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
Characterizing Idioms: Conventionality and Contingency
Idioms are unlike most phrases in two important ways. First, words in an idiom have non-canonical meanings. Second, the non-canonical meanin… (voir plus)gs of words in an idiom are contingent on the presence of other words in the idiom. Linguistic theories differ on whether these properties depend on one another, as well as whether special theoretical machinery is needed to accommodate idioms. We define two measures that correspond to the properties above, and we show that idioms fall at the expected intersection of the two dimensions, but that the dimensions themselves are not correlated. Our results suggest that introducing special machinery to handle idioms may not be warranted.
2022-05-01
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (publié)
Recent work has shown pre-trained language models capture social biases from the large amounts of text they are trained on. This has attract… (voir plus)ed attention to developing techniques that mitigate such biases. In this work, we perform an empirical survey of five recently proposed bias mitigation techniques: Counterfactual Data Augmentation (CDA), Dropout, Iterative Nullspace Projection, Self-Debias, and SentenceDebias. We quantify the effectiveness of each technique using three intrinsic bias benchmarks while also measuring the impact of these techniques on a model’s language modeling ability, as well as its performance on downstream NLU tasks. We experimentally find that: (1) Self-Debias is the strongest debiasing technique, obtaining improved scores on all bias benchmarks; (2) Current debiasing techniques perform less consistently when mitigating non-gender biases; And (3) improvements on bias benchmarks such as StereoSet and CrowS-Pairs by using debiasing strategies are often accompanied by a decrease in language modeling ability, making it difficult to determine whether the bias mitigation was effective.
2022-05-01
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (publié)
Machine learning is vulnerable to possible incorrect classification of cases that are out of the distribution observed during training and c… (voir plus)alibration
2022-05-01
2022 IEEE/ACM 1st International Conference on AI Engineering – Software Engineering for AI (CAIN) (published)
Machine learning is vulnerable to possible incorrect classification of cases that are out of the distribution observed during training and c… (voir plus)alibration
2022-05-01
2022 IEEE/ACM 1st International Conference on AI Engineering – Software Engineering for AI (CAIN) (publié)
The ability to integrate context, including perceptual and temporal cues, plays a pivotal role in grounding the meaning of a linguistic utte… (voir plus)rance. In order to measure to what extent current vision-and-language models master this ability, we devise a new multimodal challenge, Image Retrieval from Contextual Descriptions (ImageCoDe). In particular, models are tasked with retrieving the correct image from a set of 10 minimally contrastive candidates based on a contextual description.As such, each description contains only the details that help distinguish between images.Because of this, descriptions tend to be complex in terms of syntax and discourse and require drawing pragmatic inferences. Images are sourced from both static pictures and video frames.We benchmark several state-of-the-art models, including both cross-encoders such as ViLBERT and bi-encoders such as CLIP, on ImageCoDe.Our results reveal that these models dramatically lag behind human performance: the best variant achieves an accuracy of 20.9 on video frames and 59.4 on static pictures, compared with 90.8 in humans.Furthermore, we experiment with new model variants that are better equipped to incorporate visual and temporal context into their representations, which achieve modest gains. Our hope is that ImageCoDE will foster progress in grounded language understanding by encouraging models to focus on fine-grained visual differences.
2022-05-01
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (publié)
Recent research analyzing the sensitivity of natural language understanding models to word-order perturbations has shown that neural models … (voir plus)are surprisingly insensitive to the order of words.In this paper, we investigate this phenomenon by developing order-altering perturbations on the order of words, subwords, and characters to analyze their effect on neural models’ performance on language understanding tasks.We experiment with measuring the impact of perturbations to the local neighborhood of characters and global position of characters in the perturbed texts and observe that perturbation functions found in prior literature only affect the global ordering while the local ordering remains relatively unperturbed.We empirically show that neural models, invariant of their inductive biases, pretraining scheme, or the choice of tokenization, mostly rely on the local structure of text to build understanding and make limited use of the global structure.
2022-05-01
Findings of the Association for Computational Linguistics: ACL 2022 (publié)
A smart application in sensing is mainly powered by a two-stage process comprising sensing (collect data) and computing (process data). Whil… (voir plus)e the sensing stage is typically performed locally through a dedicated Internet of Things infrastructure, the computing stage may require a powerful infrastructure in the cloud. However, when connectivity is poor and low latency becomes a requirement — as in emergency response and disaster relief operations — edge computing and ad hoc cloud paradigms come in support to keep the computing stage locally. Being local network connectivity and data processing limited, it is vital to properly optimize how the computing workload will be consumed by the local ad hoc cloud. For this purpose, we present and evaluate the swarm-powered Optimized 3D Mapping Pipeline (OptiMaP) for emergency response 3D mapping missions, which is implemented as a collaborative embedded Robot Operating System (ROS) application integrating an ad hoc telecommunication middleware.We simulate — with Software-In-The-Loop — realistic 3D mapping missions comprising up to 5 drones and 363 images covering 0.293km2. We show how the completion times of mapping missions carried out in a typical centralized manner can be dramatically reduced by two versions of the OptiMaP framework powered, respectively, by a variable neighborhood search heuristic and a greedy method.
2022-05-01
International Conference on Distributed Computing in Sensor Systems (published)