DeepAI AI Chat
Log In Sign Up

Compressing Transformer-Based Semantic Parsing Models using Compositional Code Embeddings

by   Prafull Prakash, et al.

The current state-of-the-art task-oriented semantic parsing models use BERT or RoBERTa as pretrained encoders; these models have huge memory footprints. This poses a challenge to their deployment for voice assistants such as Amazon Alexa and Google Assistant on edge devices with limited memory budgets. We propose to learn compositional code embeddings to greatly reduce the sizes of BERT-base and RoBERTa-base. We also apply the technique to DistilBERT, ALBERT-base, and ALBERT-large, three already compressed BERT variants which attain similar state-of-the-art performances on semantic parsing with much smaller model sizes. We observe 95.15 20.47 semantic parsing performances. We provide the recipe for training and analyze the trade-off between code embedding sizes and downstream performances.


page 1

page 2

page 3

page 4


Establishing Strong Baselines for the New Decade: Sequence Tagging, Syntactic and Semantic Parsing with BERT

This paper presents new state-of-the-art models for three tasks, part-of...

Compositional Semantic Parsing Across Graphbanks

Most semantic parsers that map sentences to graph-based meaning represen...

Conversational Semantic Parsing

The structured representation for semantic parsing in task-oriented assi...

Making Transformers Solve Compositional Tasks

Several studies have reported the inability of Transformer models to gen...

Multilingual Compositional Wikidata Questions

Semantic parsing allows humans to leverage vast knowledge resources thro...

Low-Resource Compositional Semantic Parsing with Concept Pretraining

Semantic parsing plays a key role in digital voice assistants such as Al...

Semantic expressive capacity with bounded memory

We investigate the capacity of mechanisms for compositional semantic par...