Papers by Philippe Muller
Mining Discourse Markers for Unsupervised Sentence Representation Learning (N19-1)
Copied to clipboard
| Challenge: | Current state of the art systems in NLP heavily rely on manually annotated datasets, which are expensive to obtain and are ineffective to extract. |
| Approach: | They propose to automatically discover sentence pairs with relevant discourse markers and apply it to massive amounts of data. |
| Outcome: | The proposed method can learn transferable sentence embeddings from 174 discourse markers even for rare markers such as “coincidentally” or “amazingly”. |
In2Core: Leveraging Influence Functions for Coreset Selection in Instruction Finetuning of Large Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) exhibit surprising abilities across a variety of language tasks. |
| Approach: | They propose an algorithm which selects a coreset by analyzing correlation between training and evaluation samples with a trained model. |
| Outcome: | The proposed algorithm can achieve similar performance with just 50% of the training data while preserving the accuracy of the existing model. |
Weakly supervised discourse segmentation for multiparty oral conversations (2021.emnlp-main)
Copied to clipboard
| Challenge: | Discourse segmentation is the first step of discourse analysis. |
| Approach: | They propose a weak supervision approach to adapt a latent model to French conversation transcripts with a linguistic and acoustic input. |
| Outcome: | The proposed model improves in situations where speaker turns are lacking or noisy, gaining up to 13% in F-score. |
Zero-shot Learning for Multilingual Discourse Relation Classification (2024.lrec-main)
Copied to clipboard
| Challenge: | Discourse analysis is a hard task, but data is limited for other languages. |
| Approach: | They propose to use zero-shot learning to combine discourse relation data . they compare two versions of the same text with different labels . |
| Outcome: | The proposed method can be applied to languages, frameworks, or similarity measures. |
DiscSense: Automated Semantic Analysis of Discourse Markers (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing models for predicting discourse markers have been used to study link between markers and semantic relations . |
| Approach: | They use a model trained to predict discourse markers between sentence pairs to predict plausible markers between sentences with a known semantic relation. |
| Outcome: | The proposed method predicts markers between sentence pairs with a known semantic relation . the resulting dataset, named DiscSense, is publicly available . |
A Pragmatics-Centered Evaluation Framework for Natural Language Understanding (2022.lrec-1)
Copied to clipboard
| Challenge: | a number of studies have suggested that models induce universal text representations . current benchmarks focus on semantic phenomena, so pragmatics needs to be the focus . |
| Approach: | They propose a benchmark that unites 11 pragmatics-focused evaluation datasets for English. |
| Outcome: | The proposed benchmark shows that natural language inference does not result in genuinely universal representations. |
An Integrated Approach for Political Bias Prediction and Explanation Based on Discursive Structure (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for predicting and explaining political biases rely on lexical cues. |
| Approach: | They propose an approach to automatically characterize biases that takes into account structural differences and is efficient for long texts. |
| Outcome: | The proposed approach is efficient for long texts and takes into account structural differences. |
DISRPT: A Multilingual, Multi-domain, Cross-framework Benchmark for Discourse Processing (2024.lrec-main)
Copied to clipboard
Chloé Braud, Amir Zeldes, Laura Rivière, Yang Janet Liu, Philippe Muller, Damien Sileo, Tatsuya Aoyama
| Challenge: | DISRPT is a multilingual, multi-domain, and cross-framework benchmark dataset for discourse processing. |
| Approach: | They present a multilingual, multi-domain, and cross-framework benchmark dataset for discourse processing that includes 13 languages and 24 corpora covering about 4 millions tokens and around 250,000 discourse relation instances from 4 discourse frameworks. |
| Outcome: | The DISRPT dataset includes data from 24 corpora covering about 4 millions tokens and around 250,000 discourse relation instances from 4 discourse frameworks. |