2023-02-10 更新
From Zero-Shot to Few-Shot Learning: A Step of Embedding-Aware Generative Models
Authors:Liangjun Feng, Jiancheng Zhao, Chunhui Zhao
Embedding-aware generative model (EAGM) addresses the data insufficiency problem for zero-shot learning (ZSL) by constructing a generator between semantic and visual embedding spaces. Thanks to the predefined benchmark and protocols, the number of proposed EAGMs for ZSL is increasing rapidly. We argue that it is time to take a step back and reconsider the embedding-aware generative paradigm. The purpose of this paper is three-fold. First, given the fact that the current embedding features in benchmark datasets are somehow out-of-date, we improve the performance of EAGMs for ZSL remarkably with embarrassedly simple modifications on the embedding features. This is an important contribution, since the results reveal that the embedding of EAGMs deserves more attention. Second, we compare and analyze a significant number of EAGMs in depth. Based on five benchmark datasets, we update the state-of-the-art results for ZSL and give a strong baseline for few-shot learning (FSL), including the classic unseen-class few-shot learning (UFSL) and the more challenging seen-class few-shot learning (SFSL). Finally, a comprehensive generative model repository, namely, generative any-shot learning (GASL) repository, is provided, which contains the models, features, parameters, and settings of EAGMs for ZSL and FSL. Any results in this paper can be readily reproduced with only one command line based on GASL.
PDF
点此查看论文截图
Few-Shot Table-to-Text Generation with Prompt Planning and Knowledge Memorization
Authors:Zhixin Guo, Minyxuan Yan, Jiexing Qi, Jianping Zhou, Ziwei He, Zhouhan Lin, Guanjie Zheng, Xinbing Wang
Pre-trained language models (PLM) have achieved remarkable advancement in table-to-text generation tasks. However, the lack of labeled domain-specific knowledge and the topology gap between tabular data and text make it difficult for PLMs to yield faithful text. Low-resource generation likewise faces unique challenges in this domain. Inspired by how humans descript tabular data with prior knowledge, we suggest a new framework: PromptMize, which targets table-to-text generation under few-shot settings. The design of our framework consists of two aspects: a prompt planner and a knowledge adapter. The prompt planner aims to generate a prompt signal that provides instance guidance for PLMs to bridge the topology gap between tabular data and text. Moreover, the knowledge adapter memorizes domain-specific knowledge from the unlabelled corpus to supply essential information during generation. Extensive experiments and analyses are investigated on three open domain few-shot NLG datasets: human, song, and book. Compared with previous state-of-the-art approaches, our model achieves remarkable performance in generating quality as judged by human and automatic evaluations.
PDF
点此查看论文截图
Re-ViLM: Retrieval-Augmented Visual Language Model for Zero and Few-Shot Image Captioning
Authors:Zhuolin Yang, Wei Ping, Zihan Liu, Vijay Korthikanti, Weili Nie, De-An Huang, Linxi Fan, Zhiding Yu, Shiyi Lan, Bo Li, Ming-Yu Liu, Yuke Zhu, Mohammad Shoeybi, Bryan Catanzaro, Chaowei Xiao, Anima Anandkumar
Augmenting pretrained language models (LMs) with a vision encoder (e.g., Flamingo) has obtained state-of-the-art results in image-to-text generation. However, these models store all the knowledge within their parameters, thus often requiring enormous model parameters to model the abundant visual concepts and very rich textual descriptions. Additionally, they are inefficient in incorporating new data, requiring a computational-expensive fine-tuning process. In this work, we introduce a Retrieval-augmented Visual Language Model, Re-ViLM, built upon the Flamingo, that supports retrieving the relevant knowledge from the external database for zero and in-context few-shot image-to-text generations. By storing certain knowledge explicitly in the external database, our approach reduces the number of model parameters and can easily accommodate new data during evaluation by simply updating the database. We also construct an interleaved image and text data that facilitates in-context few-shot learning capabilities. We demonstrate that Re-ViLM significantly boosts performance for image-to-text generation tasks, especially for zero-shot and few-shot generation in out-of-domain settings with 4 times less parameters compared with baseline methods.
PDF
点此查看论文截图
Toolformer: Language Models Can Teach Themselves to Use Tools
Authors:Timo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu, Maria Lomeli, Luke Zettlemoyer, Nicola Cancedda, Thomas Scialom
Language models (LMs) exhibit remarkable abilities to solve new tasks from just a few examples or textual instructions, especially at scale. They also, paradoxically, struggle with basic functionality, such as arithmetic or factual lookup, where much simpler and smaller models excel. In this paper, we show that LMs can teach themselves to use external tools via simple APIs and achieve the best of both worlds. We introduce Toolformer, a model trained to decide which APIs to call, when to call them, what arguments to pass, and how to best incorporate the results into future token prediction. This is done in a self-supervised way, requiring nothing more than a handful of demonstrations for each API. We incorporate a range of tools, including a calculator, a Q\&A system, two different search engines, a translation system, and a calendar. Toolformer achieves substantially improved zero-shot performance across a variety of downstream tasks, often competitive with much larger models, without sacrificing its core language modeling abilities.
PDF
点此查看论文截图