Carabao Language Kit

Carabao Language Kit is a suite of tools and components which allow your applications to make sense of natural language, or convert text to bits of knowledge. Carabao emulates human linguistic abilities, such as text understanding, sense disambiguation, or translation from language to language.

	Linguistic Analyzers
	Digital Sonata Pty Ltd
	supported by provider
	Ask for Pricing

	Print
	Tell a friend
	Ask a question

What kind of applications can I build with Carabao?

You can:

ü Extract entities – either the standard set of persons / organizations / dates / etc. or much more complex combinations, such as, for example, medications of a specific kind, or Chinese names.

ü Obtain domains of discourse and map them to fragments of text. For example, not only you can categorize a document as pertaining to automotive and finance, but mark segments referring to automotive and those referring to finance.

ü Group keywords obtained by your search engine by meaning, lemmatizing or stemming them.

ü Build smarter search engines which can recognize and match inflected forms of the words in your language.

ü Build semantic and even cross-lingual indexes. For example, you can index content in Japanese and search it by entering English keywords, which will not be translated, but rather refer to their meaning, allowing for much higher accuracy.

ü Parse natural language queries.

ü Detect obscene words, explicit content, find stylistic hints such as author’s social and geographical origin.

ü Add punctuation to unpunctuated or partially punctuated content, such as ASR software output.

ü Rapidly build machine translation engines.

ü Analyse the suitability of content for machine translation.

What are the deployment scenarios of Carabao Language Kit?

Carabao Language Kit family contains:

ü COM objects SDK. These objects can be embedded in external Microsoft Windows © and Microsoft .NET ©based applications, either server-based or client-based.

ü Linguistic development suite of GUI tools. These tools are used to develop and test the linguistic logic either by the vendors, resellers, or deployment teams, or by the customers. They do not have to be deployed at the customer site.

ü Carabao Server, based on Windows Communication Foundation. Carabao Server provides a web service API to external web based applications. Carabao Server supports all the interfaces supported by Windows Communication Foundation:

o SOAP-based web services

o Federated web services

o RESTful web services

o Direct TCP/IP

o Direct UDP

o Any custom protocol linked to WCF framework

For standalone and client-based applications, it is advised to use the COM object SDKs. For web-based applications, or applications deployed in a large LAN or WAN, it is advised to use Carabao Server.

Customer Reviews:

There are yet no reviews for this product.
Please log in to write a review.

Use Cases

Travel Advisory

Situation: A travel advisory website aggregates news feeds. An alert needs to be sent to a supervising editor when a disease outbreak, or armed conflict is reported in a particular region.

Solution: Carabao DeepAnalyzer component processes the news feeds. The customer's source code searches the collection of ID numbers returned by Carabao for any kinds of 'diseases', or anything related to 'riots', 'conflicts' or 'terrorism'. If found, the relevant news feed is emailed to the supervisor. For example, out of 10,000 news articles received daily, the supervisor receives one or two alerts.

Note that there is no need to explicitly look for every disease or conflict; as the concepts are linked, the client source code only searches for a common parent, e.g. 'disease'.

Natural Language Query Parsing and Directory Semantic Search

Situation: A Yellow Pages directory is looking to expand their reach by providing a convenient and intuitive access via SMS interface to the users with mobile phones.

Solution: Carabao DeepAnalyzer component is used to parse the queries, and expand the criteria, if necessary. For example, “Asian restaurants” trigger a search not only for restaurants labelled as “Asian”, but also for Chinese, Japanese, Korean, Indian, and other Asian restaurants.

News Categorization

Situation: A news agency aggregates news feeds from different sources, and needs to assign labels according to geographical region(s) and relevant subject(s).

Solution: Carabao DeepAnalyzer is used to extract dominant domains of discourse and geographical information. The client application simply calls a method in Carabao DeepAnalyzer class to process the data and extract the associated domains of discourse. Carabao knows to distinguish between homonymous words based on the context, such as Paris in Texas and Paris in France.

Cross-lingual Enterprise Search

Situation: A multinational organisation keeps its content in many languages. Some of the content is duplicated, or processed multiple times only because the users can’t locate the foreign content.

Solution: A combination of Carabao DeepAnalyzer and Carabao Translation Server is used to build semantic cross-lingual indexes of the content. When searching, the user is requested to select the meaning of ambiguous words, and the search is launched both for traditional keywords, and the concepts. When the concepts match, and the content is not in the user’s language, Carabao Translation Server translates the results to the user.

This component is supported by provider.

Digital Sonata Pty Ltd

Digital Sonata specializes in natural language processing products and services. With our flagship family of products - Carabao Language Kit - and our consulting services, we assist our customers to overcome the technological challenges of the new millenium. Our team represents determination, experience, and diverse cultural backgrounds.