Techniques for efficient encoding in neural semantic parsing systems

A system comprising:

• one or more processors;
• and
• one or more computer-readable media storing instructions which, when executed by the one or more processors, cause the system to perform operations comprising:
• accessing an input string comprising a natural language utterance and a database schema representation for a database;
• providing the natural language utterance to a first subset of layers of a first encoder comprising a plurality of layers to generate one or more utterance embeddings;
• providing the database schema representation to the first subset of the layers of the first encoder to generate one or more schema embeddings;
• concatenating the one or more utterance embeddings and the one or more schema embeddings to generate one or more concatenated embeddings;
• providing the one or more concatenated embeddings to a second subset of the layers of the first encoder to generate one or more embeddings of the natural language utterance and one or more embeddings of the database schema representation;
• encoding, by a second encoder, relations between elements in the database schema representation and words in the natural language utterance based on the one or more embeddings of the natural language utterance and the one or more embeddings of the database schema representation;
• and
• generating a logical form for the natural language utterance based on the encoded relations, the one or more embeddings of the natural language utterance, and the one or more embeddings of the database schema representation.

One or more non-transitory computer-readable media storing instructions which, when executed by one or more processors, cause a system to perform operations comprising:

• accessing an input string comprising a natural language utterance and a database schema representation for a database;
• providing the natural language utterance to a first subset of layers of a first encoder comprising a plurality of layers to generate one or more utterance embeddings;
• providing the database schema representation to the first subset of the layers of the first encoder to generate one or more schema embeddings;
• concatenating the one or more utterance embeddings and the one or more schema embeddings to generate one or more concatenated embeddings;
• providing the one or more concatenated embeddings to a second subset of the layers of the first encoder to generate one or more embeddings of the natural language utterance and one or more embeddings of the database schema representation;
• encoding, by a second encoder, relations between elements in the database schema representation and words in the natural language utterance based on the one or more embeddings of the natural language utterance and the one or more embeddings of the database schema representation;
• and
• generating a logical form for the natural language utterance based on the encoded relations, the one or more embeddings of the natural language utterance, and the one or more embeddings of the database schema representation.