Multilingual Open Information Extraction: Challenges and Opportunities

Abstract

The number of documents published on the Web in languages other than English grows every year. As a consequence, the need to extract useful information from different languages increases, highlighting the importance of research into Open Information Extraction (OIE) techniques. Different OIE methods have dealt with features from a unique language; however, few approaches tackle multilingual aspects. In those approaches, multilingualism is restricted to processing text in different languages, rather than exploring cross-linguistic resources, which results in low precision due to the use of general rules. Multilingual methods have been applied to numerous problems in Natural Language Processing, achieving satisfactory results and demonstrating that knowledge acquisition for a language can be transferred to other languages to improve the quality of the facts extracted. We argue that a multilingual approach can enhance OIE methods as it is ideal to evaluate and compare OIE systems, and therefore can be applied to the collected facts. In this work, we discuss how the transfer knowledge between languages can increase acquisition from multilingual approaches. We provide a roadmap of the Multilingual Open IE area concerning state of the art studies. Additionally, we evaluate the transfer of knowledge to improve the quality of the facts extracted in each language. Moreover, we discuss the importance of a parallel corpus to evaluate and compare multilingual systems.

Multilingual Epidemic Event Extraction : From simple Classification methods to Open Information Extraction (OIE) and Ontology

“…The entities have numerous applications in building knowledge representation models that report relations between words, such as ontologies, semantic networks.. In this work, we will investigate the area of multilingual open information extraction for the Portuguese, English and other languages (Claro et al, 2019). The extracted relations will be passed to a named entity recognition layer.…”

Clustering and Bootstrapping Based Framework for News Knowledge Base Completion

“…In contrast to monolingual systems, systems that extract the knowledge from sources of different languages are considered as multilingual systems. Most of the multilingual systems consider the sources in foreign languages [15,6,16,17,18,5] and only [19] extracts the Indian language Hindi along with foreign languages. However, these systems are based on either using language-specific processing tools or translating the entire documents into English.…”

“…Nevertheless, these methods are to be modified to cluster the articles across the languages. Even though open information extraction (OIE) tools like ArgOE are best suited to extract the information from multiple languages, they are developed to be used with foreign languages like English, Spanish, and Portuguese [5]. A straightforward way to solve the problem which is adopted by the existing works is to translate the entire document written in a target language like Hindi to source language English [6].…”

Topic Modeling for Amharic User Generated Texts

“…The availability of such content provides opportunities and challenges. Various text analytics applications can be developed including topic summarization [2], text classification [3], information extraction [4,5], sentiment analysis [6,7], lexicon building [8][9][10] and hate speech detection [11,12], just to name a few. This allows companies and governments to increase the quality of services, increase profits and decrease their costs.…”