Search Results for author:
Found 32 papers, 10 papers with code
Code-switched inspired losses for spoken dialog representations
Spoken dialogue systems need to be able to handle both multiple languages and multilinguality inside a conversation (e. g in case of code-switching).
Towards More Robust NLP System Evaluation: Handling Missing Scores in Benchmarks
This paper formalize an existing problem in NLP research: benchmarking when some systems scores are missing on the task, and proposes a novel approach to address it.
Hallucinations in Large Multilingual Translation Models
Large-scale multilingual machine translation systems have demonstrated remarkable ability to translate directly between numerous languages, making them increasingly appealing for real-world applications.
The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset
As language models grow ever larger, the need for large-scale high-quality text datasets has never been more pressing, especially in multilingual settings.
Unsupervised Layer-wise Score Aggregation for Textual OOD Detection
More importantly, we show that the usual choice (the last layer) is rarely the best one for OOD detection and that far better results could be achieved if the best layer were picked.
Optimal Transport for Unsupervised Hallucination Detection in Neural Machine Translation
Neural machine translation (NMT) has become the de-facto standard in real-world machine translation applications.
Rainproof: An Umbrella To Shield Text Generators From Out-Of-Distribution Data
As more and more conversational and translation systems are deployed in production, it is essential to implement and to develop effective control mechanisms guaranteeing their proper functioning and security.
Beyond Mahalanobis-Based Scores for Textual OOD Detection
Deep learning methods have boosted the adoption of NLP systems in real-life applications.
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions.
The Glass Ceiling of Automatic Evaluation in Natural Language Generation
Automatic evaluation metrics capable of replacing human judgments are critical to allowing fast development of new methods.
Of Human Criteria and Automatic Metrics: A Benchmark of the Evaluation of Story Generation
However, there is no consensus on which human evaluation criteria to use, and no analysis of how well automatic criteria correlate with them.
Learning Disentangled Textual Representations via Statistical Measures of Similarity
When working with textual data, a natural application of disentangled representations is fair classification where the goal is to make predictions without being biased (or influenced) by sensitive attributes that may be present in the data (e. g., age, gender or race).
A Differential Entropy Estimator for Training Neural Networks
Mutual Information (MI) has been widely used as a loss regularizer for training neural networks.
What are the best systems? New perspectives on NLP Benchmarking
In Machine Learning, a benchmark refers to an ensemble of datasets associated with one or multiple metrics together with a way to aggregate different systems performances.
NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation
Data augmentation is an important component in the robustness evaluation of models in natural language processing (NLP) and in enhancing the diversity of the data they are trained on.
InfoLM: A New Metric to Evaluate Summarization & Data2Text Generation
In this paper, we introduce InfoLM a family of untrained metrics that can be viewed as a string-based metric that addresses the aforementioned flaws thanks to a pre-trained masked language model.
Beam Search with Bidirectional Strategies for Neural Response Generation
Sequence-to-sequence neural networks have been widely used in language-based applications as they have flexible capabilities to learn various language models.
Improving Multimodal fusion via Mutual Dependency Maximisation
We demonstrate that our new penalties lead to a consistent improvement (up to $4. 3$ on accuracy) across a large variety of state-of-the-art models on two well-known sentiment analysis datasets: \texttt{CMU-MOSI} and \texttt{CMU-MOSEI}.
Automatic Text Evaluation through the Lens of Wasserstein Barycenters
A new metric \texttt{BaryScore} to evaluate text generation based on deep contextualized embeddings e. g., BERT, Roberta, ELMo) is introduced.
Code-switched inspired losses for generic spoken dialog representations
Spoken dialog systems need to be able to handle both multiple languages and multilinguality inside a conversation (\textit{e. g} in case of code-switching).
A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representations
We show the superiority of this method on fair classification and on textual style transfer tasks.
Ranked #1 on
Text Style Transfer
on Yelp Review Dataset (Large)
(BLEU metric)
A Pseudo-Metric between Probability Distributions based on Depth-Trimmed Regions
a probability distribution or a data set.
Learning to Disentangle Textual Representations and Attributes via Mutual Information
Learning disentangled representations of textual data is essential for many natural language tasks such as fair classification (\textit{e. g.} building classifiers whose decisions cannot disproportionately hurt or benefit specific groups identified by sensitive attributes), style transfer and sentence generation, among others.
The importance of fillers for text representations of speech transcripts
While being an essential component of spoken language, fillers (e. g."um" or "uh") often remain overlooked in Spoken Language Understanding (SLU) tasks.
Hierarchical Pre-training for Sequence Labelling in Spoken Dialog
We obtain our representations with a hierarchical encoder based on transformer architectures, for which we extend two well-known pre-training objectives.
Ranked #1 on
Text Classification
on SILICONE Benchmark
Dialogue Act Classification
Emotion Recognition in Conversation
+1
Heavy-tailed Representations, Text Polarity Classification & Data Augmentation
The dominant approaches to text representation in natural language rely on learning embeddings on massive corpora which have convenient properties such as compositionality and distance preservation.
Ranked #3 on
Sentiment Analysis
on Yelp Binary classification
Guider l'attention dans les modeles de sequence a sequence pour la prediction des actes de dialogue
The task of predicting dialog acts (DA) based on conversational dialog is a key component in the development of conversational agents.
Guiding attention in Sequence-to-sequence models for Dialogue Act prediction
The task of predicting dialog acts (DA) based on conversational dialog is a key component in the development of conversational agents.
Ranked #1 on
Dialogue Act Classification
on Switchboard corpus
Regularly varying representation for sentence embedding
The dominant approaches to sentence representation in natural language rely on learning embeddings on massive corpuses.
From the Token to the Review: A Hierarchical Multimodal approach to Opinion Mining
The task of predicting fine grained user opinion based on spontaneous spoken language is a key problem arising in the development of Computational Agents as well as in the development of social network based opinion miners.
Affect-Driven Dialog Generation
The majority of current systems for end-to-end dialog generation focus on response quality without an explicit control over the affective content of the responses.
Disney at IEST 2018: Predicting Emotions using an Ensemble
This paper describes our participating system in the WASSA 2018 shared task on emotion prediction.
