Text anomaly detection (TAD) is a crucial task that aims to identify texts that deviate significantly from the norm within a corpus. Despite its importance in various domains, TAD remains relatively underexplored in natural language processing. This article presents a systematic evaluation of 22 TAD algorithms on 17 corpora using multiple text representations, including monolingual and multilingual SBERT. The performance of the algorithms is compared based on three criteria: degree of supervision, theoretical basis, and architecture used. The results demonstrate that semi-supervised methods utilizing weak labels outperform both unsupervised methods and semi-supervised methods using only negative samples for training. Additionally, we explore the application of TAD techniques in hate speech detection. The results provide valuable insights for future TAD research and guide the selection of suitable algorithms for detecting text anomalies in different contexts.

This paper presents an information-theoretical model of syntactic generalization. We study syntactic generalization from the perspective of the capacity to disentangle semantic and structural information, emulating the human capacity to assign a grammaticality judgment to semantically nonsensical sentences. In order to isolate the structure, we propose to represent the probability distribution behind a corpus as the product of the probability of a semantic context and the probability of a structure, the latter being independent of the former. We further elaborate the notion of abstraction as a relaxation of the property of independence. It is based on the measure of structural and contextual information for a given representation. We test abstraction as an optimization objective on the task of inducing syntactic categories from natural language data and show that it significantly outperforms alternative methods. Furthermore, we find that when syntax-unaware optimization objectives succeed in the task, their success is mainly due to an implicit disentanglement process rather than to the model structure. On the other hand, syntactic categories can be deduced in a principled way from the independence between structure and context.

La détection d’anomalies textuelles est une tâche importante de la fouille de textes. Plusieurs approches générales, visant l’identification de points de données aberrants, ont été appliqués dans ce domaine. Néanmoins, ces approches exploitent peu les nouvelles avancées du traitement automatique des langues naturelles (TALN). L’avènement des modèles de langage pré-entraînés comme BERT et GPT-2 a donné naissance à un nouveau paradigme de l’apprentissage automatique appelé ingénierie d’invite (prompt engineering) qui a montré de bonnes performances sur plusieurs tâches du TALN. Cet article présente un travail exploratoire visant à examiner la possibilité de détecter des anomalies textuelles à l’aide de l’ingénierie d’invite. Dans nos expérimentations, nous avons examiné la performance de différents modèles d’invite. Les résultats ont montré que l’ingénierie d’invite est une méthode prometteuse pour la détection d’anomalies textuelles.

This paper is a theoretical contribution to the debate on the learnability of syntax from a corpus without explicit syntax-specific guidance. Our approach originates in the observable structure of a corpus, which we use to define and isolate grammaticality (syntactic information) and meaning/pragmatics information. We describe the formal characteristics of an autonomous syntax and show that it becomes possible to search for syntax-based lexical categories with a simple optimization process, without any prior hypothesis on the form of the model.

This paper describes the first task on semantic relation extraction and classification in scientific paper abstracts at SemEval 2018. The challenge focuses on domain-specific semantic relations and includes three different subtasks. The subtasks were designed so as to compare and quantify the effect of different pre-processing steps on the relation classification results. We expect the task to be relevant for a broad range of researchers working on extracting specialized knowledge from domain corpora, for example but not limited to scientific or bio-medical information extraction. The task attracted a total of 32 participants, with 158 submissions across different scenarios.

Word embeddings are used with success for a variety of tasks involving lexical semantic similarities between individual words. Using unsupervised methods and just cosine similarity, encouraging results were obtained for analogical similarities. In this paper, we explore the potential of pre-trained word embeddings to identify generic types of semantic relations in an unsupervised experiment. We propose a new relational similarity measure based on the combination of word2vec’s CBOW input and output vectors which outperforms concurrent vector representations, when used for unsupervised clustering on SemEval 2010 Relation Classification data.

This paper describes the process of creating a corpus annotated for concepts and semantic relations in the scientific domain. A part of the ACL Anthology Corpus was selected for annotation, but the annotation process itself is not specific to the computational linguistics domain and could be applied to any scientific corpora. Concepts were identified and annotated fully automatically, based on a combination of terminology extraction and available ontological resources. A typology of semantic relations between concepts is also proposed. This typology, consisting of 18 domain-specific and 3 generic relations, is the result of a corpus-based investigation of the text sequences occurring between concepts in sentences. A sample of 500 abstracts from the corpus is currently being manually annotated with these semantic relations. Only explicit relations are taken into account, so that the data could serve to train or evaluate pattern-based semantic relation classification systems.

Dans cet article, nous abordons une tâche encore peu explorée, consistant à extraire automatiquement l’état de l’art d’un domaine scientifique à partir de l’analyse d’articles de ce domaine. Nous la ramenons à deux sous-tâches élémentaires : l’identification de concepts et la reconnaissance de relations entre ces concepts. Une extraction terminologique permet d’identifier les concepts candidats, qui sont ensuite alignés à des ressources externes. Dans un deuxième temps, nous cherchons à reconnaître et classifier automatiquement les relations sémantiques entre concepts de manière nonsupervisée, en nous appuyant sur différentes techniques de clustering et de biclustering. Nous mettons en œuvre ces deux étapes dans un corpus extrait de l’archive de l’ACL Anthology. Une analyse manuelle nous a permis de proposer une typologie des relations sémantiques, et de classifier un échantillon d’instances de relations. Les premières évaluations suggèrent l’intérêt du biclustering pour détecter de nouveaux types de relations dans le corpus.

In this article, we present a distributional analysis method for extracting nominalization relations from monolingual corpora. The acquisition method makes use of distributional and morphological information to select nominalization candidates. We explain how the learning is performed on a dependency annotated corpus and describe the nominalization results. Furthermore, we show how these results served to enrich an existing lexical resource, the WOLF (Wordnet Libre du Franc¸ais). We present the techniques that we developed in order to integrate the new information into WOLF, based on both its structure and content. Finally, we evaluate the validity of the automatically obtained information and the correctness of its integration into the semantic resource. The method proved to be useful for boosting the coverage of WOLF and presents the advantage of filling verbal synsets, which are particularly difficult to handle due to the high level of verbal polysemy.