This paper summarizes the joint participation of the Trading Central Labs and the L3i laboratory of the University of La Rochelle on both sub-tasks of the Shared Task FinSim-4 evaluation campaign. The first sub-task aims to enrich the ‘Fortia ESG taxonomy’ with new lexicon entries while the second one aims to classify sentences to either ‘sustainable’ or ‘unsustainable’ with respect to ESG (Environment, Social and Governance) related factors. For the first sub-task, we proposed a model based on pre-trained Sentence-BERT models to project sentences and concepts in a common space in order to better represent ESG concepts. The official task results show that our system yields a significant performance improvement compared to the baseline and outperforms all other submissions on the first sub-task. For the second sub-task, we combine the RoBERTa model with a feed-forward multi-layer perceptron in order to extract the context of sentences and classify them. Our model achieved high accuracy scores (over 92%) and was ranked among the top 5 systems.

Dans cet article, nous abordons un paradigme récent et peu étudié pour la tâche de détection d’événements en la présentant comme un problème de question-réponse avec possibilité de réponses multiples et le support d’entités. La tâche d’extraction des déclencheurs d’événements est ainsi transformée en une tâche d’identification des intervalles de réponse à partir d’un contexte, tout en se concentrant également sur les entités environnantes. L’architecture est basée sur un modèle de langage pré-entraîné et finement ajusté, où le contexte d’entrée est augmenté d’entités marquées à différents niveaux, de leurs positions, de leurs types et, enfin, de leurs rôles d’arguments. Nos expériences sur le corpus ACE 2005 démontrent que le modèle proposé exploite correctement les informations sur les entités dans le cadre de la détection des événements et qu’il constitue une solution viable pour cette tâche. De plus, nous démontrons que notre méthode, avec différents marqueurs d’entités, est particulièrement capable d’extraire des types d’événements non vus dans des contextes d’apprentissage en peu de coups.

Dans le contexte général des traitements multimodaux, nous nous intéressons à la tâche de réponse à des questions visuelles à propos d’entités nommées en utilisant des bases de connaissances (KVQAE). Nous mettons à disposition ViQuAE, un nouveau jeu de données de 3 700 questions associées à des images, annoté à l’aide d’une méthode semi-automatique. C’est le premier jeu de données de KVQAE comprenant des types d’entités variés associé à une base de connaissances composée d’1,5 million d’articles Wikipédia, incluant textes et images. Nous proposons également un modèle de référence de KVQAE en deux étapes : recherche d’information puis extraction des réponses. Les résultats de nos expériences démontrent empiriquement la difficulté de la tâche et ouvrent la voie à une meilleure représentation multimodale des entités nommées.

Recent years have witnessed a growing interest towards learning distributed query representations that are able to capture search intent semantics. Most existing approaches learn query embeddings using relevance supervision making them suited only to document ranking tasks. Besides, they generally consider either user’s query reformulations or system’s rankings whereas previous findings show that user’s query behavior and knowledge change depending on the system’s results, intertwine and affect each other during the completion of a search task. In this paper, we explore the value of multi-view learning for generic and unsupervised session-aware query representation learning. First, single-view query embeddings are obtained in separate spaces from query reformulations and document ranking representations using transformers. Then, we investigate the use of linear (CCA) and non linear (UMAP) multi-view learning methods, to align those spaces with the aim of revealing similarity traits in the multi-view shared space. Experimental evaluation is carried out in a query classification and session-based retrieval downstream tasks using respectively the KDD and TREC session datasets. The results show that multi-view learning is an effective and controllable approach for unsupervised learning of generic query representations and can reflect search behavior patterns.

This paper summarizes the participation of the L3i laboratory of the University of La Rochelle in the SemEval-2022 Task 11, Multilingual Complex Named Entity Recognition (MultiCoNER). The task focuses on detecting semantically ambiguous and complex entities in short and low-context monolingual and multilingual settings. We argue that using a language-specific and a multilingual language model could improve the performance of multilingual and mixed NER. Also, we consider that using additional contexts from the training set could improve the performance of a NER on short texts. Thus, we propose a straightforward technique for generating additional contexts with and without the presence of entities. Our findings suggest that, in our internal experimental setup, this approach is promising. However, we ranked above average for the high-resource languages and lower than average for low-resource and multilingual models.

Despite the success of state-of-the-art pre-trained language models (PLMs) on a series of multi-hop reasoning tasks, they still suffer from their limited abilities to transfer learning from simple to complex tasks and vice-versa. We argue that one step forward to overcome this limitation is to better understand the behavioral trend of PLMs at each hop over the inference chain. Our critical underlying idea is to mimic human-style reasoning: we envision the multi-hop reasoning process as a sequence of explicit single-hop reasoning steps. To endow PLMs with incremental reasoning skills, we propose a set of inference strategies on relevant facts and distractors allowing us to build automatically generated training datasets. Using the SHINRA and ConceptNet resources jointly, we empirically show the effectiveness of our proposal on multiple-choice question answering and reading comprehension, with a relative improvement in terms of accuracy of 68.4% and 16.0% w.r.t. classic PLMs, respectively.

This paper presents tools and data sources collected and released by the EMBEDDIA project, supported by the European Union’s Horizon 2020 research and innovation program. The collected resources were offered to participants of a hackathon organized as part of the EACL Hackashop on News Media Content Analysis and Automated Report Generation in February 2021. The hackathon had six participating teams who addressed different challenges, either from the list of proposed challenges or their own news-industry-related tasks. This paper goes beyond the scope of the hackathon, as it brings together in a coherent and compact form most of the resources developed, collected and released by the EMBEDDIA project. Moreover, it constitutes a handy source for news media industry and researchers in the fields of Natural Language Processing and Social Science.

We present a collection of Named Entity Recognition (NER) systems for six Slavic languages: Bulgarian, Czech, Polish, Slovenian, Russian and Ukrainian. These NER systems have been trained using different BERT models and a Frustratingly Easy Domain Adaptation (FEDA). FEDA allow us creating NER systems using multiple datasets without having to worry about whether the tagset (e.g. Location, Event, Miscellaneous, Time) in the source and target domains match, while increasing the amount of data available for training. Moreover, we boosted the prediction on named entities by marking uppercase words and predicting masked words. Participating in the 3rd Shared Task on SlavNER, our NER systems reached a strict match micro F-score of up to 0.908. The results demonstrate good generalization, even in named entities with weak regularity, such as book titles, or entities that were never seen during the training.

Nous proposons une idée originale pour exploiter les relations entre les classes dans les problèmes multiclasses. Nous définissons deux architectures multitâches de type one-vs-rest qui combinent des ensembles de classifieurs appris dans une configuration multitâche en utilisant des réseaux de neurones. Les expériences menées sur six jeux de données pour la classification des sentiments, des émotions, des thématiques et des relations lexico-sémantiques montrent que nos architectures améliorent constamment les performances par rapport aux stratégies de l’état de l’art de type one-vsrest et concurrencent fortement les autres stratégies multiclasses.

This paper tackles the task of named entity recognition (NER) applied to digitized historical texts obtained from processing digital images of newspapers using optical character recognition (OCR) techniques. We argue that the main challenge for this task is that the OCR process leads to misspellings and linguistic errors in the output text. Moreover, historical variations can be present in aged documents, which can impact the performance of the NER process. We conduct a comparative evaluation on two historical datasets in German and French against previous state-of-the-art models, and we propose a model based on a hierarchical stack of Transformers to approach the NER task for historical data. Our findings show that the proposed model clearly improves the results on both historical datasets, and does not degrade the results for modern datasets.

Knowledge bases are increasingly exploited as gold standard data sources which benefit various knowledge-driven NLP tasks. In this paper, we explore a new research direction to perform knowledge base (KB) representation learning grounded with the recent theoretical framework of knowledge distillation over neural networks. Given a set of KBs, our proposed approach KD-MKB, learns KB embeddings by mutually and jointly distilling knowledge within a dynamic teacher-student setting. Experimental results on two standard datasets show that knowledge distillation between KBs through entity and relation inference is actually observed. We also show that cooperative learning significantly outperforms the two proposed baselines, namely traditional and sequential distillation.

This paper presents our participation at the shared task on multilingual named entity recognition at BSNLP2019. Our strategy is based on a standard neural architecture for sequence labeling. In particular, we use a mixed model which combines multilingualcontextual and language-specific embeddings. Our only submitted run is based on a voting schema using multiple models, one for each of the four languages of the task (Bulgarian, Czech, Polish, and Russian) and another for English. Results for named entity recognition are encouraging for all languages, varying from 60% to 83% in terms of Strict and Relaxed metrics, respectively.

This paper describes the Rouletabille participation to the Hyperpartisan News Detection task. We propose the use of different text classification methods for this task. Preliminary experiments using a similar collection used in (Potthast et al., 2018) show that neural-based classification methods reach state-of-the art results. Our final submission is composed of a unique run that ranks among all runs at 3/49 position for the by-publisher test dataset and 43/96 for the by-article test dataset in terms of Accuracy.

La désambiguïsation d’entités (ou liaison d’entités), qui consiste à relier des mentions d’entités d’un texte à des entités d’une base de connaissance, est un problème qui se pose, entre autre, pour le peuplement automatique de bases de connaissances à partir de textes. Une difficulté de cette tâche est la résolution d’ambiguïtés car les systèmes ont à choisir parmi un nombre important de candidats. Cet article propose une nouvelle approche fondée sur l’apprentissage joint de représentations distribuées des mots et des entités dans le même espace, ce qui permet d’établir un modèle robuste pour la comparaison entre le contexte local de la mention d’entité et les entités candidates.