Abstract: According to one embodiment, a first phrase having one or more keywords is received to be added to a phrase blacklist, where the first phrase has been determined to be related to unwanted content. An analysis is performed on the keywords of the first phrase to identifying a set of one or more related phrases that are related to the first phrase. The first phrase and the set of related phrases are added in the phrase blacklist. The phrase blacklist contains a plurality of phrases that have been determined to be related to unwanted content. The phrase blacklist is utilized to prevent a content item from appearing in a search result, in response to a search query having a phrase matching at least one of the phrases in the phrase backlist.

Abstract: A method for text generation, relates to a field of natural language processing, including: obtaining corpus data; labeling the corpus data to obtain a first constraint element; obtaining a first generation target; and generating a first text matching the first generation target by inputting the corpus data and the first constraint element into a generation model.

Abstract: A method and apparatus for correcting a speech recognition result, a device and a computer-readable storage medium are provided. The method includes performing speech recognition on acquired speech data to obtain initial text information; and recognizing and correcting the initial text information by a neural machine translation NMT model to obtain a final text recognition result.

Abstract: An information searching method and an information searching device are provided. The information searching method includes: receiving, at one or more computing devices, a first query from a client device, and obtaining, at the one or more computing devices an intention clarification guidance sentence according to the first query; receiving a second query updated according to the intention clarification guidance sentence; obtaining a search result according to the second query; and returning the search result to the client device.

Abstract: A method for extracting an event from a text including obtaining an input text; inputting the input text into a model for extracting trigger words to obtain a trigger word extraction result of the input text; inputting the input text and the trigger word extraction result into a model for extracting arguments to obtain an argument extraction result of the input text; and obtaining an event extraction result of the input text according to the trigger word extraction result and the argument extraction result.

Abstract: There is provided a method and apparatus for generating a competition commentary based on artificial intelligence, and a storage medium. The method comprises: obtaining commentator's words commentaries and structured data of historical competitions; generating a commentating model according to obtained information; during live broadcast of a competition, determining a corresponding words commentary according to the commentating model with respect to the structured data obtained each time.

Abstract: The present disclosure provides a search result aggregation method and apparatus based on artificial intelligence and a search engine. The method includes: obtaining a query; generating a plurality of search results according to the query; obtaining a plurality of corresponding demand dimensions according to the query; aggregating the plurality of demand dimensions according to the plurality of search results; obtaining an answer corresponding to each demand dimension, and aggregating the answers corresponding to the plurality of demand dimensions according to the aggregated demand dimensions to generate an aggregation result.

Abstract: The present disclosure discloses a comment information processing method and apparatus, and a medium. The specific implementation solution is: in response to a user operation, determining an opinion category corresponding to each opinion phrase in a comment opinion dictionary; obtaining a target corpus matching each opinion phrase from a plurality of comment corpora; for each opinion phrase, using a corresponding opinion category to label the target corpus matching each opinion phrase to obtain a first training sample; and training a classification model with the first training sample to identify the opinion category of a comment by using a trained classification model.

Abstract: The present invention provides a conversation processing method, a conversation management system and a computer device. The method comprises: acquiring task-related user requirement data; updating a user conversation state based on the user requirement data and a pre-configured task-related task parameter; generating at least one piece of candidate action data according to the user conversation state; and generating response text data according to the at least one piece of candidate action data. The expandability of the conversation management system is improved by customizing the conversion service related to the task in the conversation system.

Abstract: Embodiments of the present disclosure provide a method and apparatus for performing word segmentation on a text, a device and a medium, which relate to the field of data processing technology and particularly to a smart search technology. The method may include: dividing a to-be-segmented text into at least two layers of character fragment combinations, any layer of character fragments being child character fragments of a previous layer of character fragments and/or parent character fragments of a next layer of character fragments; and segmenting the to-be-segmented text according to a target word granularity based on the at least two layers of character fragment combinations.

Abstract: A method and apparatus for generating information are disclosed. An implementation of the method includes: receiving a target text, the target text including an objective and descriptive information of the objective; performing a dependency syntax parsing on the target text to generate a dependency tree of the target text; matching predetermined syntactic structure tree with the dependency tree to obtain at least one triple, a triple including a subject, a predicate, and an object; and determining, based on words contained in a triple among the at least one triple and a predetermined weight of the syntactic structure tree matched to obtain the triple, a target triple among the at least one triple.

Abstract: The present disclosure discloses a search result displaying method and an apparatus. The method includes: obtaining a plurality of webpages according to a search request of a user, and performing proper noun recognition and word segmentation processing on a title of each webpage to obtain part-of-speech and extended information corresponding to a word segmentation result; determining core information of each webpage according to the part-of-speech and extended information corresponding to the word segmentation result; selecting webpages matching the search request from the plurality of webpages based on the core information of each webpage; and performing cluster analysis on the webpages matching the search request to generate a search result, and displaying the searching result to the user.

Abstract: The disclosure provides a method, a device and a storage medium for predicting a punctuation in a text. The method includes: inputting a text to be predicted into a sequence tagging model to obtain at least one prediction result and a corresponding first score of each character in the text to be predicted; generating a text to be inputted corresponding to each of the at least one prediction result; obtaining a second score corresponding to each of the at least one prediction result; determining a punctuation existence situation of the corresponding character based on the first score and the second score corresponding to each of the at least one prediction result; and performing punctuation processing on the text to be predicted based on the punctuation existence situation of each character in the text to be predicted to obtain a punctuated text corresponding to the text to be predicted.

Abstract: Embodiments of the present disclosure disclose a method and apparatus for switching multiple speech recognition models. The method includes: acquiring at least one piece of speech information in user input speech; recognizing the speech information and matching a linguistic category for the speech information to determine a corresponding target linguistic category based on a matching degree; and switching a currently used speech recognition model to a speech recognition model corresponding to the target linguistic category. The embodiments of the present disclosure determine the corresponding target linguistic category based on the matching degree by recognizing the speech information and matching the linguistic category for the speech information, and switch the currently used speech recognition model to the speech recognition model corresponding to the target linguistic category.

Abstract: The present disclosure provides a method and a device for generating a text tag. The method includes: performing keyword extraction using strategies corresponding to respective tag types on a target text, to obtain one or more candidate tags of the respective tag types for the target text, wherein the tag type includes at least one of an entity word, a segment text and a topic; performing reduplication removing between different tag types on the one or more candidate tags of the respective tag types to obtain one or more validated candidate tags; and determining one or more target tags of the target text based on the one or more validated candidate tags.

Abstract: Embodiments of the present disclosure relate to a dialogue interaction method and apparatus, a device and a storage medium, and relate to the field of artificial intelligence technology. The method may include: determining a first semantic encoding of received user information according to a sentence tree; determining a second semantic encoding for responding to the user information from a dialogue tree according to the first semantic encoding, the sentence tree and the dialogue tree being trained and obtained through sentence node information and/or word node information in a logical brain map sample; and determining a target response sentence of the second semantic encoding from the sentence tree, to be used for a dialogue with a user.

Abstract: Embodiments of a method and an apparatus for improving a model based on a pre-trained semantic model are provided. The method may include: based on the pre-trained semantic model, obtaining an initial improved model, where semantic result information of an input vector is determined in the initial improved model based on a hash search method; and based on a model distillation method, training the initial improved model to obtain an improved model. Some embodiments can obtain the semantic result information of the input vector by performing the hash search method on the input vector, replace the original complex iterative calculation process of a semantic model, and obtain the improved model with few model parameters and high compression ratio.

Abstract: A method for processing questions and answers includes: in a process of determining an answer to a question to be answered, determining the semantic representation on the question to be answered respectively with a first semantic representation model of question and a second semantic representation model of question. Semantic representation vectors obtained through the first semantic representation model of question and the second semantic representation model of question are spliced. A spliced semantic vector is determined as a semantic representation vector of the question to be answered. An answer semantic vector matching the semantic representation vector of the question to be answered is acquired from a vector index library of answer, and an answer corresponding to the answer semantic vector is determined as a target answer to the question to be answered.

Abstract: The present disclosure discloses an artificial intelligence based method and apparatus for constructing a comment graph. A specific embodiment of the method comprises: determining a comment text based on comment data on a network page; identifying a comment subject and a comment opinion in the comment text, based on a characteristic in the comment text; generating a subject opinion pair including the comment subject, the comment opinion and an emotional tendency based on the comment subject and the comment opinion; generating a comment label associated with the subject opinion pair based on news information; and generating a comment graph, based on the comment label and the subject opinion pair. This embodiment improves the pertinence and the accuracy of the comment and the control to the comment emotion, when providing comments externally.

Abstract: Embodiments of the present invention provide a method, system and storage medium for implementing intelligent question answering. The method includes: receiving a query question; performing a semantic analysis of the question; performing corresponding search processing for the question based on a result of the semantic analysis, wherein the search processing includes search processing performed for the question by at least one of a semantic relationship mining system, a text library search system, a knowledge base search system, and a question and answer library search system; and returning an answer based on a result of the search processing. In this way, the accuracy of answers to the questions is effectively improved.