Abstract: Embodiments of this disclosure include an encoding method and apparatus. The encoding may include obtaining a target paragraph and a context sentence of the target paragraph, and inputting the target paragraph and the context sentence into a memory encoding model. The encoding may further include obtaining an original vector set and a memory vector set in the input layer and obtaining a first target sentence matrix of the original vector set in the memory layer according to the original vector set and the memory vector set. The encoding may further include obtaining a paragraph vector of the target paragraph in the output layer according to the first target sentence matrix and performing processing based on the paragraph vector.

Abstract: The disclosure discloses a method and an apparatus for training a dialog generation model, and a dialog generation method and apparatus, and relates to the field of artificial intelligence. The method includes: encoding a context sample to obtain a first latent variable, and recognizing the first latent variable to obtain a prior latent variable; encoding a response sample to obtain a second latent variable; encoding a response similar sample to obtain a third latent variable; performing recognition according to a Gaussian mixture distribution of the first latent variable, the second latent variable, and the third latent variable to obtain a posterior latent variable; and matching the prior latent variable with the posterior latent variable, and performing adversarial training on a dialog generation model.

Abstract: A method is performed at a backend server. The server receives a to-be-processed interaction message from a user interface of a social network platform. The server performs intention classification on the to-be-processed interaction message, to obtain an intention classification result of the to-be-processed interaction message. The server performs semantic analysis on the to-be-processed interaction message when the intention classification result comprises a mini program intention, to determine a message keyword of the to-be-processed interaction message. The server determines a program identifier of a target mini program corresponding to the to-be-processed interaction message according to the message keyword. The server transmits a message processing result based on the program identifier of the target mini program.

Abstract: A man-machine conversation method includes: extracting a keyword from input information of a user; determining a candidate article according to the keyword; obtaining a plurality of sentences in the candidate article, and determining a score of each of the plurality of sentences; extracting part of the plurality of sentences based on the score of each of the plurality of sentences; and generating return information that includes the extracted part of the plurality of sentences.

Abstract: This disclosure relates to a method and an apparatus for training a text classification model. The method may include determining a semantic representation of the training sample using the text classification model and determining a predicted classification result of the training sample based on the semantic representation. The method may further include generating an adversarial sample corresponding to the training sample based on the training sample and perturbation information and determining a semantic representation of the adversarial sample corresponding to the training sample using the text classification model.

Abstract: A suction nozzle assembly used in manufacture for the gentlest handling of delicate components such as a camera lens includes a suction nozzle rod and a suction nozzle member. The suction nozzle rod includes a first through hole. The suction nozzle member includes a main body and a suction nozzle located on both sides of the main body. The main body includes a second through hole connected to the first through hole, and a third through hole connected to the second through hole. The suction nozzle includes at least one suction nozzle hole connected to the third through hole. The disclosure also provides a suction device having the suction nozzle assembly.

Abstract: A method is performed at a backend server. The server receives a to-be-processed interaction message from a user interface of a social network platform. The server performs intention classification on the to-be-processed interaction message, to obtain an intention classification result of the to-be-processed interaction message. The server performs semantic analysis on the to-be-processed interaction message when the intention classification result comprises a mini program intention, to determine a message keyword of the to-be-processed interaction message. The server determines a program identifier of a target mini program corresponding to the to-be-processed interaction message according to the message keyword. The server transmits a message processing result based on the program identifier of the target mini program.

Abstract: A method is performed at an electronic device. The electronic device receives, in a user interface of a social network platform, a to-be-processed interaction message/ The device transmits a message processing request based on the to-be-processed interaction message to a remote server, wherein the remote server identifies one or more target mini application programs based on semantic analysis of the to-be-processed interaction message. The device receives, from the server, a message processing result in accordance with the message processing request. The message processing result includes one or more links to the target mini application programs running on the social network platform. The electronic device displays, in the user interface, a target interaction message for each target mini application program according to the message processing result.

Abstract: A pressing member includes a base, a first pressing portion, and a second pressing portion. The first pressing portion and the second pressing portion are arranged on a same surface of the base. The base is provided with a first hole. The first pressing portion includes a first contact surface facing away from the base. The first contact surface defines a second hole extending toward the base and communicating with the first hole to cooperatively define a channel. The second pressing portion includes a second contact surface facing away from the base. The second contact surface and the first contact surface are arranged on a same plane.

Abstract: The disclosure discloses a method and an apparatus for training a dialog generation model, and a dialog generation method and apparatus, and relates to the field of artificial intelligence. The method includes: encoding a context sample to obtain a first latent variable, and recognizing the first latent variable to obtain a prior latent variable; encoding a response sample to obtain a second latent variable; encoding a response similar sample to obtain a third latent variable; performing recognition according to a Gaussian mixture distribution of the first latent variable, the second latent variable, and the third latent variable to obtain a posterior latent variable; and matching the prior latent variable with the posterior latent variable, and performing adversarial training on a dialog generation model.

Abstract: An encoding method is provided for an encoding apparatus. The method includes obtaining a target paragraph and a preset database, and inputting the target paragraph and preset database into a memory encoding model, obtaining, in an input layer, an original vector set of the target paragraph and a knowledge vector set of the preset database, obtaining, in a first memory layer, a first target sentence matrix according to the original vector set and the knowledge vector set, and obtaining, in an output layer, a paragraph vector of the target paragraph according to the first target sentence matrix, and performing processing based on the paragraph vector.

Abstract: Embodiments of this disclosure include an encoding method and apparatus. The encoding may include obtaining a target paragraph and a context sentence of the target paragraph, and inputting the target paragraph and the context sentence into a memory encoding model. The encoding may further include obtaining an original vector set and a memory vector set in the input layer and obtaining a first target sentence matrix of the original vector set in the memory layer according to the original vector set and the memory vector set. The encoding may further include obtaining a paragraph vector of the target paragraph in the output layer according to the first target sentence matrix and performing processing based on the paragraph vector.

Abstract: A method is performed at an electronic device. The electronic device receives, in a user interface of a social network platform, a to-be-processed interaction message/ The device transmits a message processing request based on the to-be-processed interaction message to a remote server, wherein the remote server identifies one or more target mini application programs based on semantic analysis of the to-be-processed interaction message. The device receives, from the server, a message processing result in accordance with the message processing request. The message processing result includes one or more links to the target mini application programs running on the social network platform. The electronic device displays, in the user interface, a target interaction message for each target mini application program according to the message processing result.

Abstract: A pressing member includes a base, a first pressing portion, and a second pressing portion. The first pressing portion and the second pressing portion are arranged on a same surface of the base. The base is provided with a first hole. The first pressing portion includes a first contact surface facing away from the base. The first contact surface defines a second hole extending toward the base and communicating with the first hole to cooperatively define a channel. The second pressing portion includes a second contact surface facing away from the base. The second contact surface and the first contact surface are arranged on a same plane.

Abstract: A self-cleaning wire bonding machine includes a spool, a cleaning tank, a drying element, a tensioner, and a nozzle. The spool includes a rotating body and a metal wire wound around the rotating body. The cleaning tank is configured to clean the metal wire after the rotating body passes the metal wire through the cleaning tank. The drying element is configured to dry the metal wire after passing through the cleaning tank. The tensioner is configured to adjust a tension of the metal wire. The nozzle is configured to heat the metal wire, and the metal wire exits out of the nozzle after being heated.

Abstract: A man-machine conversation method includes: extracting a keyword from input information of a user; determining a candidate article according to the keyword; obtaining a plurality of sentences in the candidate article, and determining a score of each of the plurality of sentences; extracting part of the plurality of sentences based on the score of each of the plurality of sentences; and generating return information that includes the extracted part of the plurality of sentences.

Abstract: Systems, methods, and computer-readable media for dynamically generating text associated with an advertisement are provided. Core text associated with an advertisement is received from an advertiser, as is at least one attribute relevant to the advertiser and/or a user. Based upon the received attribute(s), it is determined whether customization of the core text is desired. If customization is desired, the core text is modified and presented in association with the advertisement. If customization is not desired, the core text is presented in association with the advertisement. In one embodiment, target advertisement placement information may also be utilized to determine whether customization of the core text is desired.

Abstract: A classifier is built to rank documents of different languages found in a query based at least in part on similarity to other documents and the relevance of those other documents to the query. A joint ranking model, e.g., based upon a Boltzmann machine, is used to represent the content similarity among documents, and to help determine joint relevance probability for a set of documents. The relevant documents of one language are thus leveraged to improve the relevance estimation for documents of different languages. In one aspect, a hidden layer of units (neurons) represents clusters (corresponding to relevant topics) among the retrieved documents, with an output layer representing the relevant documents and their features, and edges representing a relationship between clusters and documents.

Abstract: A set of candidate documents, each of which may be part of a bilingual, parallel set of documents, are identified. The set of documents illustratively includes textual material in a source language. It is then determined whether parallel text can be identified. For each document in the set of documents, it is first determined whether the parallel text resides within the document itself. If not, the document is examined for links to other documents, and those linked documents are examined for bilingual parallelism with the selected documents. If not, named entities are extracted from the document and translated into the target language. The translations are used to query search engines to retrieve the parallel correspondent for the selected documents.

Abstract: A set of candidate parallel pages is identified based on trigger words in one or more pages downloaded from a given network location (such as a website). A set of document trees representing each of the candidate pages are aligned to identify translationally parallel content and hyperlinks. The parallel content is further fed into conventional sentence aligner for parallel sentences. And the parallel hyperlinks usually refer to other parallel documents, and lead to a recursive mining of parallel documents.