Professional Documents
Culture Documents
Applications of parsing is very large area. It expands from simple phrase finding, e.g. for proper name
recognition, to deep semantic analysis of text, e.g. for information extraction, machine translation or
question answering system ...
+ Proper Noun Recognition and Classification:
Recognizing and classifying proper nouns involves determining which strings in a text name individuals
and categorizing which classes these individuals fall into. Typical name classes include organizations,
persons, locations, dates, monetary amounts ,.... The task is made difficult by the unpredictable length
of names (company names can be twelve or more words long), ambiguity between name classes
(Ford can be a company, a person, or a location), embedding, where e.g. a location name occurs within
an organization name, variant forms, and unreliability of capitalization as a cue, e.g. in headlines in
English and everywhere in German.
+ Information retrieval:
Information retrieval(IR) system aim to provide mechanisms for
users to find out information in large electronic collections(except
audio, images). Typically this involves retrieving that subset of
documents (or portions thereof) in the collection which is
deemed relevant by the system in relation to a query issued by
the user. The query may be anything from a single word to a
paragraph or more of text expressing the user's area of interest.
With the proliferation of on-line textual information (especially
the World Wide Web) IR technology has become of significant
interest both as a research topic and in applications (cf. the
sudden emergence of commercially supported Web search
engines).
+ Intent mining:
Intent mining is a sub-area of data mining. It assess the attitude of the document author with respect to
a given subject, e.g. problem(description, solution), agreement(assent, dissent), preference(likes,
dislikes), statement(claim, denial).
+Options mining:
Daily human create a bunch of billions of information in Internet. The information can be published in
personal blog, article, website ... In the billions of those information, we have many personal opinions. It
is very worth if we can parse, process, stored those ones in the way easy for searching.
+ Machine translation: