Disclosed herein are various embodiments for training and enriching a natural language processing system. An embodiment operates by determining that a first prediction from a first machine model has been generated based on a dataset comprising a plurality of attributes. A technical map identifying a first subset of attributes of the plurality of attributes used to generate the first prediction by the first machine model is generated. Natural language translations corresponding to at least a portion of the first subset of attributes used to generate the first prediction by the first machine model are identified. A natural language map of the first subset of attributes is generated based on the natural language translations. The natural language map is provided with the first prediction.

An electronic apparatus is disclosed. The electronic apparatus includes a display, a storage in which keyword information by product specification is stored, and a processor configured to obtain user feedback on the product by crawling a website, identify positive feedback or negative feedback among the user feedback corresponding to the keyword information by specification by performing natural language processing (NLP) to which at least two different algorithms are applied, and display a result of the identification through the display.

An electronic apparatus is disclosed. The electronic apparatus includes a display, a storage in which keyword information by product specification is stored, and a processor configured to obtain user feedback on the product by crawling a website, identify positive feedback or negative feedback among the user feedback corresponding to the keyword information by specification by performing natural language processing (NLP) to which at least two different algorithms are applied, and display a result of the identification through the display.

Provided are a method and apparatus for constructing a compact translation model that may be installed on a terminal on the basis of a pre-built reference model, in which a pre-built reference model is miniaturized through a parameter imitation learning and is efficiently compressed through a tree search structure imitation learning without degrading the translation performance. The compact translation model provides translation accuracy and speed in a terminal environment that is limited in network, memory, and computation performance.

Provided are a method and apparatus for constructing a compact translation model that may be installed on a terminal on the basis of a pre-built reference model, in which a pre-built reference model is miniaturized through a parameter imitation learning and is efficiently compressed through a tree search structure imitation learning without degrading the translation performance. The compact translation model provides translation accuracy and speed in a terminal environment that is limited in network, memory, and computation performance.

An entity resolution system performs a method of resolving one or more candidate entities based on a data set. The entity resolution system has a rules-based module, a machine learning module, a narrative module, and an evaluation module. The rules-based module compares the first entity features to the second entity features and determines whether a rule identifies a relationship between the first entity and the second entity. The machine learning module rates a similarity of the first entity features and the second entity features. The narrative module generates a narrative output based on one or more of the rules-based module and the machine learning module, the narrative output stating an identified relationship between the first entity and the second entity. The evaluation module determines one or more metrics to apply feedback to the system.

An entity resolution system performs a method of resolving one or more candidate entities based on a data set. The entity resolution system has a rules-based module, a machine learning module, a narrative module, and an evaluation module. The rules-based module compares the first entity features to the second entity features and determines whether a rule identifies a relationship between the first entity and the second entity. The machine learning module rates a similarity of the first entity features and the second entity features. The narrative module generates a narrative output based on one or more of the rules-based module and the machine learning module, the narrative output stating an identified relationship between the first entity and the second entity. The evaluation module determines one or more metrics to apply feedback to the system.

Techniques for the generation of dubbed audio for an audio/video are described. An exemplary approach is to receive a request to generate dubbed speech for an audio/visual file; and in response to the request to: extract speech segments from an audio track of the audio/visual file associated with identified speakers; translate the extracted speech segments into a target language; determine a machine learning model per identified speaker, the trained machine learning models to be used to generate a spoken version of the translated, extracted speech segments based on the identified speaker; generate, per translated, extracted speech segment, a spoken version of the translated, extracted speech segments using a trained machine learning model that corresponds to the identified speaker of the translated, extracted speech segment and prosody information for the extracted speech segments; and replace the extracted speech segments from the audio track of the audio/visual file with the spoken versions spoken version of the translated, extracted speech segments to generate a modified audio track.

A generation apparatus 100 includes: an argumentative scheme adding unit 10 which adds an argumentative scheme with respect to pair data constituted by an input utterance and a counter utterance 121 that voices a negative opinion with respect to the input utterance and which generates argumentative scheme-added pair data 122; a generation model learning unit 20 which learns a generation model for generating a counter utterance from an input utterance in consideration of the argumentative scheme by using the argumentative scheme-added pair data 122 as learning data and which generates a learned counter utterance generation model 123; and a counter utterance generating unit 30 which acquires an input utterance of a user and a designated argumentative scheme and which outputs a counter utterance using the counter utterance generation model 123.

Aspects of the present disclosure relate to techniques for interactive content generation. In examples, processed content may be produced by a generative model based on a content seed, such as a sentence or paragraph. User input associated with the processed content may be received, for example to revise the processed content or provide additional input with respect to a subpart of the processed content that is associated with a low confidence score. A generative model may produce updated processed content based at least in part on the previously processed content, the user input, and/or, in some examples, additional content, as may be indicated by a user. Thus, a user may iterate on processed content that is produced by such generative models through successive interactions, thereby enabling the user to provide input to the generative model as part of the content generation process.