Discourse segmentation received increased attention in the past years, however the majority of studies have focused on written genres and with high-resource languages. This paper investigates discourse segmentation of a Taiwan Southern Min spontaneous speech corpus. We compare the fine-tuning a Language Model (LLM using two approaches: supervised, thanks to a high-quality annotated dataset, and weakly-supervised, requiring only a small amount of manual labeling. The corpus used here is transcribed with both Chinese characters and romanized transcription. This allows us to compare the impact of the written form on the discourse segmentation task. Additionally, the dataset includes manual prosodic breaks labeling, allowing an exploration of the role prosody can play in contemporary discourse segmentation systems grounded in LLMs. In our study, the supervised approach outperforms weak-supervision ; character-based version demonstrated better scores compared to the romanized version; and prosodic information proved to be an interesting source to increase discourse segmentation performance.

While discourse parsing has made considerable progress in recent years, discourse segmentation of conversational speech remains a difficult issue. In this paper, we exploit a French data set that has been manually segmented into discourse units to compare two approaches to discourse segmentation: fine-tuning existing systems on manual segmentation vs. using hand-crafted labelling rules to develop a weakly supervised segmenter. Our results show that both approaches yield similar performance in terms of f-score while data programming requires less manual annotation work. In a second experiment we play with the amount of training data used for fine-tuning systems and show that a small amount of hand labelled data is enough to obtain good results (although significantly lower than in the first experiment using all the annotated data available).

We present the second shared task on eye-tracking data prediction of the Cognitive Modeling and Computational Linguistics Workshop (CMCL). Differently from the previous edition, participating teams are asked to predict eye-tracking features from multiple languages, including a surprise language for which there were no available training data. Moreover, the task also included the prediction of standard deviations of feature values in order to account for individual differences between readers.A total of six teams registered to the task. For the first subtask on multilingual prediction, the winning team proposed a regression model based on lexical features, while for the second subtask on cross-lingual prediction, the winning team used a hybrid model based on a multilingual transformer embeddings as well as statistical features.

Eye-tracking data from reading represent an important resource for both linguistics and natural language processing. The ability to accurately model gaze features is crucial to advance our understanding of language processing. This paper describes the Shared Task on Eye-Tracking Data Prediction, jointly organized with the eleventh edition of the Work- shop on Cognitive Modeling and Computational Linguistics (CMCL 2021). The goal of the task is to predict 5 different token- level eye-tracking metrics of the Zurich Cognitive Language Processing Corpus (ZuCo). Eye-tracking data were recorded during natural reading of English sentences. In total, we received submissions from 13 registered teams, whose systems include boosting algorithms with handcrafted features, neural models leveraging transformer language models, or hybrid approaches. The winning system used a range of linguistic and psychometric features in a gradient boosting framework.

ISO standard 24617-2 for dialogue act annotation, established in 2012, has in the past few years been used both in corpus annotation and in the design of components for spoken and multimodal dialogue systems. This has brought some inaccuracies and undesirbale limitations of the standard to light, which are addressed in a proposed second edition. This second edition allows a more accurate annotation of dependence relations and rhetorical relations in dialogue. Following the ISO 24617-4 principles of semantic annotation, and borrowing ideas from EmotionML, a triple-layered plug-in mechanism is introduced which allows dialogue act descriptions to be enriched with information about their semantic content, about accompanying emotions, and other information, and allows the annotation scheme to be customised by adding application-specific dialogue act types.

In this paper we present investigation of real-life, bi-directional conversations. We introduce the multimodal corpus derived from these natural conversations alternating between human-human and human-robot interactions. The human-robot interactions were used as a control condition for the social nature of the human-human conversations. The experimental set up consisted of conversations between the participant in a functional magnetic resonance imaging (fMRI) scanner and a human confederate or conversational robot outside the scanner room, connected via bidirectional audio and unidirectional videoconferencing (from the outside to inside the scanner). A cover story provided a framework for natural, real-life conversations about images of an advertisement campaign. During the conversations we collected a multimodal corpus for a comprehensive characterization of bi-directional conversations. In this paper we introduce this multimodal corpus which includes neural data from functional magnetic resonance imaging (fMRI), physiological data (blood flow pulse and respiration), transcribed conversational data, as well as face and eye-tracking recordings. Thus, we present a unique corpus to study human conversations including neural, physiological and behavioral data.

In this paper, we present a tool allowing dynamic prediction and visualization of an individual’s local brain activity during a conversation. The prediction module of this tool is based on classifiers trained using a corpus of human-human and human-robot conversations including fMRI recordings. More precisely, the module takes as input behavioral features computed from raw data, mainly the participant and the interlocutor speech but also the participant’s visual input and eye movements. The visualisation module shows in real-time the dynamics of brain active areas synchronised with the behavioral raw data. In addition, it shows which integrated behavioral features are used to predict the activity in individual brain areas.

Cognitive models of conversation and research on user-adaptation in dialogue systems involves a better understanding of speakers convergence in conversation. Convergence effects have been established on controlled data sets, for various acoustic and linguistic variables. Tracking interpersonal dynamics on generic corpora has provided positive but more contrasted outcomes. We propose here to enrich large conversational corpora with dialogue act (DA) information. We use DA-labels as filters in order to create data sub sets featuring homogeneous conversational activity. Those data sets allow a more precise comparison between speakers’ speech variables. Our experiences consist of comparing convergence on low level variables (Energy, Pitch, Speech Rate) measured on raw data sets, with human and automatically DA-labelled data sets. We found that such filtering does help in observing convergence suggesting that studies on interpersonal dynamics should consider such high level dialogue activity types and their related NLP topics as important ingredients of their toolboxes.

This paper introduces LexFr, a corpus-based French lexical resource built by adapting the framework LexIt, originally developed to describe the combinatorial potential of Italian predicates. As in the original framework, the behavior of a group of target predicates is characterized by a series of syntactic (i.e., subcategorization frames) and semantic (i.e., selectional preferences) statistical information (a.k.a. distributional profiles) whose extraction process is mostly unsupervised. The first release of LexFr includes information for 2,493 verbs, 7,939 nouns and 2,628 adjectives. In these pages we describe the adaptation process and evaluated the final resource by comparing the information collected for 20 test verbs against the information available in a gold standard dictionary. In the best performing setting, we obtained 0.74 precision, 0.66 recall and 0.70 F-measure.

The question of the type of text used as primary data in treebanks is of certain importance. First, it has an influence at the discourse level: an article is not organized in the same way as a novel or a technical document. Moreover, it also has consequences in terms of semantic interpretation: some types of texts can be easier to interpret than others. We present in this paper a new type of treebank which presents the particularity to answer to specific needs of experimental linguistic. It is made of short texts (book backcovers) that presents a strong coherence in their organization and can be rapidly interpreted. This type of text is adapted to short reading sessions, making it easy to acquire physiological data (e.g. eye movement, electroencepholagraphy). Such a resource offers reliable data when looking for correlations between computational models and human language processing.

There have been several attempts to annotate communicative functions to utterances of verbal feedback in English previously. Here, we suggest an annotation scheme for verbal and non-verbal feedback utterances in French including the categories base, attitude, previous and visual. The data comprises conversations, maptasks and negotiations from which we extracted ca. 13,000 candidate feedback utterances and gestures. 12 students were recruited for the annotation campaign of ca. 9,500 instances. Each instance was annotated by between 2 and 7 raters. The evaluation of the annotation agreement resulted in an average best-pair kappa of 0.6. While the base category with the values acknowledgement, evaluation, answer, elicit achieve good agreement, this is not the case for the other main categories. The data sets, which also include automatic extractions of lexical, positional and acoustic features, are freely available and will further be used for machine learning classification experiments to analyse the form-function relationship of feedback.

The question of interoperability for linguistic annotated resources covers different aspects. First, it requires a representation framework making it possible to compare, and eventually merge, different annotation schema. In this paper, a general description level representing the multimodal linguistic annotations is proposed. It focuses on time representation and on the data content representation: This paper reconsiders and enhances the current and generalized representation of annotations. An XML schema of such annotations is proposed. A Python API is also proposed. This framework is implemented in a multi-platform software and distributed under the terms of the GNU Public License.

This paper introduces the Aix Map Task corpus, a corpus of audio and video recordings of task-oriented dialogues. It was modelled after the original HCRC Map Task corpus. Lexical material was designed for the analysis of speech and prosody, as described in Astésano et al. (2007). The design of the lexical material, the protocol and some basic quantitative features of the existing corpus are presented. The corpus was collected under two communicative conditions, one audio-only condition and one face-to-face condition. The recordings took place in a studio and a sound attenuated booth respectively, with head-set microphones (and in the face-to-face condition with two video cameras). The recordings have been segmented into Inter-Pausal-Units and transcribed using transcription conventions containing actual productions and canonical forms of what was said. It is made publicly available online.

Knowledge on evaluation metrics and best practices of using them have improved fast in the recent years Fort et al. (2012). However, the advances concern mostly evaluation of classification related tasks. Segmentation tasks have received less attention. Nevertheless, there are crucial in a large number of linguistic studies. A range of metrics is available (F-score on boundaries, F-score on units, WindowDiff ((WD), Boundary Similarity (BS) but it is still relatively difficult to interpret these metrics on various linguistic segmentation tasks, such as prosodic and discourse segmentation. In this paper, we consider real segmented datasets (introduced in Peshkov et al. (2012)) as references which we deteriorate in different ways (random addition of boundaries, random removal boundaries, near-miss errors introduction). This provide us with various measures on controlled datasets and with an interesting benchmark for various linguistic segmentation tasks.

This paper describes the ANNODIS resource, a discourse-level annotated corpus for French. The corpus combines two perspectives on discourse: a bottom-up approach and a top-down approach. The bottom-up view incrementally builds a structure from elementary discourse units, while the top-down view focuses on the selective annotation of multi-level discourse structures. The corpus is composed of texts that are diversified with respect to genre, length and type of discursive organisation. The methodology followed here involves an iterative design of annotation guidelines in order to reach satisfactory inter-annotator agreement levels. This allows us to raise a few issues relevant for the comparison of such complex objects as discourse structures. The corpus also serves as a source of empirical evidence for discourse theories. We present here two first analyses taking advantage of this new annotated corpus --one that tested hypotheses on constraints governing discourse structure, and another that studied the variations in composition and signalling of multi-level discourse structures.

Ce travail s’inscrit dans l’analyse automatique d’un corpus de récits de voyage. À cette fin, nous raffinons la sémantique de Montague pour rendre compte des phénomènes d’adaptation du sens des mots au contexte dans lequel ils apparaissent. Ici, nous modélisons les constructions de type ‘le chemin descend pendant une demi-heure’ où ledit chemin introduit un voyageur fictif qui le parcourt, en étendant des idées que le dernier auteur a développé avec Bassac et Mery. Cette introduction du voyageur utilise la montée de type afin que le quantificateur introduisant le voyageur porte sur toute la phrase et que les propriétés du chemin ne deviennent pas des propriétés du voyageur, fût-il fictif. Cette analyse sémantique (ou plutôt sa traduction en lambda-DRT) est d’ores et déjà implantée pour une partie du lexique de Grail.

Large annotation projects, typically those addressing the question of multimodal annotation in which many different kinds of information have to be encoded, have to elaborate precise and high level annotation schemes. Doing this requires first to define the structure of the information: the different objects and their organization. This stage has to be as much independent as possible from the coding language constraints. This is the reason why we propose a preliminary formal annotation model, represented with typed feature structures. This representation requires a precise definition of the different objects, their properties (or features) and their relations, represented in terms of type hierarchies. This approach has been used to specify the annotation scheme of a large multimodal annotation project (OTIM) and experimented in the annotation of a multimodal corpus (CID, Corpus of Interactional Data). This project aims at collecting, annotating and exploiting a dialogue video corpus in a multimodal perspective (including speech and gesture modalities). The corpus itself, is made of 8 hours of dialogues, fully transcribed and richly annotated (phonetics, syntax, pragmatics, gestures, etc.).

Le projet ANNODIS vise la construction d’un corpus de textes annotés au niveau discursif ainsi que le développement d’outils pour l’annotation et l’exploitation de corpus. Les annotations adoptent deux points de vue complémentaires : une perspective ascendante part d’unités de discours minimales pour construire des structures complexes via un jeu de relations de discours ; une perspective descendante aborde le texte dans son entier et se base sur des indices pré-identifiés pour détecter des structures discursives de haut niveau. La construction du corpus est associée à la création de deux interfaces : la première assiste l’annotation manuelle des relations et structures discursives en permettant une visualisation du marquage issu des prétraitements ; une seconde sera destinée à l’exploitation des annotations. Nous présentons les modèles et protocoles d’annotation élaborés pour mettre en oeuvre, au travers de l’interface dédiée, la campagne d’annotation.

The measurement of conceptual similarity in a hierarchical structure has been proposed by studies such as Wu and Palmer (1994) which have been summarized and evaluated in Budanisky and Hirst (2006). The present study applies the measurement of conceptual similarity to conceptual metaphor research by comparing concreteness of ontological resource nodes to several prototypical concrete nodes selected by human subjects. Here, the purpose of comparing conceptual similarity between nodes is to select a concrete sense for a word which is used metaphorically. Through using WordNet-SUMO interface such as SinicaBow (Huang, Chang and Lee, 2004), concrete senses of a lexicon will be selected once its SUMO nodes have been compared in terms of conceptual similarity with the prototypical concrete nodes. This study has strong implications for the interaction of psycholinguistic and computational linguistic fields in conceptual metaphor research.