Facebook

About: Facebook is a company organization based out in Tel Aviv, Israel. It is known for research contribution in the topics: Artificial neural network & Language model. The organization has 7856 authors who have published 10906 publications receiving 570123 citations. The organization is also known as: facebook.com & FB.

Search and retrieval of objects in a social networking system

Abstract: A social networking system receives a query associated with a user and, in response, provides a combined result set comprising objects stored by a social networking system that match the query. The combined result set comprises multiple result sets obtained from different search algorithms. The various objects stored by the social networking system may be of different types representing different concepts, such as user objects, application objects, event objects, location objects, group objects, and hub/page objects, any of which may be included in the result set. The objects of the result set may be further filtered, ordered, and/or grouped based at least in part on known relationships of the user with the objects, such as geographic distances between locations associated with the user and the objects.

CamemBERT: a Tasty French Language Model

Abstract: Pretrained language models are now ubiquitous in Natural Language Processing. Despite their success, most available models have either been trained on English data or on the concatenation of data in multiple languages. This makes practical use of such models—in all languages except English—very limited. Aiming to address this issue for French, we release CamemBERT, a French version of the Bi-directional Encoders for Transformers (BERT). We measure the performance of CamemBERT compared to multilingual models in multiple downstream tasks, namely part-of-speech tagging, dependency parsing, named-entity recognition, and natural language inference. CamemBERT improves the state of the art for most of the tasks considered. We release the pretrained model for CamemBERT hoping to foster research and downstream applications for French NLP.

The Dialog State Tracking Challenge Series: A Review

Abstract: In a spoken dialog system, dialog state tracking refers to the task of correctly inferring the state of the conversation -- such as the user's goal -- given all of the dialog history up to that turn. Dialog state tracking is crucial to the success of a dialog system, yet until recently there were no common resources, hampering progress. The Dialog State Tracking Challenge series of 3 tasks introduced the first shared testbed and evaluation metrics for dialog state tracking, and has underpinned three key advances in dialog state tracking: the move from generative to discriminative models; the adoption of discriminative sequential techniques; and the incorporation of the speech recognition results directly into the dialog state tracker. This paper reviews this research area, covering both the challenge tasks themselves and summarizing the work they have enabled.

Unifying distillation and privileged information

Abstract: Distillation (Hinton et al., 2015) and privileged information (Vapnik & Izmailov, 2015) are two techniques that enable machines to learn from other machines. This paper unifies these two techniques into generalized distillation, a framework to learn from multiple machines and data representations. We provide theoretical and causal insight about the inner workings of generalized distillation, extend it to unsupervised, semisupervised and multitask learning scenarios, and illustrate its efficacy on a variety of numerical simulations on both synthetic and real-world data.