Papers by Chloé Clavel
Toward the Automatic Detection of Word Meaning Negotiation Indicators in Conversation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Word Meaning Negotiations (WMN) are sequences in conversation where speakers collectively discuss and shape word meaning. |
| Approach: | They propose to detect WMN indicators in conversations where a speaker signals the need to clarify or challenge word meaning. |
| Outcome: | The proposed models have better precision than previous regular expression based approaches and show some generalization abilities, but have moderate recall. |
How About Kind of Generating Hedges using End-to-End Neural Models? (2023.acl-long)
Copied to clipboard
| Challenge: | hedging is a strategy for softening the impact of a statement in conversation. |
| Approach: | They propose to fine-tune state-of-the-art language models trained on human-human tutoring data and then use a hedge classifier to select the candidate that best matches the expected hedging strategy. |
| Outcome: | The proposed model is feasible in a noisy environment with reranking, and it is compared with other approaches. |
Opinions in Interactions : New Annotations of the SEMAINE Database (2022.lrec-1)
Copied to clipboard
| Challenge: | a new method for the detection of opinions in interactions is proposed . a dataset of dyadic interactions is annotated continuously in two affective dimensions related to the emotions . |
| Approach: | They propose to annotate opinions over a multimodal corpus of dyadic interactions . they use a d-acting algorithm to annnotate the opinions of a speaker . |
| Outcome: | The proposed method allows to obtain a precise annotation regarding the opinion of a speaker. |
Code-switched inspired losses for spoken dialog representations (2021.emnlp-main)
Copied to clipboard
| Challenge: | We introduce new pretraining losses tailored to learn generic multilingual spoken dialogue representations . goal is to expose model to code-switched language . |
| Approach: | They propose to build a pretraining corpus of multilingual conversations in five different languages from OpenSubtitles. |
| Outcome: | The proposed models perform better in monolingual and multilingual settings. |
The importance of fillers for text representations of speech transcripts (2020.emnlp-main)
Copied to clipboard
| Challenge: | Fillers are a type of disfluency that can be a sound ("um" or "uh") filling a pause in an utterance or conversation. |
| Approach: | They propose to represent fillers with deep contextualised embeddings to improve modelling of spoken language and two downstream tasks . |
| Outcome: | The proposed representations improve modelling of spoken language and two downstream tasks, predicting a speaker’s stance and expressed confidence. |
The POTUS Corpus, a Database of Weekly Addresses for the Study of Stance in Politics and Virtual Agents (2020.lrec-1)
Copied to clipboard
| Challenge: | Embodied Conversational Agents (ECAs) are used to generate socially believable agents. |
| Approach: | They propose to use audio-video files of political addresses to generate a corpus of socially believable agents which can be annotated by external observers. |
| Outcome: | The proposed corpus analyzes audio-video files of political addresses to the american people and provides the same speeches given by a virtual agent named Rodrigue. |
TINA: Textual Inference with Negation Augmentation (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing transformer-based models perform poorly on textual entailment when examples contain negations. |
| Approach: | They propose a new definition of textual entailment that captures negation and a principled technique for negated data augmentation that can be combined with unlikelihood loss function. |
| Outcome: | The proposed method significantly improves on textual entailment datasets with negations without sacrificing performance on datasets without negation. |
One Word, Two Sides: Traces of Stance in Contextualized Word Representations (2022.coling-1)
Copied to clipboard
| Challenge: | a Lexical Semantic Change study examines the way we use words . it focuses on the use of words by people who disagree on a particular topic . |
| Approach: | They examine whether word embeddings reflect the way we use words . they use BERT embeddables from datasets with stance annotations to examine this question . |
| Outcome: | The results show that people with opposing stances use different words when talking about a topic . the results are not related to studies that investigate the usage of specific words across different viewpoints. |
Graphically Speaking: Unmasking Abuse in Social Media with Conversation Insights (2025.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to detect abusive language often ignore conversational context, leading to inconsistent and sometimes inconclusive results. |
| Approach: | They propose a graph neural network approach that uses conversational context to model social media conversations as graphs, where nodes represent comments and edges capture reply structures. |
| Outcome: | The proposed model outperforms baseline and linear context-aware methods and achieves significant improvements in F1 scores. |
The Curious Decline of Linguistic Diversity: Training Language Models on Synthetic Text (2024.findings-naacl)
Copied to clipboard
| Challenge: | a new study examines the effects of training language models on synthetic data generated by their predecessors. |
| Approach: | They propose to use recursive finetuning techniques to assess linguistic diversity of models. |
| Outcome: | The proposed metrics show a decrease in diversity of model outputs through successive iterations, especially for tasks demanding high levels of creativity. |
Few-Shot Emotion Recognition in Conversation with Sequential Prototypical Networks (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on dyadic human-human interactions focus on conversations without specific business objectives. |
| Approach: | They propose a method to detect emotions in a live chat customer service . they propose 'ProtoSeq' for conversational emotion classification using different languages . |
| Outcome: | The proposed method is competitive even when applied to other ones. |
Hierarchical Pre-training for Sequence Labelling in Spoken Dialog (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Sequence labelling tasks like Dialog Act and Emotion/Sentiment identification are a key component of spoken dialog systems. |
| Approach: | They propose a new approach to learn generic representations adapted to spoken dialog using a hierarchical encoder based on transformer architectures. |
| Outcome: | The proposed model is model-agnostic and contains 10 datasets of various sizes. |
A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representations (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods for learning disentangled representations of textual data are difficult to implement and suffer from the degeneracy of other losses in multi-class scenarios. |
| Approach: | They propose a variational upper bound to the mutual information between an attribute and the latent code of an encoder that controls the approximation error. |
| Outcome: | The proposed method is superior on fair classification and on textual style transfer tasks. |
EZCAT: an Easy Conversation Annotation Tool (2022.lrec-1)
Copied to clipboard
| Challenge: | EZCAT is an annotation tool for textual conversations, but it is not customizable. |
| Approach: | They propose an easy-to-use interface to annotate conversations in a configurable schema . they use it to annnotate private chats and chats, and they use the schema to test it . |
| Outcome: | The proposed interface allows users to control data and annotate conversations in two levels . it eliminates the need for a server and accounts management, and allows users access to data . |
MAFALDA: A Benchmark and Comprehensive Study of Fallacy Detection and Classification (2024.naacl-long)
Copied to clipboard
| Challenge: | Fallacy classification is a task of broad importance due to advances in deep learning and availability of more data. |
| Approach: | They propose a new annotation scheme tailored for subjective NLP tasks and a method designed to handle subjectivity. |
| Outcome: | The proposed approach integrates existing fallacy classification datasets with new ones. |
Multimodal Analysis of Cohesion in Multi-party Interactions (2020.lrec-1)
Copied to clipboard
Reshmashree Bangalore Kantharaju, Caroline Langlet, Mukesh Barange, Chloé Clavel, Catherine Pelachaud
| Challenge: | Existing studies have associated group cohesion with performance, team satisfaction and adherence. |
| Approach: | They propose to use 16 two-minute segments annotated with group cohesion from the AMI corpus to analyze their impact on perceived level of cohesicity. |
| Outcome: | The proposed analysis shows that laughter and interruption are higher in high cohesive segments. |
From the Token to the Review: A Hierarchical Multimodal approach to Opinion Mining (D19-1)
Copied to clipboard
| Challenge: | Existing work on fine grained opinion annotations rely only on coarsely labeled opinions. |
| Approach: | They propose to use hierarchical structure of opinions to build a fine and coarse grained opinion model that exploits different views of the opinion expression. |
| Outcome: | The proposed model outperforms existing models on a recently released multimodal fine grained annotated corpus on IMDB and social networks. |
“Mm, Wat?” Detecting Other-initiated Repair Requests in Dialogue (2025.emnlp-main)
Copied to clipboard
| Challenge: | Current conversational agents (CAs) do not recognize repair initiation, leading to breakdowns or disengagement. |
| Approach: | They propose a multimodal model to automatically detect repair initiation in Dutch dialogues by integrating linguistic and prosodic features grounded in Conversation Analysis. |
| Outcome: | The proposed model integrates linguistic and prosodic features grounded in Conversation Analysis to detect repair initiation in Dutch dialogues. |
“You might think about slightly revising the title”: Identifying Hedges in Peer-tutoring Interactions (2022.acl-long)
Copied to clipboard
| Challenge: | In peer-tutoring, hedges are used to manage rapport and tone down negative feedback . a hybrid approach that outperforms existing baselines is easier to interpret . |
| Approach: | They propose to use a peer-tutoring dataset to identify hedges that manage rapport with teens . they propose to combine pre-trained resources with models that integrate social science insights . |
| Outcome: | The proposed model outperforms existing models while being easier to interpret. |
Improving Multimodal fusion via Mutual Dependency Maximisation (2021.emnlp-main)
Copied to clipboard
| Challenge: | Multimodal sentiment analysis is a trending area of research, and multimodal fusion is one of its most active topics. |
| Approach: | They propose to use modality-based penalties to measure dependency between models to improve accuracy. |
| Outcome: | The proposed methods improve accuracy on two well-known sentiment analysis datasets by 4.3 on the proposed models and by-product includes a statistical network which can interpret the high dimensional representations learnt by the model. |
Questioning the Validity of Summarization Datasets and Improving Their Factual Consistency (2022.emnlp-main)
Copied to clipboard
| Challenge: | Abstractive summarization systems have a lack of a defined definition for the task . factual consistency is a key factor in summarizing, but there are still deficiencies . a new study shows that summarized summarisation models achieve improved performance . |
| Approach: | They propose a filtered summarization dataset with improved factual consistency to address this problem . they argue that the dataset should become a valid benchmark for developing and evaluating summarizing systems . |
| Outcome: | The proposed model improves on a popular summarization dataset with improved factual consistency. |
EmoDynamiX: Emotional Support Dialogue Strategy Prediction by Modelling MiXed Emotions and Discourse Dynamics (2025.naacl-long)
Copied to clipboard
| Challenge: | Recent studies show that implicit strategy planning lacks transparency and that LLMs’ inherent preference bias towards certain socio-emotional strategies hinders the delivery of high-quality emotional support. |
| Approach: | They propose to decouple strategy prediction from language generation and introduce a new dialogue strategy prediction framework, EmoDynamiX, which models the discourse dynamics between user fine-grained emotions and system strategies using a heterogeneous graph for better performance and transparency. |
| Outcome: | The proposed framework outperforms state-of-the-art methods on two ESC datasets with a significant margin (better proficiency and lower preference bias). |
LogiTorch: A PyTorch-based library for logical reasoning on natural language (2022.emnlp-demos)
Copied to clipboard
| Challenge: | Logical reasoning on natural language is one of the most challenging tasks for deep learning models. |
| Approach: | They propose a library that includes logical reasoning benchmarks and models . they use a dataset to run the library or fine tune the models with different hyperparameters . |
| Outcome: | This library includes logical reasoning benchmarks, models, utility functions and co-reference resolution. |
Automatic Text Evaluation through the Lens of Wasserstein Barycenters (2021.emnlp-main)
Copied to clipboard
| Challenge: | metric BaryScore is used to evaluate text generation based on deep contextualized embeddings. |
| Approach: | They propose to model the layer output of deep contextualized embeddings as a probability distribution rather than a vector embeddable layer. |
| Outcome: | The proposed metric outperforms other BERT based metrics and exhibits more consistent behaviour in particular for text summarization. |
Of Human Criteria and Automatic Metrics: A Benchmark of the Evaluation of Story Generation (2022.coling-1)
Copied to clipboard
| Challenge: | Existing studies on automatic story generation (ASG) rely on human criteria, but there is little research on how well they correlate with human criteria. |
| Approach: | They propose to use human criteria to evaluate automatic story generation (ASG) their paper proposes to use HANNA to quantitatively evaluate correlations between 72 automatic metrics and human criteria. |
| Outcome: | The proposed model compared human criteria with automatic criteria and found that they were significantly better than human criteria. |
Automatic Analysis of Substantiation in Scientific Peer Reviews (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing systems to analyze peer reviews' quality are inadequate due to the increasing workload of reviewers and the lack of domain experts . |
| Approach: | They propose to use a claim-evidence pair extraction problem to analyze substantiation in peer reviews and train an argument mining system to do the same. |
| Outcome: | The proposed system could be used by conference managers and reviewers to analyze the quality of peer reviews. |
Polysemy in Spoken Conversations and Written Texts (2022.lrec-1)
Copied to clipboard
| Challenge: | a recent study examined the use of polysemous words in discourses . a lexical ambiguity is a result of the use and use of multiple senses in a text . |
| Approach: | They propose a "one sense per discourse" hypothesis to explain the use of polysemous words in discourses . they compare the polysesty level of spoken dialogs with spoken dialog . |
| Outcome: | The proposed "one sense per discourse" hypothesis is not valid in all texts. |