ChatGPT is a language model based on Generative AI. Existing research work on ChatGPT focused on its use in various domains. However, its potential for Sign Language Translation (SLT) is yet to be explored. This paper addresses this void. Therefore, we present GPT's evolution aiming a retrospective analysis of the improvements to its architecture for SLT. We explore ChatGPT's capabilities in translating different sign languages in paving the way to better accessibility for deaf and hard-of-hearing community. Our experimental results indicate that ChatGPT can accurately translate from English to American (ASL), Australian (AUSLAN), and British (BSL) sign languages and from Arabic Sign Language (ArSL) to English with only one prompt iteration. However, the model failed to translate from Arabic to ArSL and ASL, AUSLAN, and BSL to Arabic. Consequently, we present challenges and derive insights for future research directions.
Tsinghua University（清华大学）；University of Illinois at Chicago（伊利诺伊大学芝加哥分校）
This paper presents the first comprehensive analysis of ChatGPT's Text-to-SQL ability. Given the recent emergence of large-scale conversational language model ChatGPT and its impressive capabilities in both conversational abilities and code generation, we sought to evaluate its Text-to-SQL performance. We conducted experiments on 12 benchmark datasets with different languages, settings, or scenarios, and the results demonstrate that ChatGPT has strong text-to-SQL abilities. Although there is still a gap from the current state-of-the-art (SOTA) model performance, considering that the experiment…
Deakin University（迪肯大学）；Chinese Academy of Sciences（中国科学院）；Victoria University（维多利亚大学）；Data61（Data61机构）；Harbin Engineering University（哈尔滨工程大学）；Southweat University（西南大学）；VinUnivesity（VinUniversity）
University of California, Los Angeles（加州大学洛杉矶分校）；Nanyang Technological University（南洋理工大学）；University of California, Davis（加州大学戴维斯分校）；National University of Singapore（新加坡国立大学）；Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
ChatGPT is a Knowledgeable but Inexperienced Solver: An Investigation of Commonsense Problem in Large Language Models
University of Chinese Academy of Sciences（中国科学院大学）；Chinese Information Processing Laboratory（中文信息处理实验室）；Ricoh Software Research Center (Beijing) Co., Ltd.（理光软件研究中心（北京）有限公司）
Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；Paradigm. Inc.（第四范式公司）；HKUST（香港科技大学）
Event extraction is a fundamental task in natural language processing that involves identifying and extracting information about events mentioned in text. However, it is a challenging task due to the lack of annotated data, which is expensive and time-consuming to obtain. The emergence of large language models (LLMs) such as ChatGPT provides an opportunity to solve language tasks with simple prompts without the need for task-specific datasets and fine-tuning. While ChatGPT has demonstrated impressive results in tasks like machine translation, text summarization, and question answering, it pres…
Jožef Stefan Institute（约泽夫·斯蒂芬研究所）；Center za jezikovne vire in tehnologije（语言资源与技术中心）；Univerze v Ljubljani（卢布尔雅那大学）
ChatGPT has shown strong capabilities in natural language generation tasks, which naturally leads researchers to explore where its abilities end. In this paper, we examine whether ChatGPT can be used for zero-shot text classification, more specifically, automatic genre identification. We compare ChatGPT with a multilingual XLM-RoBERTa language model that was fine-tuned on datasets, manually annotated with genres. The models are compared on test sets in two languages: English and Slovenian. Results show that ChatGPT outperforms the fine-tuned model when applied to the dataset which was not seen…
KTH Royal Institute of Technology（KTH皇家理工学院）；Microsoft Research（微软研究院）
ChatGPT has demonstrated exceptional proficiency in natural language conversation, e.g., it can answer a wide range of questions while no previous large language models can. Thus, we would like to push its limit and explore its ability to answer causal discovery questions by using a medical benchmark (Tu et al. 2019) in causal discovery.
