Pular para o conteúdo principal

BabelNet & World Atlas - Estado da Arte KG

A huge multilingual knowledge graph

Knowledge graphs are the 21st century counterpart of dictionaries in previous centuries. They organize knowledge into a coherent network of meanings and they enable Artificial Intelligence applications which exploit this knowledge to perform text understanding.

WordAtlas is the next-generation multilingual knowledge graph. It greatly enhances BabelNet®, the award-winning multilingual semantic network, thanks to the know-how of years of research in computational linguistics in Prof. Roberto Navigli’s lab at the Sapienza University of Rome.

What makes WordAtlas special is its linkage between concepts and words in hundreds of languages: WordAtlas provides millions of lexicalizations for each language, from common nouns, adjectives, verbs and adverbs, to hundreds of thousands of technical terms and millions of named entities, such as people, locations, organizations and products.

Knowledge graph APIs

WordAtlas comes with high-performance API for Python and Java (therefore supporting all JVM-based languages, such as Kotlin, Scala and Groovy). The API enables access to the multilingual knowledge graph and includes a wide range of methods for:

    searching by word and concept id;
    retrieving information about concepts and entities, such as multilingual lexicalizations (synonyms), definitions, examples, semantic relations (e.g. hypernymy, meronymy, relatedness, born-in, etc.), links to images and much more;
    support of functional programming, enabling the use of lambda functions for querying and retrieval purposes.

The Python API mimics the organization of the Java API, therefore making it easy to switch from one to the other. The APIs support both online and offline querying of WordAtlas and come with professional support.

If you are a Ph.D. student or a researcher affiliated with a research institution and you need to use the BabelNet indices for your non-commercial research project, please make a request for downloading the indices through the Sapienza NLP resource repository.

IMPORTANT: The email used in your BabelNet account registration must belong to your research institution.
NOTE: Each request is subject to approval and fulfillment is based on the above conditions.

https://babelnet.org/downloads
https://babelscape.com/wordatlas#api
https://babelnet.org/how-to-use
 

Marcadores:

Comentários

Postar um comentário

Sinta-se a vontade para comentar. Críticas construtivas são sempre bem vindas.

Postagens mais visitadas deste blog

Connected Papers: Uma abordagem alternativa para revisão da literatura

Durante um projeto de pesquisa podemos encontrar um artigo que nos identificamos em termos de problema de pesquisa e também de solução. Então surge a vontade de saber como essa área de pesquisa se desenvolveu até chegar a esse ponto ou quais desdobramentos ocorreram a partir dessa solução proposta para identificar o estado da arte nesse tema. Podemos seguir duas abordagens:  realizar uma revisão sistemática usando palavras chaves que melhor caracterizam o tema em bibliotecas digitais de referência para encontrar artigos relacionados ou realizar snowballing ancorado nesse artigo que identificamos previamente, explorando os artigos citados (backward) ou os artigos que o citam (forward)  Mas a ferramenta Connected Papers propõe uma abordagem alternativa para essa busca. O problema inicial é dado um artigo de interesse, precisamos encontrar outros artigos relacionados de "certa forma". Find different methods and approaches to the same subject Track down the state of the art rese...
3 comentários
Leia mais

Knowledge Graph Embedding with Triple Context - Leitura de Abstract

  Jun Shi, Huan Gao, Guilin Qi, and Zhangquan Zhou. 2017. Knowledge Graph Embedding with Triple Context. In Proceedings of the 2017 ACM on Conference on Information and Knowledge Management (CIKM '17). Association for Computing Machinery, New York, NY, USA, 2299–2302. https://doi.org/10.1145/3132847.3133119 ABSTRACT Knowledge graph embedding, which aims to represent entities and relations in vector spaces, has shown outstanding performance on a few knowledge graph completion tasks. Most existing methods are based on the assumption that a knowledge graph is a set of separate triples, ignoring rich graph features, i.e., structural information in the graph. In this paper, we take advantages of structures in knowledge graphs, especially local structures around a triple, which we refer to as triple context. We then propose a Triple-Context-based knowledge Embedding model (TCE). For each triple, two kinds of structure information are considered as its context in the graph; one is the out...
Postar um comentário
Leia mais

KnOD 2021

Beyond Facts: Online Discourse and Knowledge Graphs A preface to the proceedings of the 1st International Workshop on Knowledge Graphs for Online Discourse Analysis (KnOD 2021, co-located with TheWebConf’21) https://ceur-ws.org/Vol-2877/preface.pdf https://knod2021.wordpress.com/   ABSTRACT Expressing opinions and interacting with others on the Web has led to the production of an abundance of online discourse data, such as claims and viewpoints on controversial topics, their sources and contexts . This data constitutes a valuable source of insights for studies into misinformation spread, bias reinforcement, echo chambers or political agenda setting. While knowledge graphs promise to provide the key to a Web of structured information, they are mainly focused on facts without keeping track of the diversity, connection or temporal evolution of online discourse data. As opposed to facts, claims are inherently more complex. Their interpretation strongly depends on the context and a vari...
2 comentários
Leia mais