Interactive Natural Language Processing

• DOI: 10.48550/arxiv.2305.13246
• Publication Date: 2023-01-01
• Authors: Zekun Wang; Ge Zhang; Kexin Yang; Ning Shi; Wangchunshu Zhou; Shaochun Hao; Guangzheng Xiong; Yi‐Zhi Li; Mong Yuan Sim; Xiuying Chen; Qingqing Zhu; Zhenzhu Yang; Adam Nik; Qi Liu; Chenghua Lin; Shi Wang; Ruibo Liu; Wenhu Chen; Ke Xu; Dayiheng Liu; Yike Guo; Jie Fu
• Keywords: Relevance

Interactive Natural Language Processing (iNLP) has emerged as a novel paradigm within the field of NLP, aimed at addressing limitations in existing frameworks while aligning with ultimate goals artificial intelligence. This considers language models agents capable observing, acting, and receiving feedback iteratively from external entities. Specifically, this context can: (1) interact humans for better understanding user needs, personalizing responses, human values, improving overall experience; (2) knowledge bases enriching representations factual knowledge, enhancing contextual relevance dynamically leveraging information to generate more accurate informed responses; (3) tools effectively decomposing complex tasks, specialized expertise specific subtasks, fostering simulation social behaviors; (4) environments learning grounded language, tackling embodied tasks such reasoning, planning, decision-making response environmental observations. paper offers comprehensive survey iNLP, starting by proposing unified definition framework concept. We then provide systematic classification dissecting its various components, including interactive objects, interaction interfaces, methods. proceed delve into evaluation methodologies used field, explore diverse applications, scrutinize ethical safety issues, discuss prospective research directions. serves an entry point researchers who are interested rapidly evolving area broad view current landscape future trajectory iNLP.