Sentence processing apparatus and method thereof,utilizing dictionaries to interpolate elliptic characters or symbols

• US 6,173,253 B1
• Filed: 03/24/1999
• Issued: 01/09/2001
• Est. Priority Date: 03/30/1998
• Status: Expired due to Fees

• Current Assignee: Hitachi, Ltd.
• Original Assignee: Hitachi, Ltd.
• Inventors: Abe, Keiko, Miura, Masaki, Yokota, Toshimi, Katsura, Koyo, Kuzunuki, Soshiro
• Primary Examiner(s): Thomas, Joseph
• Application Number:
  US09/275,025
• Time in Patent Office: 657 Days
• Field of Search: 704/10, 704/9, 704/8, 704/1, 704/2, 704/3, 704/7, 704/257, 704/251, 704/252, 704/255, 704/270, 707/531, 707/532, 707/533, 707/534, 707/541, 434/169, 434/162, 434/163, 434/164, 434/165, 434/156, 434/159
• US Class Current: 704/10
• CPC Class Codes: G06F 40/10 Text processing natural language analysis G06F40/20; semantic analysis G06F40/30; processing or translation of natural language G06F40/40
• CPC Class Codes: G06F 40/247 Thesauruses; Synonyms

Abstract

A document or sentence processing apparatus having an input unit for inputting characters, a display unit for displaying input characters and a processing unit for converting and editing the input characters, in which the processing unit has a candidate word extraction unit which extracts candidates for the words with their characters omitted and/or omitted words themselves by referring to the vocabulary dictionary storing words and their usage frequency, to the dictionary of transition between words defining the information on the transition between words and the probability of the transition between words, and by searching the characters before and after the elliptic character included in the input sentence into the vocabulary dictionary, and a determination unit which selects a single word among the extracted candidate words by referring to the dictionary of transition between words.

Claims

1. A sentence processing apparatus comprising:

an input unit for inputting characters,

a display unit for displaying said input characters, and

a processing unit for converting and editing said input characters,

wherein said processing unit includes;

candidate word extraction means which extracts candidate words for an elliptic word by referring to a vocabulary dictionary storing a word and its usage frequency, to a dictionary of transition between words defining an information on transition between words and a probability of transition between words, and by searching the characters before and after the elliptic character included in the input sentence in the vocabulary dictionary, and

determination means which selects a single word among said extracted candidate words by referring to said dictionary of transition between words.

2. A sentence processing apparatus according to claim 1, wherein

said input unit includes a tablet for allowing an input of words by handwriting, and

said processing unit includes recognition means for extracting and recognizing stroke information input by handwriting.

3. A sentence processing apparatus according to claim 1, wherein

said processing unit includes vocabulary dictionary building means for decomposing an input sentence into individual words, and storing an occurrence count of said individual word in said sentence and said individual word into said vocabulary dictionary.

4. A sentence processing apparatus according to claim 1, wherein

said processing unit includes means for building a dictionary of transition between words for decomposing an input sentence into individual words, and storing a transition count between said individual words in said sentence and said individual word into said dictionary of transition between words.

5. A sentence processing method comprising:

a step of decomposing an input sentence into individual words, and storing an occurrence count of an individual word in said sentence and said individual word into a vocabulary dictionary,

a step of storing an transition count between said individual words into a dictionary of transition between words and searching a class of a particle for said individually decomposed word,

a step of extracting candidate words of omitted words by referring to said vocabulary dictionary on characters before and after an elliptic symbol included in said input sentence, and

a step of determining a single word among said candidate words extracted on a basis of said dictionary of transition between words.

6. A sentence processing method comprising:

a step of decomposing an input sentence into individual words, and storing an occurrence count of an individual word in said sentence and said individual word into a vocabulary dictionary,

a step of storing an transition count between said individual words into a dictionary of transition between words and searching a class of a particle for said individually decomposed word,

a step of extracting a candidate of omitted words by referring to said vocabulary dictionary on characters before and after an elliptic symbol included in said input sentence, and

a step of determining a single word among said candidate words extracted on a basis of said dictionary of transition between words, wherein

in a case where said determined word is found in said vocabulary dictionary, an occurrence count of said determined word is modified and said dictionary of transition between words is modified on a basis of an information on transition between words.