Discourse segmentation, the first step of discourse analysis, has been shown to improve results for text summarization, translation and other NLP tasks. While segmentation models for written text tend to perform well, they are not directly applicable to spontaneous, oral conversation, which has linguistic features foreign to written text. Segmentation is less studied for this type of language, where annotated data is scarce, and existing corpora more heterogeneous. We develop a weak supervision approach to adapt, using minimal annotation, a state of the art discourse segmenter trained on written text to French conversation transcripts. Supervision is given by a latent model bootstrapped by manually defined heuristic rules that use linguistic and acoustic information. The resulting model improves the original segmenter, especially in contexts where information on speaker turns is lacking or noisy, gaining up to 13% in F-score. Evaluation is performed on data like those used to define our heuristic rules, but also on transcripts from two other corpora.

Various research works have dealt with the comprehensibility of textual, audio, or audiovisual documents, and showed that factors related to text (e.g. linguistic complexity), sound (e.g. speech intelligibility), image (e.g. presence of visual context), or even to cognition and emotion can play a major role in the ability of humans to understand the semantic and pragmatic contents of a given document. However, to date, no reference human data is available that could help investigating the role of the linguistic and extralinguistic information present at these different levels (i.e., linguistic, audio/phonetic, and visual) in multimodal documents (e.g., movies). The present work aimed at building a corpus of human annotations that would help to study further how much and in which way the human perception of comprehensibility (i.e., of the difficulty of comprehension, referred in this paper as overall difficulty) of audiovisual documents is affected (1) by lexical complexity, grammatical complexity, and speech intelligibility, and (2) by the modality/ies (text, audio, video) available to the human recipient.

La compréhensibilité de documents audiovisuels peut dépendre de facteurs propres à l’auditeur/spectateur (ex. langue maternelle, performances cognitives) et de facteurs propres aux contenus des documents (ex. complexité linguistique, intelligibilité de la parole). Dans ces travaux, nous étudions les effets de facteurs propres aux contenus sur la compréhensibilité de 55 dialogues extraits de films, présentés à 15 experts (enseignants de français langue étrangère) selon cinq modalités différentes (transcription, transcription + audio, audio, audio + vidéo, transcription + audio + vidéo). Les experts ont évalué les dialogues en termes de compréhensibilité générale, de complexité du vocabulaire, de complexité grammaticale, et d’intelligibilité de la parole. L’analyse de leurs évaluations montre que (1) la complexité du vocabulaire, la complexité grammaticale, et l’intelligibilité de la parole sont significativement corrélées à la compréhensibilité générale, et (2) que les évaluations de compréhensibilité générale ont tendance à être plus élevées lors de présentations multimodales.