This is an internal, incomplete preview of a proposed change to the ACL Anthology.
For efficiency reasons, we don't generate MODS or Endnote formats, and the preview may be incomplete in other ways, or contain mistakes.
Do not treat this content as an official publication.
MariameMaarouf
Fixing paper assignments
Please select all papers that belong to the same person.
Indicate below which author they should be assigned to.
This study explores the automatic normalization of noisy and highly technical anomaly reports by an LLM. Different prompts are tested to instruct the LLM to clean the text without changing the structure, vocabulary or specialized lexicon. The evaluation of this task is made in two steps. First, the Character Error Rate (CER) is calculated to assess the changes made compared to a gold standard on a small sample. Second, an automatic sequence labeling task is performed on the original and on the corrected datasets with a transformer-based classifier. If some configurations of LLM and prompts can reach satisfying CER scores, the sequence labeling task shows that the normalization has a small negative impact on performance.
This paper describes the development of a chunker for spoken data by supervised machine learning using the CRFs, based on a small reference corpus composed of two kinds of discourse: prepared monologue vs. spontaneous talk in interaction. The methodology considers the specific character of the spoken data. The machine learning uses the results of several available taggers, without correcting the results manually. Experiments show that the discourse type (monologue vs. free talk), the speech nature (spontaneous vs. prepared) and the corpus size can influence the results of the machine learning process and must be considered while interpreting the results.
Le travail décrit le développement d’un chunker pour l’oral par apprentissage supervisé avec les CRFs, à partir d’un corpus de référence de petite taille et composé de productions de nature différente : monologue préparé vs discussion spontanée. La méthodologie respecte les spécificités des données traitées. L’apprentissage tient compte des résultats proposés par différents étiqueteurs morpho-syntaxiques disponibles sans correction manuelle de leurs résultats. Les expériences montrent que le genre de discours (monologue vs discussion), la nature de discours (spontané vs préparé) et la taille du corpus peuvent influencer les résultats de l’apprentissage, ce qui confirme que la nature des données traitées est à prendre en considération dans l’interprétation des résultats.