Search Results for author: Maxime Amblard

Found 20 papers, 4 papers with code

Investigating non lexical markers of the language of schizophrenia in spontaneous conversations

1 code implementation CODI 2021 Chuyuan Li, Maxime Amblard, Chloé Braud, Caroline Demily, Nicolas Franck, Michel Musiol

We investigate linguistic markers associated with schizophrenia in clinical conversations by detecting predictive features among French-speaking patients.

Quantification Annotation in ISO 24617-12, Second Draft

no code implementations LREC 2022 Harry Bunt, Maxime Amblard, Johan Bos, Karën Fort, Bruno Guillaume, Philippe de Groote, Chuyuan Li, Pierre Ludmann, Michel Musiol, Siyana Pavlova, Guy Perrier, Sylvain Pogodalla

This paper describes the continuation of a project that aims at establishing an interoperable annotation schema for quantification phenomena as part of the ISO suite of standards for semantic annotation, known as the Semantic Annotation Framework.

GECko+: a Grammatical and Discourse Error Correction Tool

1 code implementation JEP/TALN/RECITAL 2021 Eduardo Calò, Léo Jacqmin, Thibo Rosemplatt, Maxime Amblard, Miguel Couceiro, Ajinkya Kulkarni

GECko+ : a Grammatical and Discourse Error Correction Tool We introduce GECko+, a web-based writing assistance tool for English that corrects errors both at the sentence and at the discourse level.

Sentence Sentence Ordering

Modal Subordination in Type Theoretic Dynamic Logic

no code implementations LILT 2016 Sai Qian, Philippe de Groote, Maxime Amblard

In general, modal subordination is concerned with more than two modalities, where the modality in subsequent sentences is interpreted in a context ‘subordinate’ to the one created by the first modal expression.

Sentence Vocal Bursts Type Prediction

With a Little Help from my (Linguistic) Friends: Topic Segmentation of Multi-party Casual Conversations

no code implementations5 Feb 2024 Amandine Decker, Maxime Amblard

Topics play an important role in the global organisation of a conversation as what is currently discussed constrains the possible contributions of the participant.

Discourse Structure Extraction from Pre-Trained and Fine-Tuned Language Models in Dialogues

no code implementations12 Feb 2023 Chuyuan Li, Patrick Huber, Wen Xiao, Maxime Amblard, Chloé Braud, Giuseppe Carenini

As a result, we explore approaches to build discourse structures for dialogues, based on attention matrices from Pre-trained Language Models (PLMs).

Sentence Sentence Ordering

How much of UCCA can be predicted from AMR?

no code implementations ISA (LREC) 2022 Siyana Pavlova, Maxime Amblard, Bruno Guillaume

In this paper, we consider two of the currently popular semantic frameworks: Abstract Meaning Representation (AMR)a more abstract framework, and Universal Conceptual Cognitive Annotation (UCCA)-an anchored framework.

Graph Querying for Semantic Annotations

no code implementations ISA (LREC) 2022 Maxime Amblard, Bruno Guillaume, Siyana Pavlova, Guy Perrier

This paper presents how the online tool GREW-MATCH can be used to make queries and visualise data from existing semantically annotated corpora.

A Multi-Party Dialogue Ressource in French

no code implementations LREC 2022 Maria Boritchev, Maxime Amblard

We present Dialogues in Games (DinG), a corpus of manual transcriptions of real-life, oral, spontaneous multi-party dialogues between French-speaking players of the board game Catan.

Multi-Task Learning for Depression Detection in Dialogs

1 code implementation SIGDIAL (ACL) 2022 Chuyuan Li, Chloé Braud, Maxime Amblard

Depression is a serious mental illness that impacts the way people communicate, especially through their emotions, and, allegedly, the way they interact with others.

Depression Detection Multi-Task Learning

Reducing Unintended Bias of ML Models on Tabular and Textual Data

no code implementations5 Aug 2021 Guilherme Alves, Maxime Amblard, Fabien Bernier, Miguel Couceiro, Amedeo Napoli

Unintended biases in machine learning (ML) models are among the major concerns that must be addressed to maintain public trust in ML.

Fairness

Investigation par m\'ethodes d'apprentissage des sp\'ecificit\'es langagi\`eres propres aux personnes avec schizophr\'enie (Investigating Learning Methods Applied to Language Specificity of Persons with Schizophrenia)

no code implementations JEPTALNRECITAL 2020 Maxime Amblard, Chlo{\'e} Braud, Chuyuan Li, Caroline Demily, Nicolas Franck, Michel Musiol

Nous pr{\'e}sentons des exp{\'e}riences visant {\`a} identifier automatiquement des patients pr{\'e}sentant des sympt{\^o}mes de schizophr{\'e}nie dans des conversations contr{\^o}l{\'e}es entre patients et psychoth{\'e}rapeutes.

Specificity

A compositional view of questions

no code implementations WS 2019 Maria Boritchev, Maxime Amblard

We present a research on compositional treatment of questions in neo-davidsonian event semantics style.

Introducing a Calculus of Effects and Handlers for Natural Language Semantics

no code implementations20 Jun 2016 Jirka Maršík, Maxime Amblard

In compositional model-theoretic semantics, researchers assemble truth-conditions or other kinds of denotations using the lambda calculus.

Pragmatic Side Effects

no code implementations17 Jun 2015 Jiri Marsik, Maxime Amblard

In the quest to give a formal compositional semantics to natural languages, semanticists have started turning their attention to phenomena that have been also considered as parts of pragmatics (e. g., discourse anaphora and presupposition projection).

Treating clitics with minimalist grammars

no code implementations8 Oct 2013 Maxime Amblard

We propose an extension of Stabler's version of clitics treatment for a wider coverage of the French language.

Cannot find the paper you are looking for? You can Submit a new open access paper.