WORD ALIGNMENT SCORE COMPUTING APPARATUS, WORD ALIGNMENT APPARATUS, AND COMPUTER PROGRAM

• US 20170068665A1
• Filed: 02/12/2015
• Published: 03/09/2017
• Est. Priority Date: 03/07/2014
• Status: Active Grant

• Current Assignee: National Institute of Information and Communications Technology
• Original Assignee: National Institute of Information and Communications Technology
• Inventors: TAMURA, Akihiro, WATANABE, Taro, SUMITA, Eiichiro
• Granted Patent: US 10,049,105 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 40/44 Statistical methods, e.g. probability models
• CPC Class Codes: G06F 40/45 Example-based machine translation; Alignment
• CPC Class Codes: G10L 25/30 using neural networks

Abstract

[Object] An object is to provide an apparatus for attaining highly precise word alignment.

[Solution] The apparatus includes: selecting means receiving a bilingual sentence pair and a word alignment for the bilingual sentence pair, for successively selecting words f_j of a sentence in a first language in a prescribed order; and a recurrent neural network (RNN) 100, computing, for all words of the sentence in the first language, a score 102 representing a probability that a word pair consisting of the word f_j and a word e_{a_{j}} aligned with the word f_j by a word alignment a_j in a second language of the bilingual sentence pair is a correct word pair, and based on this score, for computing a score of the word alignment a_j. When computing a score of word pair (f_j, e_{a_{j}}), RNN 100 computes a score 102 of the word pair (f_j, e_{a_{j}}) based on all word alignments a₁^j-1 selected by the selecting means prior to the word f_j of the word pair (f_j, e_{a_{j}}), of the word alignments a_j, by means of a recurrent connection 118.

Claims

1. A word alignment score computing apparatus for computing a score of word alignment of a bilingual sentence pair of first and second languages, comprising:

selecting means, responsive to said bilingual sentence pair and a word alignment for the bilingual sentence pair, for successively selecting words of a sentence in said first language of said bilingual sentence pair in a prescribed order; and

score computing means for computing, for every word of the sentence in said first language of said bilingual sentence pair, a score representing a probability of the word selected by said selecting means and a word in said second language aligned with said word by said word alignment forming a correct word pair, and based on this score, for computing a score of said word alignment;

wherein

in computing a score of a certain word pair, said score computing means computes the score of the certain word pair based on all alignments of words selected by said selecting means preceding that word in said first language which forms the certain word pair.

2. The word alignment score computing apparatus according to claim 1, wherein said selecting means includes means for successively selecting words of the sentence in said first language of said bilingual sentence pair starting from the beginning of the sentence in said first language.

3. The word alignment score computing apparatus according to claim 1, wherein

said score computing means includes:

first computing means for computing a score representing a probability of a word pair consisting of the word selected by said selecting means and a word in a sentence in said second language of said bilingual sentence pair aligned with said word by said word alignment being a correct word pair; and

second computing means for computing, based on scores of all words of the sentence in said first language of said bilingual sentence pair computed by said first computing means, the score of said word alignment.

4. The word alignment score computing apparatus according to claim 3, wherein said second computing means includes means for computing the score of said word alignment by multiplying the scores of all words of the sentence in said first language of said bilingual sentence pair computed by said first computing means.

5. The word alignment score computing apparatus according to claim 1, wherein

said score computing means includes

a recurrent neural network having a first input receiving a word selected by said selecting means and a second input receiving a word in said second language aligned with said word by said word alignment, and

input control means for applying the word selected by said selecting means and the word aligned with the word by said word alignment to said first and second inputs, respectively;

said recurrent neural network includes

an input layer having said first and second inputs, and computing and outputting word embedding vectors from words respectively applied to said first and second inputs,

a hidden layer connected to receive outputs of said input layer, for generating, by a predetermined non-linear operation, a vector representing a relation between two outputs from said input layer, and

an output layer computing and outputting said score based on the output of said hidden layer; and

the output of said hidden layer is applied as an input to said hidden layer when a next word pair is given to said word alignment score computing apparatus.

6. A word alignment apparatus for estimating word alignment of bilingual sentence pair of first and second languages, comprising:

the word alignment score computing apparatus according to claim 1;

word alignment candidate generating means for generating a plurality of word alignment candidates for said bilingual sentence pair;

computing means for computing, for each of said plurality of word alignment candidates generated by said word alignment candidate generating means, a word alignment score for said bilingual sentence pair using said word alignment score computing apparatus; and

word alignment determining means for determining and outputting as the word alignment for said bilingual sentence pair, that one of the word alignment candidates computed by said computing means for said plurality of word alignment candidates which corresponds to the highest score.

7. A computer program causing, when executed by a computer, said computer to function as each means described in claim 1.

8. The word alignment score computing apparatus according to claim 2, wherein

said score computing means includes:

first computing means for computing a score representing a probability of a word pair consisting of the word selected by said selecting means and a word in a sentence in said second language of said bilingual sentence pair aligned with said word by said word alignment being a correct word pair; and

second computing means for computing, based on scores of all words of the sentence in said first language of said bilingual sentence pair computed by said first computing means, the score of said word alignment.

9. The word alignment score computing apparatus according to claim 2, wherein

said score computing means includes

a recurrent neural network having a first input receiving a word selected by said selecting means and a second input receiving a word in said second language aligned with said word by said word alignment, and

input control means for applying the word selected by said selecting means and the word aligned with the word by said word alignment to said first and second inputs, respectively;

said recurrent neural network includes

an input layer having said first and second inputs, and computing and outputting word embedding vectors from words respectively applied to said first and second inputs,

a hidden layer connected to receive outputs of said input layer, for generating, by a predetermined non-linear operation, a vector representing a relation between two outputs from said input layer, and

an output layer computing and outputting said score based on the output of said hidden layer; and

the output of said hidden layer is applied as an input to said hidden layer when a next word pair is given to said word alignment score computing apparatus.

10. The word alignment score computing apparatus according to claim 3, wherein

said score computing means includes

a recurrent neural network having a first input receiving a word selected by said selecting means and a second input receiving a word in said second language aligned with said word by said word alignment, and

input control means for applying the word selected by said selecting means and the word aligned with the word by said word alignment to said first and second inputs, respectively;

said recurrent neural network includes

an input layer having said first and second inputs, and computing and outputting word embedding vectors from words respectively applied to said first and second inputs,

a hidden layer connected to receive outputs of said input layer, for generating, by a predetermined non-linear operation, a vector representing a relation between two outputs from said input layer, and

an output layer computing and outputting said score based on the output of said hidden layer; and

the output of said hidden layer is applied as an input to said hidden layer when a next word pair is given to said word alignment score computing apparatus.

11. The word alignment score computing apparatus according to claim 4, wherein

said score computing means includes

a recurrent neural network having a first input receiving a word selected by said selecting means and a second input receiving a word in said second language aligned with said word by said word alignment, and

input control means for applying the word selected by said selecting means and the word aligned with the word by said word alignment to said first and second inputs, respectively;

said recurrent neural network includes

an input layer having said first and second inputs, and computing and outputting word embedding vectors from words respectively applied to said first and second inputs,

a hidden layer connected to receive outputs of said input layer, for generating, by a predetermined non-linear operation, a vector representing a relation between two outputs from said input layer, and

an output layer computing and outputting said score based on the output of said hidden layer; and

the output of said hidden layer is applied as an input to said hidden layer when a next word pair is given to said word alignment score computing apparatus.

12. A word alignment apparatus for estimating word alignment of bilingual sentence pair of first and second languages, comprising:

the word alignment score computing apparatus according to claim 2;

word alignment candidate generating means for generating a plurality of word alignment candidates for said bilingual sentence pair;

computing means for computing, for each of said plurality of word alignment candidates generated by said word alignment candidate generating means, a word alignment score for said bilingual sentence pair using said word alignment score computing apparatus; and

word alignment determining means for determining and outputting as the word alignment for said bilingual sentence pair, that one of the word alignment candidates computed by said computing means for said plurality of word alignment candidates which corresponds to the highest score.

13. A word alignment apparatus for estimating word alignment of bilingual sentence pair of first and second languages, comprising:

the word alignment score computing apparatus according to claim 3;

word alignment candidate generating means for generating a plurality of word alignment candidates for said bilingual sentence pair;

computing means for computing, for each of said plurality of word alignment candidates generated by said word alignment candidate generating means, a word alignment score for said bilingual sentence pair using said word alignment score computing apparatus; and

word alignment determining means for determining and outputting as the word alignment for said bilingual sentence pair, that one of the word alignment candidates computed by said computing means for said plurality of word alignment candidates which corresponds to the highest score.

14. A word alignment apparatus for estimating word alignment of bilingual sentence pair of first and second languages, comprising:

the word alignment score computing apparatus according to claim 4;

word alignment candidate generating means for generating a plurality of word alignment candidates for said bilingual sentence pair;

computing means for computing, for each of said plurality of word alignment candidates generated by said word alignment candidate generating means, a word alignment score for said bilingual sentence pair using said word alignment score computing apparatus; and

word alignment determining means for determining and outputting as the word alignment for said bilingual sentence pair, that one of the word alignment candidates computed by said computing means for said plurality of word alignment candidates which corresponds to the highest score.

15. A word alignment apparatus for estimating word alignment of bilingual sentence pair of first and second languages, comprising:

the word alignment score computing apparatus according to claim 5;

word alignment candidate generating means for generating a plurality of word alignment candidates for said bilingual sentence pair;

computing means for computing, for each of said plurality of word alignment candidates generated by said word alignment candidate generating means, a word alignment score for said bilingual sentence pair using said word alignment score computing apparatus; and

word alignment determining means for determining and outputting as the word alignment for said bilingual sentence pair, that one of the word alignment candidates computed by said computing means for said plurality of word alignment candidates which corresponds to the highest score.

16. A computer program causing, when executed by a computer, said computer to function as each means described in claim 2.

17. A computer program causing, when executed by a computer, said computer to function as each means described in claim 3.

18. A computer program causing, when executed by a computer, said computer to function as each means described in claim 4.

19. A computer program causing, when executed by a computer, said computer to function as each means described in claim 5.

20. A computer program causing, when executed by a computer, said computer to function as each means described in claim 6.