Example based machine translation system
AssigneeMicrosoft Corporation
InventorsMing Zhou, Jin-Xia Huang, Chang Ning (Tom) Huang, Wei Wang
Life of this patent
Estimating the term…
Abstract
The present invention performs machine translation by matching fragments of a source language sentence to be translated to source language portions of an example in example base. When all relevant examples have been identified in the example base, the examples are subjected to phrase alignment in which fragments of the target language sentence in each example are aligned against the matched fragments of the source language sentence in the same example. A translation component then substitutes the aligned target language phrases from the matched examples for the matched fragments in the source language sentence.
Claims21
A method of performing machine translation of a source language (SL) input to a translation output in a target language (TL), comprising:
- matching fragments of the SL input to SL fragments of examples in an example base;
- identifying all matched blocks in the SL input as blocks of terms in the SL input that are matched by one or more SL fragments in an example;
- selecting block combinations of the matched blocks to cover one or more fragments of the SL input;
- for each block in the selected block combinations, identifying an example associated with the block;
- aligning TL portions of the identified example with SL portions of the identified example that match the one or more fragments of the SL input;
- and
- providing the translation output based on the aligned portions wherein identifying an example associated with a block comprises:
- calculating a block score corresponding to each example containing the block by calculating the block score as follows:
- similarity
- j
- =
- ∑
- k
- =
- 1
- K
-
-
- TFIDF
- kj
- Where,
- TFIDF is term frequency inverse document frequency:
- K=a total number of common terms included both in example j and the SL input;
- TFIDFkj=Term k's TF/IDF weight in example j;
- and
- Similarityj=matching weight between the example j and the SL input;
- and
- identifying the example associated with the block based on the block score.
A method of performing machine translation of a source language (SL) input to a translation output in a target language (TL), comprising:
- matching fragments of the SL input to SL fragments of examples in an example base;
- identifying all matched blocks in the SL input as blocks of terms in the SL input that are matched by one or more SL fragments in an example;
- selecting block combinations of the matched blocks to cover one or more fragments of the SL input;
- for each block in the selected block combinations calculating a block score corresponding to each example containing the block, and, identifying an example associated with the block based on the block score;
- aligning TL portions of the identified example with SL portions of the identified example that match the one or more fragments of the SL input;
- providing the translation output as a plurality of possible translation outputs based on the aligned portions;
- and
- calculating a confidence measure for each translation output, as a translation confidence level, as follows:
- ConL
- =
- c
- 1
- ×
- log
-
- (
- AlignCon
- ×
- 10
- )
- +
- c
- 2
- ×
- log
-
- (
- TransPercent
- ×
- 10
- )
- +
- c
- 3
- ×
- log
-
- (
- 10
- /
- Example_num
- )
- +
- c
- 4
- ×
- log
-
- (
- 10
- /
- Valid_block
-
- _num
- )
- AlignCon
- =
- ∑
- w
- i
- ∈
- PhrSL
- ,
- w
- j
- ∈
- PhrTL
- i…j
- :
- are
-
-
- connected
-
-
- Conf
-
- (
- C
- ij
- )
- /
-
- PhrTL
-
- (
- 0
- ≤
- AlignCon
- ≤
- 1
- ,
- 0
- ≤
- TransPercent
- ≤
- 1
- ,
- ∑
- i
- =
- 1
- 4
-
-
- c
- i
- =
- 1
- )
- where,
- ConL:
- is the translation confidence level;
- c1,c2, . . . ,c4:
- are constants,
- AlignCon:
- is an alignment confidence level;
- TransPercent:
- is a weighted translation percentage;
- Example13num:
- is an employed example number identifying the identified example;
- Valid13block13num:
- is a fragment number in a possible TL Translation under consideration;
- PhrSL:
- is a SL phrase that relates to a given input string;
- PhrTL:
- is a TL correspondence in the possible translation of the SL input;
- |PhrTL|:
- is a word number of PhrTL;
- Ci . . . j:
- is a connection between SL word i and TL word j;
- and
- Conf(Ci . . . j):
- is the translation confidence level of word Alignment.
Dependencies are inferred from the claim text.