In an example, a text sentence comprising a plurality of words is obtained. Each of the plurality of words is passed through a deep compositional character-to-word model to encode character-level information of each of the plurality of words into a character-to-word expression. The character-to-word expressions are combined with pre-trained word embeddings. The combined character-to-word expressions and pre-trained word embeddings are fed into one or more bidirectional long short-term memories to learn contextual information for each of the plurality of words. Then, sequential conditional random fields are applied to the contextual information for each of the plurality of words.

The subject matter discloses a method for translating text in an image, comprising extracting at least a portion of the text in a source language from the image, identifying one or more bounding boxes containing the text in the image, translating at least a portion of the text in the source language to a destination language, generating a new image containing the text in the destination language in the bounding boxes of the associated words in the source language.

The subject matter discloses a method for translating text in an image, comprising extracting at least a portion of the text in a source language from the image, identifying one or more bounding boxes containing the text in the image, translating at least a portion of the text in the source language to a destination language, generating a new image containing the text in the destination language in the bounding boxes of the associated words in the source language.

Provided are a speech translation method and apparatus, an electronic device and a storage medium. The method includes: acquiring a source speech corresponding to a to-be-translated language; acquiring a specified target language; inputting the source speech and indication information matched with the target language into a pre-trained speech translation model, where the speech translation model is configured to translate a language in a first language set into a language in a second language set, the first language set includes a plurality of languages, the first language set includes the to-be-translated language, the second language set includes a plurality of languages, and the second language set includes the target language; and acquiring a translated speech corresponding to the target language and output by the speech translation model; where the to-be-translated language is different from the target language.

Provided are a speech translation method and apparatus, an electronic device and a storage medium. The method includes: acquiring a source speech corresponding to a to-be-translated language; acquiring a specified target language; inputting the source speech and indication information matched with the target language into a pre-trained speech translation model, where the speech translation model is configured to translate a language in a first language set into a language in a second language set, the first language set includes a plurality of languages, the first language set includes the to-be-translated language, the second language set includes a plurality of languages, and the second language set includes the target language; and acquiring a translated speech corresponding to the target language and output by the speech translation model; where the to-be-translated language is different from the target language.

Implementations relate to effectively localizing system responses, that include dynamic information, to target language(s), such that the system responses are grammatical and/or natural in the target language(s). Some of those implementations relate to various techniques for resource efficient generation of templates for a target language. Some versions of those implementations relate to resource efficient generation of target language natural language generation (NLG) templates and, more particularly, to techniques that enable a human user to generate a target language NLG template more efficiently and/or with greater accuracy. The more efficient target language NLG template generation enables less utilization of various client device resources and/or can mitigate the risk of flawed NLG templates being provided for live use in one or more systems.

Implementations relate to effectively localizing system responses, that include dynamic information, to target language(s), such that the system responses are grammatical and/or natural in the target language(s). Some of those implementations relate to various techniques for resource efficient generation of templates for a target language. Some versions of those implementations relate to resource efficient generation of target language natural language generation (NLG) templates and, more particularly, to techniques that enable a human user to generate a target language NLG template more efficiently and/or with greater accuracy. The more efficient target language NLG template generation enables less utilization of various client device resources and/or can mitigate the risk of flawed NLG templates being provided for live use in one or more systems.

An electronic device and a method for controlling the electronic device thereof are provided. The electronic device includes a memory storing instructions, and a processor configured to control the electronic device by executing the instructions stored in the memory, and the processor is configured to, based on a user's speech being input, acquire a first sentence in a first language corresponding to the user's speech through a speech recognition model corresponding to a language of the user's speech, acquire a second sentence in a second language corresponding to the first sentence in the first language through a machine translation model trained to translate a plurality of languages into the predefined second language, and acquire a control instruction of the electronic device corresponding to the acquired second sentence or acquire a response to the second sentence through a natural language understanding model trained based on the second language.

An electronic device and a method for controlling the electronic device thereof are provided. The electronic device includes a memory storing instructions, and a processor configured to control the electronic device by executing the instructions stored in the memory, and the processor is configured to, based on a user's speech being input, acquire a first sentence in a first language corresponding to the user's speech through a speech recognition model corresponding to a language of the user's speech, acquire a second sentence in a second language corresponding to the first sentence in the first language through a machine translation model trained to translate a plurality of languages into the predefined second language, and acquire a control instruction of the electronic device corresponding to the acquired second sentence or acquire a response to the second sentence through a natural language understanding model trained based on the second language.

A method includes: acquiring an input sentence in a first language in a current round of conversation; translating the input sentence in the first language to obtain an input sentence in a second language, according to dialogue contents in the first language and dialogue contents in the second language that have a mutual translation relationship with the dialogue contents in the first language in historical rounds of conversation; invoking a multi-round conversation generation model to parse the input sentence in the second language in the current round of conversation to generate an output sentence in the second language in the current round of conversation; translating the output sentence in the second language in the current round of conversation to obtain at least one candidate result in the first language; and determining an output sentence in the first language from the at least one candidate result in the first language.