Institution
Company•Tel Aviv, Israel•
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.
Topics: Artificial neural network, Language model, Reinforcement learning, Machine translation, Social network
Papers published on a yearly basis
Papers
More filters
••
11 Jun 2019TL;DR: The authors showed that BERT's attention heads exhibit patterns such as attending to delimiter tokens, specific positional offsets, or broadly attending over the whole sentence, with heads in the same layer often exhibiting similar behaviors.
Abstract: Large pre-trained neural networks such as BERT have had great recent success in NLP, motivating a growing body of research investigating what aspects of language they are able to learn from unlabeled data. Most recent analysis has focused on model outputs (e.g., language model surprisal) or internal vector representations (e.g., probing classifiers). Complementary to these works, we propose methods for analyzing the attention mechanisms of pre-trained models and apply them to BERT. BERT’s attention heads exhibit patterns such as attending to delimiter tokens, specific positional offsets, or broadly attending over the whole sentence, with heads in the same layer often exhibiting similar behaviors. We further show that certain attention heads correspond well to linguistic notions of syntax and coreference. For example, we find heads that attend to the direct objects of verbs, determiners of nouns, objects of prepositions, and coreferent mentions with remarkably high accuracy. Lastly, we propose an attention-based probing classifier and use it to further demonstrate that substantial syntactic information is captured in BERT’s attention.
815 citations
••
22 Jan 2018TL;DR: In this paper, the task of making chit-chat more engaging by conditioning on profile information is addressed, and the resulting dialogue can be used to predict profile information about the interlocutors.
Abstract: Chit-chat models are known to have several problems: they lack specificity, do not display a consistent personality and are often not very captivating. In this work we present the task of making chit-chat more engaging by conditioning on profile information. We collect data and train models to (i)condition on their given profile information; and (ii) information about the person they are talking to, resulting in improved dialogues, as measured by next utterance prediction. Since (ii) is initially unknown our model is trained to engage its partner with personal topics, and we show the resulting dialogue can be used to predict profile information about the interlocutors.
808 citations
•
05 Dec 2016TL;DR: A simple neural model is explored, called CommNet, that uses continuous communication for fully cooperative tasks and the ability of the agents to learn to communicate amongst themselves is demonstrated, yielding improved performance over non-communicative agents and baselines.
Abstract: Many tasks in AI require the collaboration of multiple agents. Typically, the communication protocol between agents is manually specified and not altered during training. In this paper we explore a simple neural model, called CommNet, that uses continuous communication for fully cooperative tasks. The model consists of multiple agents and the communication between them is learned alongside their policy. We apply this model to a diverse set of tasks, demonstrating the ability of the agents to learn to communicate amongst themselves, yielding improved performance over non-communicative agents and baselines. In some cases, it is possible to interpret the language devised by the agents, revealing simple but effective strategies for solving the task at hand.
804 citations
••
26 Apr 2010TL;DR: Using user-supplied address data and the network of associations between members of the Facebook social network, an algorithm is introduced that predicts the location of an individual from a sparse set of located users with performance that exceeds IP-based geolocation.
Abstract: Geography and social relationships are inextricably intertwined; the people we interact with on a daily basis almost always live near us. As people spend more time online, data regarding these two dimensions -- geography and social relationships -- are becoming increasingly precise, allowing us to build reliable models to describe their interaction. These models have important implications in the design of location-based services, security intrusion detection, and social media supporting local communities.Using user-supplied address data and the network of associations between members of the Facebook social network, we can directly observe and measure the relationship between geography and friendship. Using these measurements, we introduce an algorithm that predicts the location of an individual from a sparse set of located users with performance that exceeds IP-based geolocation. This algorithm is efficient and scalable, and could be run on a network containing hundreds of millions of users.
785 citations
•
TL;DR: This article used a combination of known tricks that are rarely used together to train pre-trained word vector representations and achieved state-of-the-art performance on a number of NLP tasks.
Abstract: Many Natural Language Processing applications nowadays rely on pre-trained word representations estimated from large text corpora such as news collections, Wikipedia and Web Crawl. In this paper, we show how to train high-quality word vector representations by using a combination of known tricks that are however rarely used together. The main result of our work is the new set of publicly available pre-trained models that outperform the current state of the art by a large margin on a number of tasks.
784 citations
Authors
Showing all 7875 results
Name | H-index | Papers | Citations |
---|---|---|---|
Yoshua Bengio | 202 | 1033 | 420313 |
Xiang Zhang | 154 | 1733 | 117576 |
Jitendra Malik | 151 | 493 | 165087 |
Trevor Darrell | 148 | 678 | 181113 |
Christopher D. Manning | 138 | 499 | 147595 |
Robert W. Heath | 128 | 1049 | 73171 |
Pieter Abbeel | 126 | 589 | 70911 |
Yann LeCun | 121 | 369 | 171211 |
Li Fei-Fei | 120 | 420 | 145574 |
Jon Kleinberg | 117 | 444 | 87865 |
Sergey Levine | 115 | 652 | 59769 |
Richard Szeliski | 113 | 359 | 72019 |
Sanjeev Kumar | 113 | 1325 | 54386 |
Bruce Neal | 108 | 561 | 87213 |
Larry S. Davis | 107 | 693 | 49714 |