Dialogue system, dialogue processing method, translating apparatus, and method of translation
View Patent ↗A translating apparatus includes: a translator configured to translate an input sentence of a first language into a second language to generate a plurality of output sentences; a first dialogue manager configured to generate a meaning representation for the input sentence of the first language; a second dialogue manager configured to generate a meaning representation for each of the plurality of output sentences of the second language; and a determiner configured to determine a final output sentence among the plurality of output sentences of the second language based on the meaning representation for the input sentence of the first language and the meaning representation for each of the plurality of output sentences of the second language.
1. A translating apparatus comprising:
a user terminal that communicates with an input device and an output device; and
a processor configured to
convert a voice signal received from the input device via the user terminal to text,
generate an input sentence of a first language corresponding to the converted text,
translate the input sentence of the first language into a second language to generate a plurality of output sentences,
generate a meaning representation for the input sentence of the first language,
generate a meaning representation for each of the plurality of output sentences of the second language,
determine a final output sentence among the plurality of output sentences of the second language based on the meaning representation for the input sentence of the first language and the meaning representation for each of the plurality of output sentences of the second language,
control the user terminal to transmit the final output sentence to the output device,
assign a similarity score for each of the plurality of output sentences of the second language based on a similarity degree between the meaning representation for the input sentence of the first language and the meaning representation for each of the plurality of output sentences of the second language, and
determine the final output sentence based on a sum score that adds the similarity score and a confidence score for each of the plurality of output sentences of the second language,
wherein the input device includes at least one of a microphone, a touch screen, and a keyboard, and
wherein the output device includes at least one of a display and a speaker.
2. The translating apparatus according to claim 1 , wherein the processor determines a rank of the plurality of output sentences of the second language using a N-best algorithm.
3. The translating apparatus according to claim 2 , wherein the processor determines the rank of the plurality of output sentences again based on the similarity degree between the meaning representation for the input sentence of the first language and the meaning representation for each of the plurality of output sentences of the second language.
4. The translating apparatus according to claim 3 , wherein the processor assigns the confidence score to each of the plurality of output sentences of the second language using the N-best algorithm.
5. A translating method comprising:
performing, by a user terminal, communication with an input device and an output device;
converting, by a processor, a voice signal received from the input device via the user terminal to text;
generating, by the processor, an input sentence of a first language corresponding to the converted text;
generating, by the processor, a plurality of output sentences by translating the input sentence of a first language into a second language;
generating, by the processor, a meaning representation for the input sentence of the first language;
generating, by the processor, a meaning representation for each of the plurality of output sentences of the second language;
determining, by by the processor, a final output sentence among the plurality of output sentences of the second language based on the meaning representation for the input sentence of the first language and the meaning representation for each of the plurality of output sentences of the second language, and
controlling, by the processor, the user terminal to transmit the final output sentence to the output device,
wherein determining, by the processor, the final output sentence comprises
assigning, by the processor, a similarity score for each of the plurality of output sentences of the second language based on a similarity degree between the meaning representation for the input sentence of the first language and the meaning representation for each of the plurality of output sentences of the second language, and
determining, by the processor, the final output sentence based on a sum score that adds the similarity score and a confidence score for each of the plurality of output sentences of the second language,
wherein the input device includes at least one of a microphone, a touch screen, and a keyboard, and
wherein the output device includes at least one of a display and a speaker.
6. The translating method according to claim 5 , wherein generating, by the processor, the plurality of output sentences of the second language comprises determining a rank of the plurality of output sentences of the second language using a N-best algorithm.
7. The translating method according to claim 6 , wherein determining, by the processor, the final output sentence comprises determining the rank of the plurality of output sentences again based on the similarity degree between the meaning representation for the input sentence of the first language and the meaning representation for each of the plurality of output sentences of the second language.
8. The translating method according to claim 7 , wherein generating, by the processor, the plurality of the output sentences of the second language comprises assigning the confidence score to each of the plurality of output sentences of the second language using the N-best algorithm.