Providing example sentences that are diverse and aligned with learners’ proficiency levels is essential for fostering effective language acquisition.This study examines the use of Pre-trained Language Models (PLMs) to produce example sentences targeting L2 Japanese learners.We utilize PLMs in two ways: as quality scoring components in a retrieval system that draws from a newly curated corpus of Japanese sentences, and as direct sentence generators using zero-shot learning.We evaluate the quality of sentences by considering multiple aspects such as difficulty, diversity, and naturalness, with a panel of raters consisting of learners of Japanese, native speakers – and GPT-4.Our findings suggest that there is inherent disagreement among participants on the ratings of sentence qualities, except for difficulty. Despite that, the retrieval approach was preferred by all evaluators, especially for beginner and advanced target proficiency, while the generative approaches received lower scores on average.Even so, our experiments highlight the potential for using PLMs to enhance the adaptability of sentence suggestion systems and therefore improve the language learning journey.
Writing a scientific article is a challenging task as it is a highly codified and specific genre, consequently proficiency in written communication is essential for effectively conveying research findings and ideas. In this article, we propose an original textual resource on the revision step of the writing process of scientific articles. This new dataset, called CASIMIR, contains the multiple revised versions of 15,646 scientific articles from OpenReview, along with their peer reviews. Pairs of consecutive versions of an article are aligned at sentence-level while keeping paragraph location information as metadata for supporting future revision studies at the discourse level. Each pair of revised sentences is enriched with automatically extracted edits and associated revision intention. To assess the initial quality on the dataset, we conducted a qualitative study of several state-of-the-art text revision approaches and compared various evaluation metrics. Our experiments led us to question the relevance of the current evaluation methods for the text revision task.
Cet article présente le projet NaviTerm dont l’objectif est d’accélérer la montée en compétence des chercheurs sur un domaine de recherche par la création automatique de représentations terminologiques synthétiques et navigables des connaissances scientifiques.
Les modèles encodeur-décodeur constituent l’état de l’art en génération de mots-clés. Cependant, malgré de nombreuses adaptations de cette architecture, générer des mots-clés absents du texte du document est toujours une tâche difficile. Cette étude montre qu’entraîner au préalable un modèle sur une tâche de classification de relation entre un document et un mot-clé, permet d’améliorer la génération de mots-clés absents.
Écrire un article scientifique est une tâche difficile. L’écriture scientifique étant un genre très codifié, de bonnes compétences d’écriture sont essentielles pour transmettre ses idées et les résultats de ses recherches. Cet article décrit les motivations et les travaux préliminaires de la création du corpus CASIMIR dont l’objectif est d’offrir une ressource sur l’étape de révision du processus d’écriture d’un article scientifique. CASIMIR est un corpus des multiples versions de 26 355 articles scientifiques provenant d’OpenReview accompagné des relectures par les pairs.
Automatic Term Extraction (ATE) is a key component for domain knowledge understanding and an important basis for further natural language processing applications. Even with persistent improvements, ATE still exhibits weak results exacerbated by small training data inherent to specialized domain corpora. Recently, transformers-based deep neural models, such as BERT, have proven to be efficient in many downstream NLP tasks. However, no systematic evaluation of ATE has been conducted so far. In this paper, we run an extensive study on fine-tuning pre-trained BERT models for ATE. We propose strategies that empirically show BERT’s effectiveness using cross-lingual and cross-domain transfer learning to extract single and multi-word terms. Experiments have been conducted on four specialized domains in three languages. The obtained results suggest that BERT can capture cross-domain and cross-lingual terminologically-marked contexts shared by terms, opening a new design-pattern for ATE.
Keyphrase generation is the task consisting in generating a set of words or phrases that highlight the main topics of a document. There are few datasets for keyphrase generation in the biomedical domain and they do not meet the expectations in terms of size for training generative models. In this paper, we introduce kp-biomed, the first large-scale biomedical keyphrase generation dataset collected from PubMed abstracts. We train and release several generative models and conduct a series of experiments showing that using large scale datasets improves significantly the performances for present and absent keyphrase generation. The dataset and models are available online.
Neural keyphrase generation models have recently attracted much interest due to their ability to output absent keyphrases, that is, keyphrases that do not appear in the source text. In this paper, we discuss the usefulness of absent keyphrases from an Information Retrieval (IR) perspective, and show that the commonly drawn distinction between present and absent keyphrases is not made explicit enough. We introduce a finer-grained categorization scheme that sheds more light on the impact of absent keyphrases on scientific document retrieval. Under this scheme, we find that only a fraction (around 20%) of the words that make up keyphrases actually serves as document expansion, but that this small fraction of words is behind much of the gains observed in retrieval effectiveness. We also discuss how the proposed scheme can offer a new angle to evaluate the output of neural keyphrase generation models.
Automatic terminology extraction is a notoriously difficult task aiming to ease effort demanded to manually identify terms in domain-specific corpora by automatically providing a ranked list of candidate terms. The main ways that addressed this task can be ranged in four main categories: (i) rule-based approaches, (ii) feature-based approaches, (iii) context-based approaches, and (iv) hybrid approaches. For this first TermEval shared task, we explore a feature-based approach, and a deep neural network multitask approach -BERT- that we fine-tune for term extraction. We show that BERT models (RoBERTa for English and CamemBERT for French) outperform other systems for French and English languages.
Formulaic expressions, such as ‘in this paper we propose’, are used by authors of scholarly papers to perform communicative functions; the communicative function of the present example is ‘stating the aim of the paper’. Collecting such expressions and pairing them with their communicative functions would be highly valuable for various tasks, particularly for writing assistance. However, such collection and paring in a principled and automated manner would require high-quality annotated data, which are not available. In this study, we address this shortcoming by creating a manually annotated dataset for detecting communicative functions in sentences. Starting from a seed list of labelled formulaic expressions, we retrieved new sentences from scholarly papers in the ACL Anthology and asked multiple human evaluators to label communicative functions. To show the usefulness of our dataset, we conducted a series of experiments that determined to what extent sentence representations acquired by recent models, such as word2vec and BERT, can be employed to detect communicative functions in sentences.
Sequence-to-sequence models have lead to significant progress in keyphrase generation, but it remains unknown whether they are reliable enough to be beneficial for document retrieval. This study provides empirical evidence that such models can significantly improve retrieval performance, and introduces a new extrinsic evaluation framework that allows for a better understanding of the limitations of keyphrase generation models. Using this framework, we point out and discuss the difficulties encountered with supplementing documents with -not present in text- keyphrases, and generalizing models across domains. Our code is available at https://github.com/boudinfl/ir-using-kg
Nous présentons dans cet article la participation de l’équipe TALN du LS2N à la tâche d’indexation de cas cliniques (tâche 1). Nous proposons deux systèmes permettant d’identifier, dans la liste de mots-clés fournie, les mots-clés correspondant à un couple cas clinique/discussion, ainsi qu’un classifieur entraîné sur la combinaison des sorties des deux systèmes. Nous présenterons dans le détail les descripteurs utilisés pour représenter les mots-clés ainsi que leur impact sur nos systèmes de classification.
Keyphrase generation is the task of predicting a set of lexical units that conveys the main content of a source text. Existing datasets for keyphrase generation are only readily available for the scholarly domain and include non-expert annotations. In this paper we present KPTimes, a large-scale dataset of news texts paired with editor-curated keyphrases. Exploring the dataset, we show how editors tag documents, and how their annotations differ from those found in existing datasets. We also train and evaluate state-of-the-art neural keyphrase generation models on KPTimes to gain insights on how well they perform on the news domain. The dataset is available online at https://github.com/ygorg/KPTimes.
We propose an unsupervised keyphrase extraction model that encodes topical information within a multipartite graph structure. Our model represents keyphrase candidates and topics in a single graph and exploits their mutually reinforcing relationship to improve candidate ranking. We further introduce a novel mechanism to incorporate keyphrase selection preferences into the model. Experiments conducted on three widely used datasets show significant improvements over state-of-the-art graph-based models.
Dans cet article, nous nous intéressons à l’indexation de documents de domaines de spécialité par l’intermédiaire de leurs termes-clés. Plus particulièrement, nous nous intéressons à l’indexation telle qu’elle est réalisée par les documentalistes de bibliothèques numériques. Après analyse de la méthodologie de ces indexeurs professionnels, nous proposons une méthode à base de graphe combinant les informations présentes dans le document et la connaissance du domaine pour réaliser une indexation (hybride) libre et contrôlée. Notre méthode permet de proposer des termes-clés ne se trouvant pas nécessairement dans le document. Nos expériences montrent aussi que notre méthode surpasse significativement l’approche à base de graphe état de l’art.
The SemEval-2010 benchmark dataset has brought renewed attention to the task of automatic keyphrase extraction. This dataset is made up of scientific articles that were automatically converted from PDF format to plain text and thus require careful preprocessing so that irrevelant spans of text do not negatively affect keyphrase extraction performance. In previous work, a wide range of document preprocessing techniques were described but their impact on the overall performance of keyphrase extraction models is still unexplored. Here, we re-assess the performance of several keyphrase extraction models and measure their robustness against increasingly sophisticated levels of document preprocessing.
Keyphrase extraction is the task of finding phrases that represent the important content of a document. The main aim of keyphrase extraction is to propose textual units that represent the most important topics developed in a document. The output keyphrases of automatic keyphrase extraction methods for test documents are typically evaluated by comparing them to manually assigned reference keyphrases. Each output keyphrase is considered correct if it matches one of the reference keyphrases. However, the choice of the appropriate textual unit (keyphrase) for a topic is sometimes subjective and evaluating by exact matching underestimates the performance. This paper presents a dataset of evaluation scores assigned to automatically extracted keyphrases by human evaluators. Along with the reference keyphrases, the manual evaluations can be used to validate new evaluation measures. Indeed, an evaluation measure that is highly correlated to the manual evaluation is appropriate for the evaluation of automatic keyphrase extraction methods.
Keyphrase annotation is the task of identifying textual units that represent the main content of a document. Keyphrase annotation is either carried out by extracting the most important phrases from a document, keyphrase extraction, or by assigning entries from a controlled domain-specific vocabulary, keyphrase assignment. Assignment methods are generally more reliable. They provide better-formed keyphrases, as well as keyphrases that do not occur in the document. But they are often silent on the contrary of extraction methods that do not depend on manually built resources. This paper proposes a new method to perform both keyphrase extraction and keyphrase assignment in an integrated and mutual reinforcing manner. Experiments have been carried out on datasets covering different domains of humanities and social sciences. They show statistically significant improvements compared to both keyphrase extraction and keyphrase assignment state-of-the art methods.
We describe pke, an open source python-based keyphrase extraction toolkit. It provides an end-to-end keyphrase extraction pipeline in which each component can be easily modified or extented to develop new approaches. pke also allows for easy benchmarking of state-of-the-art keyphrase extraction approaches, and ships with supervised models trained on the SemEval-2010 dataset.
Le résumé automatique cross-lingue consiste à générer un résumé rédigé dans une langue différente de celle utilisée dans les documents sources. Dans cet article, nous proposons une approche de résumé automatique multi-document, basée sur une représentation par graphe, qui prend en compte des scores de qualité de traduction lors du processus de sélection des phrases. Nous évaluons notre méthode sur un sous-ensemble manuellement traduit des données utilisées lors de la campagne d’évaluation internationale DUC 2004. Les résultats expérimentaux indiquent que notre approche permet d’améliorer la lisibilité des résumés générés, sans pour autant dégrader leur informativité.
Le résumé automatique de texte est une problématique difficile, fortement dépendante de la langue et qui peut nécessiter un ensemble de données d’apprentissage conséquent. L’approche par extraction peut aider à surmonter ces difficultés. (Mihalcea, 2004) a démontré l’intérêt des approches à base de graphes pour l’extraction de segments de texte importants. Dans cette étude, nous décrivons une approche indépendante de la langue pour la problématique du résumé automatique multi-documents. L’originalité de notre méthode repose sur l’utilisation d’une mesure de similarité permettant le rapprochement de segments morphologiquement proches. De plus, c’est à notre connaissance la première fois que l’évaluation d’une approche de résumé automatique multi-document est conduite sur des textes en français.