There is provided a method and system for training and using a transformer language model (TLM) part of a recommendation engine. Natural language discussions about a category of items are received, the discussions comprising tags each indicative of a respective item belonging to the category of item. Information is received for each respective item. Based on the natural language discussions, the tags and the information about the respective item, the TLM is trained to: upon receipt of a user input, determine whether a given item should be recommended based on the user input, if the given item should be recommended, retrieving given information about the given item and generating a response to the user input, the response to the user input comprising the given item to be recommended and the given information, and output the response to the user input. The response is generated in natural language format.

An intelligent reminding method is provided, which is applicable to a first electronic device, and includes: receiving a message sent by a second electronic device, where the message is a first message received by a first application, and the first message includes a task that needs to be processed by a first user; determining whether there is first interaction information in the first electronic device, where an occurrence time of the first interaction information is later than a time point when the first message is received, and an interaction object of the first interaction information is a second user operating the second electronic device; and presenting reminding information in a case that there is not the first interaction information in the first electronic device, where the reminding information is used for reminding the first user that the task is not completed.

Systems and methods for generating candidate translations for use in creating synthetic or human-acted voice dubbings, aiding human translators in generating translations that match the corresponding video, automatically grading how well a candidate translation matches the corresponding video, suggesting modifications to the speed and/or timing of the translated text to improve the grading of a candidate translation, and suggesting modifications to the voice dubbing and/or video to improve the grading of a candidate translation. In that regard, the present technology may be used to fully automate the process of generating lip-matched translations and associated voice dubbings, or as an aid for human-in-the-loop processes that may reduce or eliminate the time and effort required from translators, adapters, voice actors, and/or audio editors to generate voice dubbings.

A method and apparatus for pre-training a model, a device, a storage medium, and a program product. An embodiment of the method includes: acquiring a sample natural language text; generating N types of prompt words based on the sample natural language text, where N is a positive integer; generating sample input data based on the sample natural language text and the N types of prompt words; and training an initial language model based on the sample input data, to obtain a pre-trained language model.

A computer divides a character string included in text data into a plurality of tokens. The computer searches, by performing matching processing between a token string indicating a specific number of consecutive tokens among the plurality of tokens and dictionary information including a plurality of named entities, the plurality of named entities for a similar named entity whose similarity to the token string is equal to or more than a threshold. The computer converts matching information indicating a result of the matching processing between the token string and the similar named entity into first vector data. The computer generates input data by using a plurality of pieces of vector data converted from the plurality of tokens and the first vector data. The computer generates a named entity recognition model that detects a named entity by performing machine learning using the input data.

A computer divides a character string included in text data into a plurality of tokens. The computer searches, by performing matching processing between a token string indicating a specific number of consecutive tokens among the plurality of tokens and dictionary information including a plurality of named entities, the plurality of named entities for a similar named entity whose similarity to the token string is equal to or more than a threshold. The computer converts matching information indicating a result of the matching processing between the token string and the similar named entity into first vector data. The computer generates input data by using a plurality of pieces of vector data converted from the plurality of tokens and the first vector data. The computer generates a named entity recognition model that detects a named entity by performing machine learning using the input data.

A learning data generation device includes processing circuitry to extract a cause expression and a result expression from an input text, and to generate a modified text by at least one of a method of interchanging the cause expression and the result expression and a method of specifying one of the cause expression and the result expression as a modification target sentence and replacing the modification target sentence with a replacement candidate sentence dissimilar to the modification target sentence.

Techniques of automated interoperation tracking in computing systems are disclosed herein. One example technique includes tokenizing a first event log from a first software component and a second event log from the second software component by calculating frequencies of appearance corresponding to strings in the first and second event logs and selecting, as tokens, a first subset of the strings in the first event log and a second subset of the strings in the second event log individually having calculated frequencies of appearance above a preset frequency threshold. The example technique can also include generating an overall event log for a task executed by both the first and second software components by matching one of the strings in the first subset to another of the strings in the second subset.

Techniques of automated interoperation tracking in computing systems are disclosed herein. One example technique includes tokenizing a first event log from a first software component and a second event log from the second software component by calculating frequencies of appearance corresponding to strings in the first and second event logs and selecting, as tokens, a first subset of the strings in the first event log and a second subset of the strings in the second event log individually having calculated frequencies of appearance above a preset frequency threshold. The example technique can also include generating an overall event log for a task executed by both the first and second software components by matching one of the strings in the first subset to another of the strings in the second subset.

A completely unsupervised solution for generating and maintaining a list of lexically similar terms for an e-commerce system is provided. Given a particular electronic collection of items in an e-commerce system, each term in a first item listing is initially paired with each term in a second item listing to form a set of token pairs. The token pairs represent possible candidates for being synonyms. For a respective token pair, an attempt is made to match the shortest token of the token pair to the longest token of the token pair, character by character. If a match is successful, the terms in the token pair are automatically labeled as synonyms for the particular electronic collection of items. Some implementations automatically filter out false positives and/or token pairs that are unrelated and not likely synonyms. The solution can be performed at the granularity of a product, category, vertical, or entire catalog.