Vaksent
Vaksent is a sentiment analysis system.
Vaklipi
Vaklipi is a programming system that allows programs to be written in a natural language.
It supports a number of languages including English, French, German, Kannada, Tamil and Hindi.
It can be used to query databases and for semantic web related analyses.
Click here for a demo of Vaklipi.
The DAT is a product for the annotation of textual data by a distributed team.
It lowers the cost and improves the scalability of corpora annotation.
It can be used to create corpora for parsing (grammar annotations), transliteration, entity/relation/event extraction, and sentiment analysis.
Click here for a demo of the DAT.
Classifiers
Text classifiers (or text categorisers) can discover interesting properties in groups of words, be they sentences, paragraphs or pages of text. In other words, they can place a piece of text into one of a number of categories.
For example, most web email accounts now automatically mark unwanted email messages as 'Spam'. Classifiers are the Natural Language Processing tool used to perform that task.
We can develop classifiers for you, and we have a range of topic classifier products available for purchase.
Here are some of the kinds of classifiers we can develop for you or license to you:
- Topic classifiers can identify the theme of a news article, say Politics, Sports, Health or Entertainment.
- Language classifiers can identify the language of a piece of text.
- Sentiment classifiers can tell whether a comment is positive (appreciative) or negative (derogatory).
We have performed tests on some of these and can supply you with accuracy figures for your feasibility studies. We can also help you evaluate open-source frameworks for classification should they serve your needs better.
Text Analytics Solutions
We bring to the table a strong understanding of, and experience in, machine learning algorithms, especially Bayesian models and can help with:
- Developing resources like gazetteers, lexicons, morphological dictionaries, and classifiers
- Assisting with feature engineering for classifiers and clustering.
- Creating models for open frameworks like Weka (.arff files).
- Creating rules for GATE or other rule-based systems.
- Creating corpora.