MACHINE TRANSLATION SYSTEM

• US 20170220559A1
• Filed: 12/12/2016
• Published: 08/03/2017
• Est. Priority Date: 02/01/2016
• Status: Active Grant

• Current Assignee: Panasonic Intellectual Property Management Co., Ltd. (Panasonic Holdings Corporation)
• Original Assignee: Panasonic Intellectual Property Management Co., Ltd. (Panasonic Holdings Corporation)
• Inventors: FUJIWARA, NANAMI, YAMAUCHI, MASAKI
• Granted Patent: US 10,318,642 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 40/45 Example-based machine translation; Alignment
• CPC Class Codes: G06F 40/51 Translation evaluation
• CPC Class Codes: G06F 40/58 Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation

Abstract

A paraphrase generation method according to the present disclosure generates one or more paraphrases of an original text by paraphrasing, within an acceptable limit for accepting paraphrasing, one or more of a plurality of fragments included in the original text into another expression in the language of the original text, the plurality of fragments being obtained by dividing the original text in accordance with a predetermined rule.

Claims

1. A paraphrase generation method comprising:

receiving, using a processor, an original text;

generating, using the processor, one or more paraphrases of the original text by paraphrasing, within an acceptable limit for accepting paraphrasing, one or more of a plurality of fragments included in the original text into another expression in a language of the original text, the plurality of fragments being obtained by dividing the original text in accordance with a predetermined rule; and

recording, using the processor, the one or more paraphrases of the original text in a server.

2. The paraphrase generation method according to claim 1,

wherein the generating of the one or more paraphrases includes

paraphrasing one of the one or more fragments included in the original text into another expression in the language of the original text to generate a paraphrase candidate for the original text, and

determining whether the paraphrasing is within the acceptable limit,

wherein the paraphrasing is executed until the determining determines that the paraphrasing is not within the acceptable limit, and

wherein the determining includes determining, as the one or more paraphrases, the paraphrase candidate generated by the paraphrasing that is determined to be within the acceptable limit.

3. The paraphrase generation method according to claim 2,

wherein the determining includes determining whether the paraphrasing is within the acceptable limit based on a paraphrase acceptability score, the paraphrase acceptability score being assigned to a paraphrase pair including a first fragment and a second fragment that represents another expression of the first fragment, the paraphrase acceptability score indicating a degree to which paraphrasing from the first fragment into the second fragment is accepted.

4. The paraphrase generation method according to claim 3,

wherein the determining includes determining whether the paraphrasing is within the acceptable limit further based on a linguistic acceptability score, the linguistic acceptability score indicating a degree to which the paraphrase candidate generated by the paraphrasing is accepted as having a linguistically correct meaning.

5. The paraphrase generation method according to claim 1, further comprising:

creating a translation corpus that includes a collection of a plurality of text pairs, the plurality of text pairs each including a first text in a first language paired with a second text in a second language,

wherein the receiving includes further receiving the second text, with the original text being the first text, and

wherein the creating of the translation corpus includes creating one or more new text pairs, the one or more new text pairs each including the received second text and the one or more paraphrases of the original text that are generated by the generating of the one or more paraphrases, the created one or more new text pairs forming a new part of the translation corpus.

8. A machine translation system comprising:

a paraphrase generator that receives an original text, and generates one or more paraphrases of the original text;

a translation corpus creator that creates a translation corpus including a collection of a plurality of text pairs, the plurality of text pairs each including a first text in a first language paired with a second text in a second language different from the first language; and

a translator that translates a source text between the first language and the second language based on the translation corpus created by the translation corpus creator, the source text representing a text to be translated,

wherein the translation corpus creator creates one or more new text pairs, the one or more new text pairs each including the second text and the one or more paraphrases of the original text that are generated by the paraphrase generator with the original text being the first text, the created one or more new text pairs forming a new part of the translation corpus, and

wherein the paraphrase generator implements the paraphrase generation method according to claim 1.

6. An apparatus comprising:

a processor; and

a medium having a computer program stored thereon, the computer program causing the processor to execute operations including;

receiving an original text;

generating one or more paraphrases of the original text by paraphrasing, within an acceptable limit for accepting paraphrasing, one or more of a plurality of fragments included in the original text into another expression in a language of the original text, the plurality of fragments being obtained by dividing the original text in accordance with a predetermined rule; and

recording the one or more paraphrases of the original text in a server.

7. A non-transitory recording medium having a computer program stored thereon, the computer program causing a processor to execute operations comprising:

receiving an original text;

generating one or more paraphrases of the original text by paraphrasing, within an acceptable limit for accepting paraphrasing, one or more of a plurality of fragments included in the original text into another expression in a language of the original text, the plurality of fragments being obtained by dividing the original text in accordance with a predetermined rule; and

recording the one or more paraphrases of the original text in a server.