Abstract: According to one embodiment of the invention, a method includes generating a person-name Information Gain (IG)-Tree and a relation IG-Tree from annotated data. The method also includes tagging and partial parsing of an input document. The names of the persons are extracted within the input document using the person-name IG-tree. Additionally, names of organizations are extracted within the input document. The method also includes extracting entity names that are not names of persons and organizations within the input document. Further, the relations between the identified entity names are extracted using the relation-IG-tree.

Abstract: According to one embodiment of the invention, a method includes generating a person-name Information Gain (IG)-Tree and a relation IG-Tree from annotated data. The method also includes tagging and partial parsing of an input document. The names of the persons are extracted within the input document using the person-name IG-tree. Additionally, names of organizations are extracted within the input document. The method also includes extracting entity names that are not names of persons and organizations within the input document. Further, the relations between the identified entity names are extracted using the relation-IG-tree.

Abstract: According to one embodiment of the invention, a method includes generating a person-name Information Gain (IG)-Tree and a relation IG-Tree from annotated data. The method also includes tagging and partial parsing of an input document. The names of the persons are extracted within the input document using the person-name IG-tree. Additionally, names of organizations are extracted within the input document. The method also includes extracting entity names that are not names of persons and organizations within the input document. Further, the relations between the identified entity names are extracted using the relation-IG-tree.

Abstract: According to one embodiment of the invention, a method includes generating a person-name Information Gain (IG)-Tree and a relation IG-Tree from annotated data. The method also includes tagging and partial parsing of an input document. The names of the persons are extracted within the input document using the person-name IG-tree. Additionally, names of organizations are extracted within the input document. The method also includes extracting entity names that are not names of persons and organizations within the input document. Further, the relations between the identified entity names are extracted using the relation-IG-tree.

Abstract: According to one embodiment of the invention, a method classifying a number of noun phrases in a first text passage and a second text passage into a number of classifications. The method also includes determining a similarity between a noun phrase from the first text passage and a noun phase from the second text passage for each of the noun phrases of a same classification. Additionally, a similarity between a sentence from the first text passage and a sentence from the second text passage is determined for each of the sentences in the first and second text passages based on similarities between the noun phrases. The method also includes determining a similarity between the first text passage and the second text passage based on a similarity between sentences.

Abstract: According to one embodiment of the invention, a method classifying a number of noun phrases in a first text passage and a second text passage into a number of classifications. The method also includes determining a similarity between a noun phrase from the first text passage and a noun phase from the second text passage for each of the noun phrases of a same classification. Additionally, a similarity between a sentence from the first text passage and a sentence from the second text passage is determined for each of the sentences in the first and second text passages based on similarities between the noun phrases. The method also includes determining a similarity between the first text passage and the second text passage based on a similarity between sentences.

Abstract: According to one embodiment of the invention, a method classifying a number of noun phrases in a first text passage and a second text passage into a number of classifications. The method also includes determining a similarity between a noun phrase from the first text passage and a noun phase from the second text passage for each of the noun phrases of a same classification. Additionally, a similarity between a sentence from the first text passage and a sentence from the second text passage is determined for each of the sentences in the first and second text passages based on similarities between the noun phrases. The method also includes determining a similarity between the first text passage and the second text passage based on a similarity between sentences.

Abstract: According to one embodiment of the invention, a method classifying a number of noun phrases in a first text passage and a second text passage into a number of classifications. The method also includes determining a similarity between a noun phrase from the first text passage and a noun phase from the second text passage for each of the noun phrases of a same classification. Additionally, a similarity between a sentence from the first text passage and a sentence from the second text passage is determined for each of the sentences in the first and second text passages based on similarities between the noun phrases. The method also includes determining a similarity between the first text passage and the second text passage based on a similarity between sentences.

Abstract: According to one embodiment of the invention, a method classifying a number of noun phrases in a first text passage and a second text passage into a number of classifications. The method also includes determining a similarity between a noun phrase from the first text passage and a noun phase from the second text passage for each of the noun phrases of a same classification. Additionally, a similarity between a sentence from the first text passage and a sentence from the second text passage is determined for each of the sentences in the first and second text passages based on similarities between the noun phrases. The method also includes determining a similarity between the first text passage and the second text passage based on a similarities between sentences.

Abstract: A method and apparatus for parsing a plurality of documents, selecting paragraphs from the documents through subsuming relation calculation, and rewriting the selected paragraphs into a summary is disclosed.

Abstract: According to one embodiment of the invention, a method includes receiving a search term for a query. The method also includes searching a network of concept terms for terms related to the search term. Additionally, the query is reformulated using the search term and the related terms. A local database is searched for data terms that match the search term and the related terms. The data terms are from documents residing on websites located on servers across a network. Moreover, the method includes retrieving the documents from the websites whose data terms match the search term and the related terms.

Abstract: A method for entity name and jargon term recognition and extraction. An embodiment of the present invention uses a suffix tree data structure to determine frequently occurring phrases. In one embodiment text to be analyzed is preprocessed. The text is then separated into clauses and a suffix tree is created for the text. The suffix tree is used to determine repetitious segments. Unrecognized text fragment, occurring with a high frequency, have a comparably high probability of being a name entity or jargon term. The set of repetitious segments is then filtered to obtain a set of possible entity names and jargon terms.

Abstract: Methods and apparatuses for processing speech data are described herein. In one aspect of the invention, an exemplary method includes providing sufficient limited domain related texts, performing text processing on the limited domain related texts, generating recording scripts corresponding to the limited domain related texts, recording the recording scripts into a first speech file, performing speech processing on the first speech file, generating second speech files based on the first speech file, and creating a database for storing the second speech files. Other methods and apparatuses are also described.

Abstract: A method for entity name and jargon term recognition and extraction. An embodiment of the present invention uses a suffix tree data structure to determine frequently occurring phrases. In one embodiment text to be analyzed is preprocessed. The text is then separated into clauses and a suffix tree is created for the text. The suffix tree is used to determine repetitious segments. Unrecognized text fragment, occurring with a high frequency, have a comparably high probability of being a name entity or jargon term. The set of repetitious segments is then filtered to obtain a set of possible entity names and jargon terms.