Abstract: A method for error reduction in intent classification according to an embodiment includes determining a set of possible intent classes for a section of input text, mapping each of the possible intent classes into a respective group of a plurality of groups, determining which groups of the plurality of groups are contradictory to one or more other groups of the plurality of groups, splitting the section of input text into a plurality of sub-parts, performing intent classification on the section of input text to determine an intent of the section of input text and on each sub-part of the plurality of sub-parts to determine a respective intent of each sub-part, evaluating the determined intent of the section of input text and the respective intents of the sub-parts for intent contradiction, and overriding the determined intent of the section of input text in response to identifying an intent contradiction.

Abstract: A method in an illustrative embodiment includes generating, based on a group of utterances in a dialog, multiple representations corresponding to the group of utterances, the multiple representations including a first representation associated with the group of utterances, a second representation associated with the group of utterances and a group of utterances following the group of utterances, and a third representation associated with the group of utterances and at least two groups of utterances in a context of the group of utterances. The method also includes obtaining, based on the multiple representations, multiple reference recognition results corresponding to the group of utterances, each of the multiple reference recognition results indicating whether the dialog needs to be transferred to a target object. The method further includes determining, based on the multiple reference recognition results, a target recognition result indicating whether the dialog needs to be transferred to the target object.

Abstract: A computing machine accesses text from a record. The computing machine identifies, using a natural language processing engine, an entity mapped to a first span of the text. The first span includes a contiguous sequence of one or more words or subwords in the text. The computing machine determines a bias category for the entity. The bias category is selected from a predefined list of bias categories. The determined bias category for the entity depends on a second span of the text. The second span includes a contiguous sequence of one or more words or subwords in the text. The second span is different from the first span.

Abstract: Disclosed are a method for training a semantic representation model, a device and a storage medium, which relate to the field of computer technologies, and particularly to the field of artificial intelligence, such as a natural language processing technology, a deep learning technology, or the like.

Abstract: A method of classifying sounds based on a neural code in a spiking neural network includes: receiving sounds to be classified and digitally converting the received sounds into sound data; preprocessing the sound data using a multiple neural code-based encoding method including rate code encoding and synchrony code encoding; inputting the preprocessed sound data to a biological spiking neural network to extract features; performing biological spike timing-dependent plasticity (STDP) rule-based learning using the extracted features; and performing classification of the sounds according to neural code propagation characteristics using a test dataset according to a result of the performing of the learning.

Abstract: A computing system includes a memory; and processing circuitry in communication with the memory. The processing circuitry is configured to: receive a paraphrase comprising a paraphrase text sample corresponding to an original text sample; and calculate a paraphrase metric value corresponding to the paraphrase, wherein the paraphrase metric value is calculated based on an adequacy score, a novelty score, and a fluency score of the paraphrase, the adequacy score indicating an extent to which the paraphrase text sample preserves a meaning of the original text sample, the novelty score indicating a level of difference between words and characters of the paraphrase text sample and words and characters of the original text sample, and the fluency score indicating an extent to which the paraphrase text sample is devoid of repetition, spelling, and grammatical mistakes.

Abstract: The method for identifying noise samples, includes: obtaining an original sample set; obtaining a target sample set by adding masks to original training corpora in the original sample set using a preset adjustment rule; performing mask prediction on a plurality of target training corpora in the target sample set using a pre-trained language model to obtain a first mask prediction character corresponding to each target training corpus; matching the first mask prediction character corresponding to each target training corpus with a preset condition; and according to target training corpora of which first mask prediction characters do not match the preset condition in the target sample set, determining corresponding original training corpora in the original sample set as noise samples.

Abstract: A method for speech recognition using cadence patterns is provided. The method includes identifying speech cadence in user speech, which includes a plurality of sounds and pauses. At least one speech cadence pattern is identified from the plurality of sounds and pauses. The user speech is transcribed, and the transcribed user speech is modified based on the identified speech cadence pattern.

Abstract: To provide a sound extraction system and a sound extraction method capable of accurately extracting, from mixture signals, a signal corresponding to a sound which a user wants to extract. The sound extraction system includes a sound extraction device configured to extract, from mixture signals including a signal corresponding to an extraction target sound, the signal corresponding to the extraction target sound. The sound extraction device is configured to extract the signal corresponding to the extraction target sound from the mixture signals based on the mixture signals and a text representing a range of the extraction target sound.

Abstract: A named entity recognition (NER) method includes: acquiring target text information; inputting the target text information into an input representation layer in a target recognition model to generate a target vector sequence; inputting the target vector sequence into a semantic representation layer to obtain a tag prediction sequence; and inputting the tag prediction sequence into a condition discrimination layer to determine target items in a set of attribution probabilities.

Abstract: A method for zero-shot event extraction, performed by a computer device. The method includes training a context encoder, a first definition encoder, and a second definition encoder with auto extracted context-definition alignment data; retrieving a plurality of verbal synsets from a lexical database; refining a representation model based on the context-definition alignment data and the plurality of verbal synsets; encoding a plurality of candidate event type definitions; encoding the refined representation model with the trained context encoder; and determining whether the encoded representation model belongs to one of the plurality of candidate event type definitions based on a cosine similarity between the encoded representation model, the trained context encoder, the first trained definition encoder, and the second trained definition encoder.

Abstract: The present invention discloses an adaptive knowledge graph representation learning method for integrating a graph structure with text information, including: (1) sampling a neighbor triple of each of a head entity and a tail entity in a target triple; (2) calculating semantic representations of the target triple, and neighbor triples of its head and tail entities; (3) calculating structure representations of the head and tail entities of the target triple; (4) splicing the semantic representation of the target triple with the structure representations of its head and tail entities, inputting a spliced result into an adaptive classification layer, and calculating a classification result and a classification loss; and (5) optimizing the foregoing module based on an optimization algorithm of gradient descent, until a loss value converges, to obtain a final spliced result between the semantic representation of the target triple and the structure representations of its head and tail entities.