The automatic extraction of character networks from literary texts is generally carried out using natural language processing (NLP) cascading pipelines. While this approach is widespread, no study exists on the impact of low-level NLP tasks on their performance. In this article, we conduct such a study on a literary dataset, focusing on the role of named entity recognition (NER) and coreference resolution when extracting co-occurrence networks. To highlight the impact of these tasks’ performance, we start with gold-standard annotations, progressively add uniformly distributed errors, and observe their impact in terms of character network quality. We demonstrate that NER performance depends on the tested novel and strongly affects character detection. We also show that NER-detected mentions alone miss a lot of character co-occurrences, and that coreference resolution is needed to prevent this. Finally, we present comparison points with 2 methods based on large language models (LLMs), including a fully end-to-end one, and show that these models are outperformed by traditional NLP pipelines in terms of recall.

Pre-trained transformer-based models have recently shown great performance when applied to Named Entity Recognition (NER). As the complexity of their self-attention mechanism prevents them from processing long documents at once, these models are usually applied in a sequential fashion. Such an approach unfortunately only incorporates local context and prevents leveraging global document context in long documents such as novels, which might hinder performance. In this article, we explore the impact of global document context, and its relationships with local context. We find that correctly retrieving global document context has a greater impact on performance than only leveraging local context, prompting for further research on how to better retrieve that context.

While recent pre-trained transformer-based models can perform named entity recognition (NER) with great accuracy, their limited range remains an issue when applied to long documents such as whole novels. To alleviate this issue, a solution is to retrieve relevant context at the document level. Unfortunately, the lack of supervision for such a task means one has to settle for unsupervised approaches. Instead, we propose to generate a synthetic context retrieval training dataset using Alpaca, an instruction-tuned large language model (LLM). Using this dataset, we train a neural context retriever based on a BERT model that is able to find relevant context for NER. We show that our method outperforms several retrieval baselines for the NER task on an English literary dataset composed of the first chapter of 40 books.

La reconnaissance d’entités nommées est une tâche de traitement automatique du langage naturel bien étudiée et utile dans de nombreuses applications. Dernièrement, les modèles neuronaux permettent de la résoudre avec de très bonnes performances. Cependant, les jeux de données permettant l’entraînement et l’évaluation de ces modèles se concentrent sur un nombre restreint de domaines et types de documents (articles journalistiques, internet). Or, les performances d’un modèle entraîné sur un domaine ciblé sont en général moindres dans un autre : ceux moins couverts sont donc pénalisés. Pour tenter de remédier à ce problème, cet article propose d’utiliser une technique d’augmentation de données permettant d’adapter un corpus annoté en entités nommées d’un domaine source à un domaine cible où les types de noms rencontrés peuvent être différents. Nous l’appliquons dans le cadre de la littérature de fantasy, où nous montrons qu’elle peut apporter des gains de performance.