Method for extracting translations from translated texts using punctuation-based sub-sentential alignment

A process of text alignment of a first document and a second document that is a translation version of the first document, comprising:

• dividing paragraphs of the first and the second documents into a number of sub-sentential segments;
• combining shorter sub-sentential segments in the paragraphs according a predetermined minimum length and a predetermined rule;
• generating pairs of alignment units after the combining from the first and second documents, wherein each of the alignment units includes at least one sub-sentential segment and has a length equal to the number of sub-sentential segments contained therein;
• pre-processing a portion of the pairs of alignment units to obtain reference components;
• scoring the remaining pairs of alignment units according to the reference components obtained during the pre-processing;
• and
• aligning the pairs of alignment units based on the scoring result.

A process of text alignment of a first document and a second document that is a translation version of the first document, each of the first document and second document including at least one sentence and one paragraph, comprising:

• tokenizing at least the sentence of the first document and at least the sentence of the second document;
• dividing the paragraph of the first document and the second document into a plurality of sub-sentential segments;
• comparing each of the sub-sentential segment lengths to a minimum length, wherein if one of the sub-sentential segment is shorter than the minimum length, a corresponding segment is combined with a previous segment;
• normalizing the sub-sentential segment;
• and
• dynamically programming the segments with consideration to punctuations.

A system for text alignment of a first document and a second document that is a translation version of the first document, comprising:

• a memory for receiving the first and the second documents;
• a pre-processor for:
• dividing paragraphs of the first and the second documents into a number of sub-sentential segments;
• combining shorter sub-sentential segments in the paragraphs according to a predetermined minimum length and predetermined rules;
• generating pairs of alignment units from the first and second documents, wherein each of the alignment unit includes at least one sub-sentential segments and has a length equal to the number of sub-sentential segments included in the alignment unit;
• pre-processing a portion of the pairs of alignment units to obtain reference components;
• and
• a processor for aligning and scoring the pairs of alignment units according to the reference components obtained by the pre-processor.