standard systems compress each document into a single vector. We instead keep a sequence of vectors and compare them with late interaction, then propose patch-level late interaction, which groups neighboring tokens into patches before matching. Matching at the sequence level greatly improves performance over the single-vector baseline, but the optimal interaction granularity is subtle.

cs.DL↗

arXiv2026

Where Does Authorship Signal Emerge in Encoder-Based Language Models?

Authorship attribution models fine-tuned with the same pretrained encoder, data, and loss can differ four-fold in performance depending only on their scoring mechanism. We use mechanistic interpretability tools to explain this gap. Stylistic features such as word length, punctuation density, and function-word frequency are similarly available at every layer in every model we probe, including an off-the-shelf control encoder, suggesting that the gap is not explained by their linear readability. Instead, causal intervention shows that the scorer appears to determine where the encoder consolidates authorship signal. Mean pooling forces consolidation by early to mid layers, while late interaction defers it to later layers. We further derive this difference from the gradient structure of each scorer, and training dynamics reveal distinct learning trajectories that follow from that difference.

cs.CL↗

arXiv2026

Using Machine Mental Imagery for Representing Common Ground in Situated Dialogue

Situated dialogue requires speakers to maintain a reliable representation of shared context rather than reasoning only over isolated utterances. Current conversational agents often struggle with this requirement, especially when the common ground must be preserved beyond the immediate context window. In such settings, fine-grained distinctions are frequently compressed into purely textual representations, leading to a critical failure mode we call \emph{representational blur}, in which similar but distinct entities collapse into interchangeable descriptions. This semantic flattening creates an illusion of grounding, where agents appear locally coherent but fail to track shared context persistently over time. Inspired by the role of mental imagery in human reasoning, and based on the increased availability of multimodal models, we explore whether conversational agents can be given an analogous ability to construct some depictive intermediate representations during dialogue to address these limitations. Thus, we introduce an active visual scaffolding framework that incrementally converts dialogue state into a persistent visual history that can later be retrieved for grounded response generation. Evaluation on the IndiRef benchmark shows that incremental externalization itself improves over full-dialog reasoning, while visual scaffolding provides additional gains by reducing representational blur and enforcing concrete scene commitments. At the same time, textual representations remain advantageous for non-depictable information, and a hybrid multimodal setting yields the best overall performance. Together, these findings suggest that conversational agents benefit from an explicitly multimodal representation of common ground that integrates depictive and propositional information.

cs.CL↗

arXiv2026

Frame of Reference: Addressing the Challenges of Common Ground Representation in Situational Dialogs

Common ground plays a critical role in situated spoken dialogs, where interlocutors must establish and maintain shared references to entities, events, and relations to sustain coherent interaction in a shared space and over time. With the increasing presence of embodied conversational agents and social robots, the ability to correctly ground this kind of conversational content in order to refer back later also becomes important for dialog systems. Prior studies have demonstrated that LLMs are capable of performing certain grounding acts like acknowledgments. However, relatively little work has investigated their capacity to leverage the grounded information, like in complex scenarios involving space and time (e.g., "let's go to that café near the park we went to yesterday"). To that end, in this work, we evaluate a model's ability to establish common ground by utilizing these "relational references" in the dynamic and shared environments of situated dialogs. We then test multiple methods for representing common ground and further propose approaches to improve their performance by using reinforcement learning on our synthetically generated dialog data .

cs.CL↗

arXiv2025

Making Software FAIR: A machine-assisted workflow for the research software lifecycle

A key issue hindering discoverability, attribution and reusability of open research software is that its existence often remains hidden within the manuscript of research papers. For these resources to become first-class bibliographic records, they first need to be identified and subsequently registered with persistent identifiers (PIDs) to be made FAIR (Findable, Accessible, Interoperable and Reusable). To this day, much open research software fails to meet FAIR principles and software resources are mostly not explicitly linked from the manuscripts that introduced them or used them. SoFAIR is a 2-year international project (2024-2025) which proposes a solution to the above problem realised over the content available through the global network of open repositories. SoFAIR will extend the capabilities of widely used open scholarly infrastructures (CORE, Software Heritage, HAL) and tools (GROBID) operated by the consortium partners, delivering and deploying an effective solution for the management of the research software lifecycle, including: 1) ML-assisted identification of research software assets from within the manuscripts of scholarly papers, 2) validation of the identified assets by authors, 3) registration of software assets with PIDs and their archival.

cs.DL↗

arXiv2025

How to build an Open Science Monitor based on publications? A French perspective

Many countries and institutions are striving to develop tools to monitor their open science policies. Since 2018, with the launch of its National Plan for Open Science, France has been progressively implementing a monitoring framework for its public policy, relying exclusively on reliable, open, and controlled data. Currently, this monitoring focuses on research outputs, particularly publications, as well as theses and clinical trials. Publications serve as a basis for analyzing other dimensions, including research data, code, and software. The metadata associated with publications is therefore particularly valuable, but the methodology for leveraging it raises several challenges. Here, we briefly outline how we have used this metadata to construct the French Open Science Monitor.

cs.DL↗

arXiv2024

Diachronic Document Dataset for Semantic Layout Analysis

We present a novel, open-access dataset designed for semantic layout analysis, built to support document recreation workflows through mapping with the Text Encoding Initiative (TEI) standard. This dataset includes 7,254 annotated pages spanning a large temporal range (1600-2024) of digitised and born-digital materials across diverse document types (magazines, papers from sciences and humanities, PhD theses, monographs, plays, administrative reports, etc.) sorted into modular subsets. By incorporating content from different periods and genres, it addresses varying layout complexities and historical changes in document structure. The modular design allows domain-specific configurations. We evaluate object detection models on this dataset, examining the impact of input size and subset-based training. Results show that a 1280-pixel input size for YOLO is optimal and that training on subsets generally benefits from incorporating them into a generic model rather than fine-tuning pre-trained weights.

cs.CV↗

arXiv2024

CamemBERT-bio: Leveraging Continual Pre-training for Cost-Effective Models on French Biomedical Data

Clinical data in hospitals are increasingly accessible for research through clinical data warehouses. However these documents are unstructured and it is therefore necessary to extract information from medical reports to conduct clinical studies. Transfer learning with BERT-like models such as CamemBERT has allowed major advances for French, especially for named entity recognition. However, these models are trained for plain language and are less efficient on biomedical data. Addressing this gap, we introduce CamemBERT-bio, a dedicated French biomedical model derived from a new public French biomedical dataset. Through continual pre-training of the original CamemBERT, CamemBERT-bio achieves an improvement of 2.54 points of F1-score on average across various biomedical named entity recognition tasks, reinforcing the potential of continual pre-training as an equally proficient yet less computationally intensive alternative to training from scratch. Additionally, we highlight the importance of using a standard evaluation protocol that provides a clear view of the current state-of-the-art for French biomedical models.

cs.CL↗

arXiv2024

Conversational Grounding: Annotation and Analysis of Grounding Acts and Grounding Units

Successful conversations often rest on common understanding, where all parties are on the same page about the information being shared. This process, known as conversational grounding, is crucial for building trustworthy dialog systems that can accurately keep track of and recall the shared information. The proficiencies of an agent in grounding the conveyed information significantly contribute to building a reliable dialog system. Despite recent advancements in dialog systems, there exists a noticeable deficit in their grounding capabilities. Traum provided a framework for conversational grounding introducing Grounding Acts and Grounding Units, but substantial progress, especially in the realm of Large Language Models, remains lacking. To bridge this gap, we present the annotation of two dialog corpora employing Grounding Acts, Grounding Units, and a measure of their degree of grounding. We discuss our key findings during the annotation and also provide a baseline model to test the performance of current Language Models in categorizing the grounding acts of the dialogs. Our work aims to provide a useful resource for further research in making conversations with machines better understood and more reliable in natural day-to-day collaborative dialogs.

cs.CL↗

arXiv2022

Towards a Cleaner Document-Oriented Multilingual Crawled Corpus

The need for raw large raw corpora has dramatically increased in recent years with the introduction of transfer learning and semi-supervised learning methods to Natural Language Processing. And while there have been some recent attempts to manually curate the amount of data necessary to train large language models, the main way to obtain this data is still through automatic web crawling. In this paper we take the existing multilingual web corpus OSCAR and its pipeline Ungoliant that extracts and classifies data from Common Crawl at the line level, and propose a set of improvements and automatic annotations in order to produce a new document-oriented version of OSCAR that could prove more suitable to pre-train large generative language models as well as hopefully other applications in Natural Language Processing and Digital Humanities.

cs.CL↗

arXiv2021

SuperMat: Construction of a linked annotated dataset from superconductors-related publications

A growing number of papers are published in the area of superconducting materials science. However, novel text and data mining (TDM) processes are still needed to efficiently access and exploit this accumulated knowledge, paving the way towards data-driven materials design. Herein, we present SuperMat (Superconductor Materials), an annotated corpus of linked data derived from scientific publications on superconductors, which comprises 142 articles, 16052 entities, and 1398 links that are characterised into six categories: the names, classes, and properties of materials; links to their respective superconducting critical temperature (Tc); and parametric conditions such as applied pressure or measurement methods. The construction of SuperMat resulted from a fruitful collaboration between computer scientists and material scientists, and its high quality is ensured through validation by domain experts. The quality of the annotation guidelines was ensured by satisfactory Inter Annotator Agreement (IAA) between the annotators and the domain experts. SuperMat includes the dataset, annotation guidelines, and annotation support tools that use automatic suggestions to help minimise human errors.

cond-mat.supr-con↗

arXiv2020

A Monolingual Approach to Contextualized Word Embeddings for Mid-Resource Languages

We use the multilingual OSCAR corpus, extracted from Common Crawl via language classification, filtering and cleaning, to train monolingual contextualized word embeddings (ELMo) for five mid-resource languages. We then compare the performance of OSCAR-based and Wikipedia-based ELMo embeddings for these languages on the part-of-speech tagging and parsing tasks. We show that, despite the noise in the Common-Crawl-based OSCAR data, embeddings trained on OSCAR perform much better than monolingual embeddings trained on Wikipedia. They actually equal or improve the current state of the art in tagging and parsing for all five languages. In particular, they also improve over multilingual Wikipedia-based contextual embeddings (multilingual BERT), which almost always constitutes the previous state of the art, thereby showing that the benefit of a larger, more diverse corpus surpasses the cross-lingual benefit of multilingual embedding architectures.

cs.CL↗

arXiv2020

Establishing a New State-of-the-Art for French Named Entity Recognition

The French TreeBank developed at the University Paris 7 is the main source of morphosyntactic and syntactic annotations for French. However, it does not include explicit information related to named entities, which are among the most useful information for several natural language processing tasks and applications. Moreover, no large-scale French corpus with named entity annotations contain referential information, which complement the type and the span of each mention with an indication of the entity it refers to. We have manually annotated the French TreeBank with such information, after an automatic pre-annotation step. We sketch the underlying annotation guidelines and we provide a few figures about the resulting annotations.

cs.CL↗

arXiv2020

CamemBERT: a Tasty French Language Model

Pretrained language models are now ubiquitous in Natural Language Processing. Despite their success, most available models have either been trained on English data or on the concatenation of data in multiple languages. This makes practical use of such models --in all languages except English-- very limited. In this paper, we investigate the feasibility of training monolingual Transformer-based language models for other languages, taking French as an example and evaluating our language models on part-of-speech tagging, dependency parsing, named entity recognition and natural language inference tasks. We show that the use of web crawled data is preferable to the use of Wikipedia data. More surprisingly, we show that a relatively small web crawled dataset (4GB) leads to results that are as good as those obtained using larger datasets (130+GB). Our best performing model CamemBERT reaches or improves the state of the art in all four downstream tasks.

cs.CL↗

arXiv2019

LMF Reloaded

Lexical Markup Framework (LMF) or ISO 24613 [1] is a de jure standard that provides a framework for modelling and encoding lexical information in retrodigitised print dictionaries and NLP lexical databases. An in-depth review is currently underway within the standardisation subcommittee , ISO-TC37/SC4/WG4, to find a more modular, flexible and durable follow up to the original LMF standard published in 2008. In this paper we will present some of the major improvements which have so far been implemented in the new version of LMF.

cs.CL↗

arXiv2016

Deep encoding of etymological information in TEI

This paper aims to provide a comprehensive modeling and representation of etymological data in digital dictionaries. The purpose is to integrate in one coherent framework both digital representations of legacy dictionaries, and also born-digital lexical databases that are constructed manually or semi-automatically. We want to propose a systematic and coherent set of modeling principles for a variety of etymological phenomena that may contribute to the creation of a continuum between existing and future lexical constructs, where anyone interested in tracing the history of words and their meanings will be able to seamlessly query lexical resources.Instead of designing an ad hoc model and representation language for digital etymological data, we will focus on identifying all the possibilities offered by the TEI guidelines for the representation of lexical information.

cs.CL↗