Section: Application Domains

Overview

NLP tools and methods have many possible domains of application. Some of then are already mature enough to be commercialized. They can be roughly classified in four groups:

• Human-computer interaction: mostly speech processing and text-to-speech, often in a dialogue context; today, commercial offers are limited to restricted domains (train tickets reservation...);

• Language writing aid: spelling, grammatical and stylistic correctors for text editors, controlled-language writing aids (e.g., for technical documents), memory-based translation aid, foreign language learning tools, as well as vocal dictation; related to this group lies the automatic correction of the output of OCR systems;

• Access to information: tools to enable a better access to information present in huge collections of texts (e.g., the Internet): automatic document classification, automatic document structuring, automatic summarizing, information acquisition and extraction, text mining, question-answering systems, as well as surface machine translation. Information access to speech archives through transcriptions is also an emerging field.

• Empirical linguistics: tools to explore language in an objective way (this is related, but not limited to corpus linguistics).

Alpage focuses on applications included in the three last points, such as information extraction and (linguistic and extra-linguistic) knowledge acquisition, text mining, spelling correction and empirical linguistics.