SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2101.00259 · ACL · 2021

Code Generation from Natural Language with Less Prior and More Monolingual Data

Sajad Norouzi, Yanshuai Cao, Keyi Tang

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Training datasets for semantic parsing are typically small due to the higher expertise required for annotation than most other NLP tasks. As a result, models for this application usually need additional prior knowledge to be built into the architecture or algorithm. The increased dependency on human experts hinders automation and raises the development and maintenance costs in practice. This work investigates whether a generic transformer-based seq2seq model can achieve competitive performance with minimal code-generation-specific inductive bias design. By exploiting a relatively sizeable monolingual corpus of the target programming language, which is cheap to mine from the web, we achieved 81.03% exact match accuracy on Django and 32.57 BLEU score on CoNaLa. Both are SOTA to the best of our knowledge. This positive evidence highlights a potentially easier path toward building accurate semantic parsers in practice. † * Work done during internship at BorealisAI † Code at https://github.com/BorealisAI/code-gen-TAE

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2101.00259")
get_code_for_paper("2101.00259")
have("2101.00259")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2101.00259.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2101.00259.svg)](https://syntology.ai/paper/2101.00259)

Connect an agent — have() is free.