API Entity and Relation Joint Extraction from Text via Dynamic Prompt-tuned Language Model

TL;DR

This paper introduces AERJE, a dynamic prompt-based language model that jointly extracts API entities and their relations from unstructured text, significantly reducing manual effort and improving accuracy in ambiguous and complex sentences.

Contribution

The paper presents a novel sequence-to-sequence approach using dynamic prompts for joint API entity and relation extraction, outperforming rule-based and labeling methods, especially in low-data scenarios.

Findings

AERJE achieves high accuracy in API extraction from Stack Overflow data.

The model performs well with zero or few-shot fine-tuning.

Dynamic prompts enhance extraction performance in ambiguous sentences.

Abstract

Extraction of Application Programming Interfaces (APIs) and their semantic relations from unstructured text (e.g., Stack Overflow) is a fundamental work for software engineering tasks (e.g., API recommendation). However, existing approaches are rule-based and sequence-labeling based. They must manually enumerate the rules or label data for a wide range of sentence patterns, which involves a significant amount of labor overhead and is exacerbated by morphological and common-word ambiguity. In contrast to matching or labeling API entities and relations, this paper formulates heterogeneous API extraction and API relation extraction task as a sequence-to-sequence generation task, and proposes AERJE, an API entity-relation joint extraction model based on the large pre-trained language model. After training on a small number of ambiguous but correctly labeled data, AERJE builds a multi-task architecture that extracts API entities and relations from unstructured text using dynamic prompts. We systematically evaluate AERJE on a set of long and ambiguous sentences from Stack Overflow. The experimental results show that AERJE achieves high accuracy and discrimination ability in API entity-relation joint extraction, even with zero or few-shot fine-tuning.