Use MeaningCloud API with the GATE plug-in

In our attempt to make MeaningCloud API the easiest way to use semantics in your application, today we are proud to present our latest development, a MeaningCloud plug-in for GATE.

GATE (General Architecture for Text Engineering) is an open-source workbench for text engineering that makes use of any kind of language processing component, from document crawling to search, and intelligent semantic annotations in particular.

Benefits for GATE and MeaningCloud API users

The plug-in provides GATE users a new set of multilingual functionalities, from parsing to entity extraction and sentiment analysis. For MeaningCloud users it would mean an easier and quicker method to prototype full applications including crawling, post-processing or indexing on annotated documents.  Besides, if you’re familiar with JAPE rules, it would enable to post-process, mix and match annotations from different processing resources for more complex pipelines. Finally, GATE is ideal for sharing and evaluating pipelines between team members, which increases productivity and produces more accurate results.

GATE - general Text processing architecture logo

GATE Developer is an IDE for language applications, a graphical interactive tool that supports the development of software applications that include language processing components. GATE Developer alredy provides basic tools for corpus annotation, document preparation, text preprocessing and evaluation as well as ANNIE, a pipeline for extracting information in English. Moreover, through the plug-in system you can plug and play components to integrate additional functionalities for crawling, storing annotations or search.

With the new MeaningCloud GATE plug-in we offer a new set of tools (Processing Resources) which can be integrated into your pipelines and are capable of accurate and detailed language annotations, from lemmatization and parsing to sentiment analysis. Besides, as MeaningCloud supports English, Spanish, Portuguese, French and Catalan, they enable a whole new range of options for multilingual processing in GATE.

MeaningCloud Processing Resources

The plug-in integrates the popular MeaningCloud Core API, our basic building block of language processing tools:plugin tree

  • Sentiment Analysis API – Detects sentiment polarity (positive, negative, neutral) and subjectivity from any document, including tweets and Facebook posts. It also detects relevant entities and concepts and their associated sentiment.
  • Topics Extraction API – Extracts topics and their relevance in a document. If you need to identify Named Entities, concepts, temporal expressions, money expressions, phone numbers, etc. this is your API. It also provides additional information for each one of these types. For instance, entities include a detailed type and links to relevant Wikipedia and Linked Data resources. For time and money expression we provide normalization and resolution.
  • Text Classification API – Performs document classification in different categorization schemas. IPTC subject codes for news provide a standard thematic classification in 17 broad categories, as well as detailed categorization up to hundreds.
  • Lemmatization, PoS Tagging and Parsing API – Adds information about the lemmas for highly inflected languages like Spanish, detailed part of speech tagging and constituent parsing.
  • Language Identification API – Identifies the language of a document among 68 different world languages.

Trendminer EU project using GATE – MeaningCloud plug-in

GATE plug-in has been instrumental for S|ngular Meaning, the company that develops MeaningCloud, in collaborating in larger research projects like Trendminer. Trendminer, an EU-funded project, aims to develop cross-language tools that help to detect trends in large scale stream media like social networks. Use cases include financial decisions support, political trends, mood and psychological trends and, finally, medicine and drug side effects monitoring. Daedalus works closely with the UC3M team to engineer the tools for the drug monitoring use case. GATE, provided by the University of Sheffield, which is a partner in the consortium too, has been the key for building more complex workflows.

Install the plug-in

Are you already a GATE user? You can install the plug-in by adding our repository.

Moreover, the plug-in is open-source and got its own Github project, so you can also contribute with patches and improvements.

About César De Pablo

Senior software engineer at MeaningCloud. I felt in love with language fifteen years ago. Since then, learning every day a bit about natural and artificial languages, big data and building ideas into software.

Leave a Reply

Your email address will not be published. Required fields are marked *