Though end-to-end neural approaches have recently been dominating NLP tasks in both performance and ease-of-use, they lack interpretability and robustness. We propose Binder, a training-free neural-symbolic framework that maps the task input to a program, which (1) allows binding a unified API of language model (LM) functionalities to a programming language (e.g., SQL, Python) to extend its grammar coverage and thus tackle more diverse questions, (2) adopts an LM as both the program parser and the underlying model called by the API during execution, and (3) requires only a few in-context exemplar annotations. Specifically, we employ GPT-3 Codex as the LM. In the parsing stage, with only a few in-context exemplars, Codex is able to identify the part of the task input that cannot be answerable by the original programming language, correctly generate API calls to prompt Codex to solve the unanswerable part, and identify where to place the API calls while being compatible with the original grammar. In the execution stage, Codex can perform versatile functionalities (e.g., commonsense QA, information extraction) given proper prompts in the API calls. Binder achieves state-of-the-art results on WikiTableQuestions and TabFact datasets, with explicit output programs that benefit human debugging. Note that previous best systems are all finetuned on tens of thousands of task-specific samples, while Binder only uses dozens of annotations as in-context exemplars without any training. Our code is available at https://github.com/HKUNLP/Binder .

Economic intersectionality can refer to the compounded effects of any combination of characteristics associated with economic disadvantage. In this article, we focus on differing levels of automation-based challenges for African American men and women of various ages and education levels in rural and urban America. We project that African Americans in the 13 community archetypes we analyzed may have a higher rate of job displacement than workers in other segments of the US population due to rising automation and gaining a smaller share of the net projected job growth between 2017 and 2030. By 2030, the employment outlook for African Americans--particularly men, younger workers (ages 18–35), and those without a college degree--may worsen dramatically. Additionally, we find that African Americans are geographically removed from future job growth centers and more likely to be concentrated in areas of job decline.