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: Computer science & Artificial neural network. The organization has 7856 authors who have published 10906 publications receiving 570123 citations. The organization is also known as: facebook.com & FB.
Topics: Computer science, Artificial neural network, Language model, Context (language use), Reinforcement learning
Papers published on a yearly basis
Papers
More filters
•
15 Apr 2009TL;DR: In this article, a method and apparatus for updating the vocabulary of a speech translation system for translating a first language into a second language including written and spoken words is described, which includes adding a new word in the first language to a first recognition lexicon and associating a description with the new word, wherein the description contains pronunciation and word class information.
Abstract: A method and apparatus are provided for updating the vocabulary of a speech translation system for translating a first language into a second language including written and spoken words. The method includes adding a new word in the first language to a first recognition lexicon of the first language and associating a description with the new word, wherein the description contains pronunciation and word class information. The new word and description are then updated in a first machine translation module associated with the first language. The first machine translation module contains a first tagging module, a first translation model and a first language module, and is configured to translate the new word to a corresponding translated word in the second language. Optionally, the invention may be used for bidirectional or multi-directional translation.
285 citations
••
Harvard University1, Intel2, Google3, Microsoft4, Facebook5, Nvidia6, Qualcomm7, Stanford University8, Tencent9, MediaTek10, Synopsys11, University of Toronto12, Xilinx13, Centaur Technology14, Alibaba Group15, General Motors16
TL;DR: This paper presents the benchmarking method for evaluating ML inference systems, MLPerf Inference, and prescribes a set of rules and best practices to ensure comparability across systems with wildly differing architectures.
Abstract: Machine-learning (ML) hardware and software system demand is burgeoning. Driven by ML applications, the number of different ML inference systems has exploded. Over 100 organizations are building ML inference chips, and the systems that incorporate existing models span at least three orders of magnitude in power consumption and five orders of magnitude in performance; they range from embedded devices to data-center solutions. Fueling the hardware are a dozen or more software frameworks and libraries. The myriad combinations of ML hardware and ML software make assessing ML-system performance in an architecture-neutral, representative, and reproducible manner challenging. There is a clear need for industry-wide standard ML benchmarking and evaluation criteria. MLPerf Inference answers that call. In this paper, we present our benchmarking method for evaluating ML inference systems. Driven by more than 30 organizations as well as more than 200 ML engineers and practitioners, MLPerf prescribes a set of rules and best practices to ensure comparability across systems with wildly differing architectures. The first call for submissions garnered more than 600 reproducible inference-performance measurements from 14 organizations, representing over 30 systems that showcase a wide range of capabilities. The submissions attest to the benchmark’s flexibility and adaptability.
284 citations
•
05 Feb 2015TL;DR: In this paper, a real-time search engine compiles the results of the user-term index query and retrieves the stored posts from the forward index, which can then be ranked and cached before presentation to the searching user.
Abstract: Indexing and retrieving real time content in a social networking system is disclosed. A user-term index includes user-term partitions, each user-term partition comprising temporal databases. As a post is received from a user, a user identifier, a post identifier, and a post is extracted. An object store communicatively coupled to a temporal database for recently received content is queried to determine whether terms in the post has already been stored. A term identifier is stored in the user-term index with the user and post identifiers. A forward index stores the post by post identifier. Responsive to a search query, the user-term index is searched by the user's connections and the terms. A real time search engine compiles the results of the user-term index query and retrieves the stored posts from the forward index. The search results may then be ranked and cached before presentation to the searching user.
282 citations
•
01 Jan 2019TL;DR: Levenshtein Transformer is developed, a new partially autoregressive model devised for more flexible and amenable sequence generation and a set of new training techniques dedicated at them, effectively exploiting one as the other's learning signal thanks to their complementary nature.
Abstract: Modern neural sequence generation models are built to either generate tokens step-by-step from scratch or (iteratively) modify a sequence of tokens bounded by a fixed length. In this work, we develop Levenshtein Transformer, a new partially autoregressive model devised for more flexible and amenable sequence generation. Unlike previous approaches, the basic operations of our model are insertion and deletion. The combination of them facilitates not only generation but also sequence refinement allowing dynamic length changes. We also propose a set of new training techniques dedicated at them, effectively exploiting one as the other's learning signal thanks to their complementary nature. Experiments applying the proposed model achieve comparable or even better performance with much-improved efficiency on both generation (e.g. machine translation, text summarization) and refinement tasks (e.g. automatic post-editing). We further confirm the flexibility of our model by showing a Levenshtein Transformer trained by machine translation can straightforwardly be used for automatic post-editing.
280 citations
••
TL;DR: The Social Connectedness Index is a new measure of social connectedness at the US county level based on friendship links on Facebook, the global online social networking service, which provides the first comprehensive measure of friendship networks at a national level.
Abstract: Social networks can shape many aspects of social and economic activity: migration and trade, job-seeking, innovation, consumer preferences and sentiment, public health, social mobility, and more. In turn, social networks themselves are associated with geographic proximity, historical ties, political boundaries, and other factors. Traditionally, the unavailability of large-scale and representative data on social connectedness between individuals or geographic regions has posed a challenge for empirical research on social networks. More recently, a body of such research has begun to emerge using data on social connectedness from online social networking services such as Facebook, LinkedIn, and Twitter. To date, most of these research projects have been built on anonymized administrative microdata from Facebook, typically by working with coauthor teams that include Facebook employees. However, there is an inherent limit to the number of researchers that will be able to work with social network data through such collaborations. In this paper, we therefore introduce a new measure of social connectedness at the US county level. Our Social Connectedness Index is based on friendship links on Facebook, the global online social networking service. Specifically, the Social Connectedness Index corresponds to the relative frequency of Facebook friendship links between every county-pair in the United States, and between every US county and every foreign country. Given Facebook's scale as well as the relative representativeness of Facebook's user body, these data provide the first comprehensive measure of friendship networks at a national level.
279 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 |