Le traitement du langage naturel à l'ère de l'IA générative
Rejoignez-nous à Mila en octobre pour un atelier de trois jour visant à explorer le potentiel de transformation des technologies langagières et leurs implications pour la société.
Ce programme est conçu pour fournir aux professionnel·le·s travaillant dans le domaine de la politique une compréhension fondamentale de la technologie de l'IA.
Nous utilisons des témoins pour analyser le trafic et l’utilisation de notre site web, afin de personnaliser votre expérience. Vous pouvez désactiver ces technologies à tout moment, mais cela peut restreindre certaines fonctionnalités du site. Consultez notre Politique de protection de la vie privée pour en savoir plus.
Paramètre des cookies
Vous pouvez activer et désactiver les types de cookies que vous souhaitez accepter. Cependant certains choix que vous ferez pourraient affecter les services proposés sur nos sites (ex : suggestions, annonces personnalisées, etc.).
Cookies essentiels
Ces cookies sont nécessaires au fonctionnement du site et ne peuvent être désactivés. (Toujours actif)
Cookies analyse
Acceptez-vous l'utilisation de cookies pour mesurer l'audience de nos sites ?
Multimedia Player
Acceptez-vous l'utilisation de cookies pour afficher et vous permettre de regarder les contenus vidéo hébergés par nos partenaires (YouTube, etc.) ?
Publications
Effectiveness of regional diffusion MRI measures in distinguishing multiple sclerosis abnormalities within the cervical spinal cord
Multiple sclerosis (MS) is an inflammatory disorder of the central nervous system. Although conventional magnetic resonance imaging (MRI) is… (voir plus) widely used for MS diagnosis and clinical follow‐up, quantitative MRI has the potential to provide valuable intrinsic values of tissue properties that can enhance accuracy. In this study, we investigate the efficacy of diffusion MRI in distinguishing MS lesions within the cervical spinal cord, using a combination of metrics extracted from diffusion tensor imaging and Ball‐and‐Stick models.
Barriers and facilitators to patient engagement in patient safety from patients and healthcare professionals' perspectives: A systematic review and meta-synthesis.
AIMS
To explore patients' and healthcare professionals' (HCPs) perceived barriers and facilitators to patient engagement in patient safety.
… (voir plus)
METHODS
We conducted a systematic review and meta-synthesis from five computerized databases, including PubMed/MEDLINE, Embase, Web of Science, Scopus and PsycINFO, as well as grey literature and reference lists of included studies. Data were last searched in December 2019 with no limitation on the year of publication. Qualitative and Mix-methods studies that explored HCPs' and patients' perceptions of barriers and facilitators to patient engagement in patient safety were included. Two authors independently screened the titles and the abstracts of studies. Next, the full texts of the screened studies were reviewed by two authors. Potential discrepancies were resolved by consensus with a third author. The Mixed Methods Appraisal Tool was used for quality appraisal. Thematic analysis was used to synthesize results.
RESULTS
Nineteen studies out of 2616 were included in this systematic review. Themes related to barriers included: patient unwillingness, HCPs' unwillingness, and inadequate infrastructures. Themes related to facilitators were: encouraging patients, sharing information with patients, establishing trustful relationship, establishing patient-centred care and improving organizational resources.
CONCLUSION
Patients have an active role in improving their safety. Strategies are required to address barriers that hinder or prevent patient engagement and create capacity and facilitate action.
The field of Continual Learning (CL) seeks to develop algorithms that accumulate knowledge and skills over time through interaction with non… (voir plus)-stationary environments. In practice, a plethora of evaluation procedures (settings) and algorithmic solutions (methods) exist, each with their own potentially disjoint set of assumptions. This variety makes measuring progress in CL difficult. We propose a taxonomy of settings, where each setting is described as a set of assumptions. A tree-shaped hierarchy emerges from this view, where more general settings become the parents of those with more restrictive assumptions. This makes it possible to use inheritance to share and reuse research, as developing a method for a given setting also makes it directly applicable onto any of its children. We instantiate this idea as a publicly available software framework called Sequoia, which features a wide variety of settings from both the Continual Supervised Learning (CSL) and Continual Reinforcement Learning (CRL) domains. Sequoia also includes a growing suite of methods which are easy to extend and customize, in addition to more specialized methods from external libraries. We hope that this new paradigm and its first implementation can help unify and accelerate research in CL. You can help us grow the tree by visiting (this GitHub URL).
This paper explores the task of Difficulty-Controllable Question Generation (DCQG), which aims at generating questions with required difficu… (voir plus)lty levels. Previous research on this task mainly defines the difficulty of a question as whether it can be correctly answered by a Question Answering (QA) system, lacking interpretability and controllability. In our work, we redefine question difficulty as the number of inference steps required to answer it and argue that Question Generation (QG) systems should have stronger control over the logic of generated questions. To this end, we propose a novel framework that progressively increases question difficulty through step-by-step rewriting under the guidance of an extracted reasoning chain. A dataset is automatically constructed to facilitate the research, on which extensive experiments are conducted to test the performance of our method.
2021-08-01
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) (publié)
With the need of fast retrieval speed and small memory footprint, document hashing has been playing a crucial role in large-scale informatio… (voir plus)n retrieval. To generate high-quality hashing code, both semantics and neighborhood information are crucial. However, most existing methods leverage only one of them or simply combine them via some intuitive criteria, lacking a theoretical principle to guide the integration process. In this paper, we encode the neighborhood information with a graph-induced Gaussian distribution, and propose to integrate the two types of information with a graph-driven generative model. To deal with the complicated correlations among documents, we further propose a tree-structured approximation method for learning. Under the approximation, we prove that the training objective can be decomposed into terms involving only singleton or pairwise documents, enabling the model to be trained as efficiently as uncorrelated ones. Extensive experimental results on three benchmark datasets show that our method achieves superior performance over state-of-the-art methods, demonstrating the effectiveness of the proposed model for simultaneously preserving semantic and neighborhood information.
2021-08-01
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) (publié)
Model-agnostic meta-learning (MAML) has been recently put forth as a strategy to learn resource-poor languages in a sample-efficient fashion… (voir plus). Nevertheless, the properties of these languages are often not well represented by those available during training. Hence, we argue that the i.i.d. assumption ingrained in MAML makes it ill-suited for cross-lingual NLP. In fact, under a decision-theoretic framework, MAML can be interpreted as minimising the expected risk across training languages (with a uniform prior), which is known as Bayes criterion. To increase its robustness to outlier languages, we create two variants of MAML based on alternative criteria: Minimax MAML reduces the maximum risk across languages, while Neyman–Pearson MAML constrains the risk in each language to a maximum threshold. Both criteria constitute fully differentiable two-player games. In light of this, we propose a new adaptive optimiser solving for a local approximation to their Nash equilibrium. We evaluate both model variants on two popular NLP tasks, part-of-speech tagging and question answering. We report gains for their average and minimum performance across low-resource languages in zeroand few-shot settings, compared to joint multisource transfer and vanilla MAML. The code for our experiments is available at https:// github.com/rahular/robust-maml.
2021-08-01
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021 (publié)
Despite considerable advancements with deep neural language models (LMs), neural text generation still suffers from degeneration: the genera… (voir plus)ted text is repetitive, generic, self-contradictory, and often lacks commonsense. Our analyses on sentence-level attention patterns in LMs reveal that neural degeneration may be associated with insufficient learning of task-specific characteristics by the attention mechanism. This finding motivates on-the-fly attention modulation -- a simple but effective method that enables the injection of priors into attention computation during inference. Automatic and human evaluation results on three text generation benchmarks demonstrate that attention modulation helps LMs generate text with enhanced fluency, creativity, and commonsense reasoning, in addition to significantly reduce sentence-level repetition.
2021-08-01
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021 (publié)
It is a common belief that training deep transformers from scratch requires large datasets. Consequently, for small datasets, people usually… (voir plus) use shallow and simple additional layers on top of pre-trained models during fine-tuning. This work shows that this does not always need to be the case: with proper initialization and optimization, the benefits of very deep transformers can carry over to challenging tasks with small datasets, including Text-to-SQL semantic parsing and logical reading comprehension. In particular, we successfully train 48 layers of transformers, comprising 24 fine-tuned layers from pre-trained RoBERTa and 24 relation-aware layers trained from scratch. With fewer training steps and no task-specific pre-training, we obtain the state of the art performance on the challenging cross-domain Text-to-SQL parsing benchmark Spider. We achieve this by deriving a novel Data dependent Transformer Fixed-update initialization scheme (DT-Fixup), inspired by the prior T-Fixup work. Further error analysis shows that increasing depth can help improve generalization on small datasets for hard cases that require reasoning and structural understanding.
2021-08-01
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) (publié)
Aspect Sentiment Triplet Extraction (ASTE) aims to extract triplets from sentences, where each triplet includes an entity, its associated se… (voir plus)ntiment, and the opinion span explaining the reason for the sentiment. Most existing research addresses this problem in a multi-stage pipeline manner, which neglects the mutual information between such three elements and has the problem of error propagation. In this paper, we propose a Semantic and Syntactic Enhanced aspect Sentiment triplet Extraction model (S3E2) to fully exploit the syntactic and semantic relationships between the triplet elements and jointly extract them. Specifically, we design a Graph-Sequence duel representation and modeling paradigm for the task of ASTE: we represent the semantic and syntactic relationships between word pairs in a sentence by graph and encode it by Graph Neural Networks (GNNs), as well as modeling the original sentence by LSTM to preserve the sequential information. Under this setting, we further apply a more efficient inference strategy for the extraction of triplets. Extensive evaluations on four benchmark datasets show that S3E2 significantly outperforms existing approaches, which proves our S3E2's superiority and flexibility in an end-to-end fashion.
2021-08-01
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021 (publié)
A stereotype is an over-generalized belief about a particular group of people, e.g., Asians are good at math or African Americans are athlet… (voir plus)ic. Such beliefs (biases) are known to hurt target groups. Since pretrained language models are trained on large real-world data, they are known to capture stereotypical biases. It is important to quantify to what extent these biases are present in them. Although this is a rapidly growing area of research, existing literature lacks in two important aspects: 1) they mainly evaluate bias of pretrained language models on a small set of artificial sentences, even though these models are trained on natural data 2) current evaluations focus on measuring bias without considering the language modeling ability of a model, which could lead to misleading trust on a model even if it is a poor language model. We address both these problems. We present StereoSet, a large-scale natural English dataset to measure stereotypical biases in four domains: gender, profession, race, and religion. We contrast both stereotypical bias and language modeling ability of popular models like BERT, GPT-2, RoBERTa, and XLnet. We show that these models exhibit strong stereotypical biases. Our data and code are available at https://stereoset.mit.edu.
2021-08-01
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) (publié)