Loading patent…
AssigneeInternational Business Machines Corporation
InventorsSeong Kim, Chang Min, Sang Kang, Jeong Cha
Estimating the term…
Generating a transfer dictionary used in a transfer-based translation machine system. A pair of source/target language sentences are received. The source language sentence comprises at least one marked idiom, at least one argument and at least one marked collocation. The target language sentence comprises the target language translation for the idiom and the source language word(s) for the argument. The source language sentence is parsed to generate a source language syntactic tree. Nodes are extracted from the source language syntactic tree. A least common ancestor node of the extracted nodes is calculated and source language structure information is generated based on the source language syntactic tree data structure. Target language structure information is generated by adding the part-of-speech information to each morpheme in the target language sentence and by replacing each source language word in the target language with the corresponding syntactic information within the source language syntactic tree.
An apparatus for generating a transfer dictionary used in a transfer-based translation machine system, the transfer dictionary storing a pair of the source/target language sentences and corresponding source/target language structure information, comprising:
The apparatus of 1, further comprising a determining unit for determining a validity of said source language structure information by checking if it forms a phrase.
The apparatus of 2, wherein said determining unit includes a first checking unit for checking whether a parent node of each argument node extracted from the source language syntactic tree is an idiom node or not and a second checking unit for checking whether there are more than two idiom nodes of which the parent node is not an idiom node.
The apparatus of 1, further comprising a redundancy-checking unit for checking a redundancy of the generated source/target language structure information by retrieving all the entries having the same idiom with that of the generated source language structure information and checking if there already exists the same target language structure information with the generated target language structure information.
A computer-readable medium stored thereon program instructions executable by the computer to perform the method of generating a transfer dictionary used in a transfer-based translation machine system, the transfer dictionary storing a pair of the source/target language sentences and corresponding source/target language structure information, the method comprising the steps of:
Dependencies are inferred from the claim text.