IBM Unraveling Language Patterns is a cloud service implementing the greedy augmented sequential patterns algorithm - an algorithm for automatically extracting patterns that characterize subtle linguistic phenomena. To that end, IBM Unraveling Language Patterns augments each term of input text with multiple layers of linguistic information. These different facets of the text terms are systematically combined to reveal rich patterns.
For example, in the context of argumentation mining, each of the following sentences includes a claim for a [topic]:
- Opponents often argue that the open primary is unconstitutional. [Open Primaries]
- Prof. Smith suggested that affirmative action devalues the accomplishments of discriminated groups. [Affirmative Action]
- The majority stated that the First Amendment does not guarantee the right to offend others. [Freedom of Speech]
These sentences share almost no words in common, however, they are similar at a more abstract level. A human observer may notice the following underlying common structure, or pattern:
[someone][argue/suggest/state][that][topic term][sentiment term].
IBM Unraveling Language Patterns aims to automatically capture such underlying structures of the given data. In the above examples, it finds the pattern
where [express] stands for all its (in)direct hyponyms, and [noun,topic] means a noun which is also related to the topic.
We incorporated the Unraveling Language Patterns algorithm inside an online service that can learn the linguistic patterns associated with your input texts. To train the service, you'll be asked to input some examples of sentences that exhibit the target linguistic phenomenon you are interested in, along with examples of text that do NOT exemplify it. The service will analyze the sentences and learn patterns that capture the common structure of such sentences. Following that, it will be able to recognize these patterns in new texts and thus detect sentences that exhibit the target linguistic phenomenon you are looking for.
To access the service, please fill in your e-mail address, select "I agree" and click the Get My Key! button below.