Salesforce Com, Inc.

Xi Victoria Lin

Caiming Xiong

Richard Socher

Chu Hong Hoi

Nazneen Rajani

Semih Yavuz

Jichuan Zeng

Qingyun Wang

Embodiments described herein provide systems and methods for data-to-text generation. The embodiments receive input data that includes a resource description framework (RDF) triples in an RDF graph. A data-to-text generation system generates position aware embeddings, including position embeddings, triple role embeddings, and tree-level embeddings. Using the position aware embeddings and the RDF graph, the data-to-text generation system generates a textual description for the RDF graph.

Structured graph-to-text generation with two step fine-tuning

A text-to-database neural network architecture is provided. The architecture receives a natural language question and a database schema and generates a serialized question-schema representation that includes a question and at least one table and at least one field from the database schema. The serialized question-schema representation is appended with at least one value that matches a word in the natural language question and at least one field in a database picklist. An encoder in the architecture generates question and schema encodings from the appended question-schema representation. Schema encodings are associated with metadata that indicates a data type of the fields and whether fields are associated with primary or foreign keys. A decoder in the architecture generates an executable query from the question encodings and schema encodings.

Bridging textual and tabular data for cross domain text-to-query language semantic parsing with a pre-trained transformer language encoder and anchor text

Approaches for multi-hop knowledge graph reasoning with reward shaping include a system and method of training a system to search relational paths in a knowledge graph. The method includes identifying, using an reasoning module, a plurality of first outgoing links from a current node in a knowledge graph, masking, using the reasoning module, one or more links from the plurality of first outgoing links to form a plurality of second outgoing links, rewarding the reasoning module with a reward of one when a node corresponding to an observed answer is reached, and rewarding the reasoning module with a reward identified by a reward shaping network when a node not corresponding to an observed answer is reached. In some embodiments, the reward shaping network is pre-trained.

Multi-hop knowledge graph reasoning with reward shaping

A system and method for translating questions into database queries are provided. A text to database query system receives a natural language question and a structure in a database. Question tokens are generated from the question and query tokens are generated from the structure in the database. The question tokens and query tokens are concatenated into a sentence and a sentence token is added to the sentence. A BERT network generates question hidden states for the question tokens, query hidden states for the query tokens, and a classifier hidden state for the sentence token. A translatability predictor network determines if the question is translatable or untranslatable. A decoder converts a translatable question into an executable query. A confusion span predictor network identifies a confusion span in the untranslatable question that causes the question to be untranslatable. An auto-correction module to auto-correct the tokens in the confusion span.

Growing community of inventors

Menlo Park, CA, United States of America

Xi Victoria Lin