As NLP models achieved state-of-the-art performances over benchmarks and gained wide
applications, it has been increasingly important to ensure the safe deployment of these …

Semantic parsing is a technique aimed at constructing a structured representation of the
meaning of a natural-language question. Recent advancements in few-shot language …

The robustness of Text-to-SQL parsers against adversarial perturbations plays a crucial role
in delivering highly reliable applications. Previous studies along this line primarily focused …

Despite significant advancements in multi-label text classification, the ability of existing
models to generalize to novel and seldom-encountered complex concepts, which are …

Textual scene graph parsing has become increasingly important in various vision-language
applications, including image caption evaluation and image retrieval. However, existing …

Multilingual semantic parsing aims to leverage the knowledge from the high-resource
languages to improve low-resource semantic parsing, yet commonly suffers from the data …

In recent years, on-device deep learning has gained attention as a means of developing
affordable deep learning applications for mobile devices. However, on-device models are …

Neural text-to-SQL models have achieved remarkable performance in translating natural
language questions into SQL queries. However, recent studies reveal that text-to-SQL …

Text-to-SQL semantic parsing has made significant progress in recent years, with various
models demonstrating impressive performance on the challenging Spider benchmark …

In this work, we present a method to add perturbations to the code descriptions to create
new inputs in natural language (NL) from well-intentioned developers that diverge from the …