• Aucun résultat trouvé

Structured Data Meets News

N/A
N/A
Protected

Academic year: 2022

Partager "Structured Data Meets News"

Copied!
1
0
0

Texte intégral

(1)

Structured Data Meets News

Cong Yu (Google)

Abstract

The news ecosystem is going through profound changes that will have long-lasting impact on our civic society. One of the key challenges in the news ecosystem is how to encourage content consumption that will bring informational values to the users instead of purely consuming users' attention via any (i.e., unhealthy) means necessary. As part of the talk, I will describe how structured data can play an important role in helping users consume content in a more healthy way and present my long term vision on how our research community can contribute to this important cause. In the rest of the talk, I will describe various technical efforts, within the Structured Data Research Group at Google AI and in partnership with many product teams, on improving news consumption at Google. One specific example is the question and answering summarization of news articles, where we combine structured data, machine learning, and natural language processing techniques to help users understand news articles quickly.

Short Bio:

Cong Yu is a research scientist and manager at Google Research in New York City and leads the Structured Data Research Group. The group’s mission is to understand and leverage structured data on the Web to enhance user experience for Google products and has been responsible for several impactful products such as Web Tables, Structured Snippets, and Fact Checking at Google. Currently, his group focuses on technical research for news and has been partnering with journalists and policy advisors to combat online misinformation and polarization and to improve news consumption. His research interests are structured data exploration and mining, computational journalism, machine learning, natural language processing, and scalable data analysis. He was a keynote speaker for VLDB 2019 and twice served as an industrial program co-chair for VLDB (2014 and 2018). Outside of Google, he periodically teaches at NYU Courant's Department of Computer Science. Before Google, Cong was a Research Scientist at Yahoo! Research, also in NYC. He has a PhD from the University of Michigan, Ann Arbor, advised by Prof. H.V. Jagadish.

ceur-ws.org/Vol-2399/keynote2.pdf

Références

Documents relatifs

In the specialized taxonomic journals (4113 studies), molecular data were widely used in mycology, but much less so in botany and zoology (Supplementary Appendix S7 available on

Two key ideas that we defend here are the following: first, the task of NLG can be regarded as the translation between a natural language and a formal meaning representation,

Flair: An easy-to-use framework for state-of-the-art NLP. Contextual string embeddings for se- quence labeling. To- wards Scalable Hybrid Stores: Constraint-Based Rewriting to

In this example, in order to infer the correct answer, one has to go down the ranked list, gather and encode facts, even those that are not immediately relevant to the question,

Apart from the technical differences existing between KGs and databases, they still share the same properties hold by any structured resource: a Data Representation Language

Statistical bureaus and environmental agencies, such as the UK Office of National Statistics (ONS) and the UK Department for Environmental, Food and Rural Affairs) (Defra),

By defining a sliding time window of size 1 (validity of 1 time slice) over the stream of requests, the join assigns exactly one set of article IDs to each request

Identified semantic units from the user’s question are translated into a machine- readable query (technical query), which is a graph composed of objects and constraints described in