Abstract: A method and apparatus comprising computer code configured to cause a processor or processors to receive an input question to the LLM, model an advantage for the input question based on at least one of a multi-gaussian mixed matrix (GMM) model and an entropy regularizer, and train the LLM based on the advantage, and the advantage includes a proximal policy optimization (PPO) objective where modeling the advantage is based on the multi-GMM model, and the advantage includes a combination of an output of a reward model (RM) and an average model performance for the input question where modeling the advantage is based on the entropy regularizer.

Abstract: A construction lifting device and a leaping method for a construction lifting device. The leaping method includes erecting a top crossbeam above a target floor in a shaft; connecting a host platform of the construction lifting device to the top crossbeam by a drive device; raising a car of the construction lifting device close to the host platform and fixedly connecting the car to the host platform; and activating the drive device to lift the host platform to the target floor.

Abstract: Method, apparatus, and non-transitory storage medium for neural network based dialogue generation, including receiving an input dialogue context, and generating queries based on the input dialogue context using a query generating neural network. The query generating neural network may be trained using a cheap noisy supervision function. The method may further include retrieving responses from a web-based search engine based on the generated queries, and generating dialogue based on the retrieved responses and the input dialogue context.

Abstract: A method, computer program, and computer system for training a graph-to-text generation network is provided. Encoded graph information corresponding to a target sentence is received, and the encoded graph information is decoded based on a biaffine attention score. One or more loss values are determined based on the decoded information, whereby the text-to-graph generation network is trained by minimizing the one or more loss values. A first loss value is generated by reconstructing one or more triple relations based on the biaffine attention score, and a second loss value predicts the graph as a linearized sequence.

Abstract: A method, performed by at least one processor, and an apparatus for augmenting multi-turn text-to-SQL datasets is provided. The method and computer program code include generating an SQL-to-text model to converse with a text-to-SQL model, pre-training the SQL-to-text model and the text-to-SQL model based on input training data, sampling an SQL query as a goal query of an interaction between the SQL-to-text model and the text-to-SQL model, generating the interaction based on the goal query, a current utterance, previous utterances in the interaction, an SQL query from a preceding turn of the interaction, and a serialized database, filtering interactions based on a similarity score between the last turn of the interaction and the goal query, and re-training the SQL-to-text model and the text-to-SQL model based on the input training data and the filtered interactions.

Abstract: There is included a method and apparatus for sentiment analysis for multi-turn conversations comprising computer code for obtaining input dialogues; extracting sentiment expressions based on sentence embeddings corresponding to the input dialogues; generating polarity values based on the sentence embeddings corresponding to the input dialogues; and determining a target mention associated with at least one of the sentiment expressions based on the sentiment expressions and the sentence embeddings, wherein the determining of the target mention includes generating rich contextual representations based on the sentence embeddings and the sentiment expressions; and determining the target mention based on calculated boundaries, wherein the calculated boundaries are generated using the rich contextual representations.

Abstract: A method performed by at least one processor includes retrieving a dialogue history including a plurality of speech utterances, each speech utterance including one or more words. The method further includes encoding the plurality of speech utterances such that each speech utterance is associated with a sequence identifier indicating an order of each speech utterance in the dialogue history. The method further includes decoding the encoded plurality of speech utterances to generate at least one discourse relation triple corresponding to the dialogue history, the at least one discourse relation triple including a first sequence identifier of a first speech utterance from the plurality of speech utterances, a second sequence identifier of a second speech utterance from the plurality of speech utterances, and a dialogue discourse type.

Abstract: Systems and methods for pre-training a dialogue model with semantic information include: generating a dialogue-level abstract meaning representation (AMR) graph for an input dialogue associated with a speaker, learning core semantic units of the input dialogue based on nodes of the dialogue-level AMR graph, learning semantic relations between words of a sentence of the input dialogue based on edges of the dialogue-level AMR graph, learning an overall agreement of the input dialogue and the dialogue-level AMR graph, and training the dialogue model based on the learned core semantic units, semantic relations between words, and overall agreement.

Abstract: A method and apparatus that identifies one or more characters within a text; determines one or more informative sections within the text, the one or more informative sections providing information regarding a gender of the one or more characters within the text; selects a most informative section from the one or more informative sections; extracts unlabeled instances corresponding to the gender of the one or more characters from the most informative section; iteratively trains a multi-task model using unlabeled corpora, the multi-task model performing both speaker identification and gender identification; and labels the gender of the one or more characters based on the extracted unlabeled instances and the multi-task model.

Abstract: A method of generating a neural network based open-domain dialogue model, includes receiving an input utterance from a device having a conversation with the dialogue model, obtaining a plurality of candidate replies to the input utterance from the dialogue model, determining a plurality of discriminator scores for the candidate replies based on reference-free discriminators, determining a plurality of quality score associated with the candidate replies, and training the dialogue model based on the quality scores.

Abstract: A method, computer program, and computer system is provided for parsing multi-party dialogue. Dialogue data having one or more elementary discourse units is received. A local representation and a global representation are determined for each of the elementary discourse units based on performing a pairwise comparison on the elementary discourse units. Relationships between the elementary discourse units are identified based on the determined local and global representations. A contextual link is predicted between non-adjacent elementary discourse units based on the identified relationships.

Abstract: A method, computer program, and computer system is provided for parsing multi-party dialogue. Dialogue data having one or more elementary discourse units is received. A local representation and a global representation are determined for each of the elementary discourse units based on performing a pairwise comparison on the elementary discourse units. Relationships between the elementary discourse units are identified based on the determined local and global representations. A contextual link is predicted between non-adjacent elementary discourse units based on the identified relationships.

Abstract: A method of generating a neural network based open-domain dialogue model, includes receiving an input utterance from a device having a conversation with the dialogue model, obtaining a plurality of candidate replies to the input utterance from the dialogue model, determining a plurality of discriminator scores for the candidate replies based on reference-free discriminators, determining a plurality of quality score associated with the candidate replies, and training the dialogue model based on the quality scores.

Abstract: A method of training a model for query generation, the method performed by at least one processor and including receiving a training instance query corresponding to a dialogue history. The method further including generating a first static view of the model based on a number of common words between the training instance query and the dialogue history. The method further including generating a second static view of the model based on one or more tokens not covered by the dialogue history, the one or more tokens corresponding to one or more query words. The method further including generating a dynamic view of the model based on a score operation that compares a candidate query generated from the model with a target query. The method further including training the model based at least on the first static view, the second static view, and the dynamic view.

Abstract: A method, performed by at least one processor, and an apparatus for augmenting multi-turn text-to-SQL datasets is provided. The method and computer program code include generating an SQL-to-text model to converse with a text-to-SQL model, pre-training the SQL-to-text model and the text-to-SQL model based on input training data, sampling an SQL query as a goal query of an interaction between the SQL-to-text model and the text-to-SQL model, generating the interaction based on the goal query, a current utterance, previous utterances in the interaction, an SQL query from a preceding turn of the interaction, and a serialized database, filtering interactions based on a similarity score between the last turn of the interaction and the goal query, and re-training the SQL-to-text model and the text-to-SQL model based on the input training data and the filtered interactions.

Abstract: Method, apparatus, and non-transitory storage medium for neural network based dialogue generation, including receiving an input dialogue context, and generating queries based on the input dialogue context using a query generating neural network. The query generating neural network may be trained using a cheap noisy supervision function. The method may further include retrieving responses from a web-based search engine based on the generated queries, and generating dialogue based on the retrieved responses and the input dialogue context.

Abstract: A method of training a model for query generation, the method performed by at least one processor and including receiving a training instance query corresponding to a dialogue history. The method further including generating a first static view of the model based on a number of common words between the training instance query and the dialogue history. The method further including generating a second static view of the model based on one or more tokens not covered by the dialogue history, the one or more tokens corresponding to one or more query words. The method further including generating a dynamic view of the model based on a score operation that compares a candidate query generated from the model with a target query. The method further including training the model based at least on the first static view, the second static view, and the dynamic view.

Abstract: A method performed by at least one processor includes retrieving a dialogue history including a plurality of speech utterances, each speech utterance including one or more words. The method further includes encoding the plurality of speech utterances such that each speech utterance is associated with a sequence identifier indicating an order of each speech utterance in the dialogue history. The method further includes decoding the encoded plurality of speech utterances to generate at least one discourse relation triple corresponding to the dialogue history, the at least one discourse relation triple including a first sequence identifier of a first speech utterance from the plurality of speech utterances, a second sequence identifier of a second speech utterance from the plurality of speech utterances, and a dialogue discourse type.

Abstract: Systems and methods for pre-training a dialogue model with semantic information include: generating a dialogue-level abstract meaning representation (AMR) graph for an input dialogue associated with a speaker, learning core semantic units of the input dialogue based on nodes of the dialogue-level AMR graph, learning semantic relations between words of a sentence of the input dialogue based on edges of the dialogue-level AMR graph, learning an overall agreement of the input dialogue and the dialogue-level AMR graph, and training the dialogue model based on the learned core semantic units, semantic relations between words, and overall agreement.

Abstract: A method, performed by at least one processor, and an apparatus for cross-lingual text-to-SQL semantic parsing is provided. The method and computer program code performed by the at least one processor include: generating a contextual representation of a source language utterances, a target language utterances, and a database schema; generating a mixed representation of the target language utterances and the database schema based on the contextual representation of the source language utterances, the target language utterances, and the database schema; concatenating the mixed representation of the target language utterances and the database schema; encoding the concatenated mixed representation of the target language utterances and the database schema, based on k-layer transformers; and generating SQL queries token-by-token based on the encoded concatenated mixed representation of the target language utterances and the database schema.