中文
相关论文

相关论文: Prompt-and-Rerank: A Method for Zero-Shot and Few-…

200 篇论文

Prompt-based fine-tuning has become an essential method for eliciting information encoded in pre-trained language models for a variety of tasks, including text classification. For multi-class classification tasks, prompt-based fine-tuning…

计算与语言 · 计算机科学 2024-10-04 Zhiwen You , Kanyao Han , Haotian Zhu , Bertram Ludäscher , Jana Diesner

This study investigates the application of large language models (LLMs), specifically GPT-3.5 and GPT-4, with Chain-of-Though (CoT) in the automatic scoring of student-written responses to science assessments. We focused on overcoming the…

计算与语言 · 计算机科学 2024-02-20 Gyeong-Geon Lee , Ehsan Latif , Xuansheng Wu , Ninghao Liu , Xiaoming Zhai

We investigate the emergent abilities of the recently proposed web-scale speech model Whisper, by adapting it to unseen tasks with prompt engineering. We selected three tasks: audio-visual speech recognition (AVSR), code-switched speech…

音频与语音处理 · 电气工程与系统科学 2023-08-17 Puyuan Peng , Brian Yan , Shinji Watanabe , David Harwath

Zero-shot text-to-speech (TTS) synthesis aims to clone any unseen speaker's voice without adaptation parameters. By quantizing speech waveform into discrete acoustic tokens and modeling these tokens with the language model, recent language…

Zero-shot text classification typically relies on prompt engineering, but the inherent prompt brittleness of large language models undermines its reliability. Minor changes in prompt can cause significant discrepancies in model performance.…

计算与语言 · 计算机科学 2025-04-07 Junlang Qian , Zixiao Zhu , Hanzhang Zhou , Zijian Feng , Zepeng Zhai , Kezhi Mao

Recent advances on prompt-tuning cast few-shot classification tasks as a masked language modeling problem. By wrapping input into a template and using a verbalizer which constructs a mapping between label space and label word space,…

计算与语言 · 计算机科学 2022-01-17 Yinyi Wei , Tong Mo , Yongtao Jiang , Weiping Li , Wen Zhao

Due to their architecture and vast pre-training data, large language models (LLMs) demonstrate strong text classification performance. However, LLM output - here, the category assigned to a text - depends heavily on the wording of the…

计算与语言 · 计算机科学 2025-12-04 Kylie L. Anglin , Stephanie Milan , Brittney Hernandez , Claudia Ventura

Weakly supervised text classification (WSTC), also called zero-shot or dataless text classification, has attracted increasing attention due to its applicability in classifying a mass of texts within the dynamic and open Web environment,…

计算与语言 · 计算机科学 2024-04-26 Miaomiao Li , Jiaqi Zhu , Yang Wang , Yi Yang , Yilin Li , Hongan Wang

Pretrained language models (PLMs) have made remarkable progress in text generation tasks via fine-tuning. While, it is challenging to fine-tune PLMs in a data-scarce situation. Therefore, it is non-trivial to develop a general and…

计算与语言 · 计算机科学 2022-05-17 Junyi Li , Tianyi Tang , Jian-Yun Nie , Ji-Rong Wen , Wayne Xin Zhao

The goal of text style transfer is to transform the style of texts while preserving their original meaning, often with only a few examples of the target style. Existing style transfer methods generally rely on the few-shot capabilities of…

计算与语言 · 计算机科学 2024-11-08 Zachary Horvitz , Ajay Patel , Kanishk Singh , Chris Callison-Burch , Kathleen McKeown , Zhou Yu

Large language models (LLMs) have revolutionized zero-shot task performance, mitigating the need for task-specific annotations while enhancing task generalizability. Despite its advancements, current methods using trigger phrases such as…

计算与语言 · 计算机科学 2024-06-13 Saurabh Srivastava , Chengyue Huang , Weiguo Fan , Ziyu Yao

The remarkable performance of pre-trained large language models has revolutionised various natural language processing applications. Due to huge parametersizes and extensive running costs, companies or organisations tend to transfer the…

计算与语言 · 计算机科学 2023-12-15 Jiazheng Li , Runcong Zhao , Yongxin Yang , Yulan He , Lin Gui

Dialogue state tracking (DST) module is an important component for task-oriented dialog systems to understand users' goals and needs. Collecting dialogue state labels including slots and values can be costly, especially with the wide…

计算与语言 · 计算机科学 2023-01-27 Yuting Yang , Wenqiang Lei , Pei Huang , Juan Cao , Jintao Li , Tat-Seng Chua

Speech Translation (ST) is the task of translating speech in one language into text in another language. Traditional cascaded approaches for ST, using Automatic Speech Recognition (ASR) and Machine Translation (MT) systems, are prone to…

计算与语言 · 计算机科学 2021-07-14 Tu Anh Dinh

Phrase break prediction is a crucial task for improving the prosody naturalness of a text-to-speech (TTS) system. However, most proposed phrase break prediction models are monolingual, trained exclusively on a large amount of labeled data.…

计算与语言 · 计算机科学 2023-06-06 Hoyeon Lee , Hyun-Wook Yoon , Jong-Hwan Kim , Jae-Min Kim

Parameter-efficient methods are able to use a single frozen pre-trained large language model (LLM) to perform many tasks by learning task-specific soft prompts that modulate model behavior when concatenated to the input text. However, these…

计算与语言 · 计算机科学 2022-08-12 Brian Lester , Joshua Yurtsever , Siamak Shakeri , Noah Constant

We propose a new paradigm for zero-shot learners that is format agnostic, i.e., it is compatible with any format and applicable to a list of language tasks, such as text classification, commonsense reasoning, coreference resolution, and…

计算与语言 · 计算机科学 2022-10-19 Ping Yang , Junjie Wang , Ruyi Gan , Xinyu Zhu , Lin Zhang , Ziwei Wu , Xinyu Gao , Jiaxing Zhang , Tetsuya Sakai

Facilitated by large language models (LLMs), personalized text generation has become a rapidly growing research direction. Most existing studies focus on designing specialized models for a particular domain, or they require fine-tuning the…

计算与语言 · 计算机科学 2024-02-09 Cheng Li , Mingyang Zhang , Qiaozhu Mei , Weize Kong , Michael Bendersky

Documents as short as a single sentence may inadvertently reveal sensitive information about their authors, including e.g. their gender or ethnicity. Style transfer is an effective way of transforming texts in order to remove any…

计算与语言 · 计算机科学 2021-09-21 David Ifeoluwa Adelani , Miaoran Zhang , Xiaoyu Shen , Ali Davody , Thomas Kleinbauer , Dietrich Klakow

Text classification is one of the most imperative tasks in natural language processing (NLP). Recent advances with pre-trained language models (PLMs) have shown remarkable success on this task. However, the satisfying results obtained by…

计算与语言 · 计算机科学 2023-08-30 Jianing Wang , Chengyu Wang , Cen Chen , Ming Gao , Jun Huang , Aoying Zhou