English
Related papers

Related papers: Formulating Few-shot Fine-tuning Towards Language …

200 papers

We study the problem of few shot learning for named entity recognition. Specifically, we leverage the semantic information in the names of the labels as a way of giving the model additional signal and enriched priors. We propose a neural…

Computation and Language · Computer Science 2022-03-18 Jie Ma , Miguel Ballesteros , Srikanth Doss , Rishita Anubhai , Sunil Mallya , Yaser Al-Onaizan , Dan Roth

Named Entity Recognition (NER) in Few-Shot setting is imperative for entity tagging in low resource domains. Existing approaches only learn class-specific semantic features and intermediate representations from source domains. This affects…

Computation and Language · Computer Science 2022-03-29 Sarkar Snigdha Sarathi Das , Arzoo Katiyar , Rebecca J. Passonneau , Rui Zhang

Prompt-based language models have produced encouraging results in numerous applications, including Named Entity Recognition (NER) tasks. NER aims to identify entities in a sentence and provide their types. However, the strong performance of…

Computation and Language · Computer Science 2023-08-08 Amirhossein Layegh , Amir H. Payberah , Ahmet Soylu , Dumitru Roman , Mihhail Matskin

We study the named entity recognition (NER) problem under the extremely weak supervision (XWS) setting, where only one example entity per type is given in a context-free way. While one can see that XWS is lighter than one-shot in terms of…

Computation and Language · Computer Science 2023-11-07 Letian Peng , Zihan Wang , Jingbo Shang

As unlabeled data carry rich task-relevant information, they are proven useful for few-shot learning of language model. The question is how to effectively make use of such data. In this work, we revisit the self-training technique for…

Computation and Language · Computer Science 2021-10-05 Yiming Chen , Yan Zhang , Chen Zhang , Grandee Lee , Ran Cheng , Haizhou Li

We present a novel approach to named entity recognition (NER) in the presence of scarce data that we call example-based NER. Our train-free few-shot learning approach takes inspiration from question-answering to identify entity spans in a…

Computation and Language · Computer Science 2020-08-25 Morteza Ziyadi , Yuting Sun , Abhishek Goswami , Jade Huang , Weizhu Chen

Few-shot natural language processing (NLP) refers to NLP tasks that are accompanied with merely a handful of labeled examples. This is a real-world challenge that an AI system must learn to handle. Usually we rely on collecting more…

Computation and Language · Computer Science 2020-07-21 Wenpeng Yin

Few-shot named entity recognition (NER) enables us to build a NER system for a new domain using very few labeled examples. However, existing prototypical networks for this task suffer from roughly estimated label dependency and closely…

Computation and Language · Computer Science 2022-08-18 Bin Ji , Shasha Li , Shaoduo Gan , Jie Yu , Jun Ma , Huijun Liu

Recently, fine-tuning pre-trained language models (e.g., multilingual BERT) to downstream cross-lingual tasks has shown promising results. However, the fine-tuning process inevitably changes the parameters of the pre-trained model and…

Computation and Language · Computer Science 2020-10-06 Zihan Liu , Genta Indra Winata , Andrea Madotto , Pascale Fung

Few-shot learning aims to train models that can be generalized to novel classes with only a few samples. Recently, a line of works are proposed to enhance few-shot learning with accessible semantic information from class names. However,…

Machine Learning · Computer Science 2023-07-11 Zihao Jiang , Yunkai Dang , Dong Pang , Huishuai Zhang , Weiran Huang

Named entity recognition (NER) systems that perform well require task-related and manually annotated datasets. However, they are expensive to develop, and are thus limited in size. As there already exists a large number of NER datasets that…

Computation and Language · Computer Science 2019-04-23 Nargiza Nosirova , Mingbin Xu , Hui Jiang

Few-shot named entity recognition (NER) aims at identifying named entities based on only few labeled instances. Current few-shot NER methods focus on leveraging existing datasets in the rich-resource domains which might fail in a…

Computation and Language · Computer Science 2022-10-14 Zeng Yang , Linhai Zhang , Deyu Zhou

Few-shot learning (FSL) is the task of learning to recognize previously unseen categories of images from a small number of training examples. This is a challenging task, as the available examples may not be enough to unambiguously determine…

Computer Vision and Pattern Recognition · Computer Science 2021-05-24 Kun Yan , Zied Bouraoui , Ping Wang , Shoaib Jameel , Steven Schockaert

In recent years, the fine-tuned generative models have been proven more powerful than the previous tagging-based or span-based models on named entity recognition (NER) task. It has also been found that the information related to entities,…

Computation and Language · Computer Science 2024-06-12 Guochao Jiang , Ziqin Luo , Yuchen Shi , Dixuan Wang , Jiaqing Liang , Deqing Yang

Deploying natural language processing (NLP) models on mobile platforms requires models that can adapt across diverse applications while remaining efficient in memory and computation. We investigate pre-finetuning strategies to enhance the…

Computation and Language · Computer Science 2025-10-10 Junyi Zhu , Savas Ozkan , Andrea Maracani , Sinan Mutlu , Cho Jung Min , Mete Ozay

Most Named Entity Recognition (NER) models operate under the assumption that training datasets are fully labelled. While it is valid for established datasets like CoNLL 2003 and OntoNotes, sometimes it is not feasible to obtain the complete…

Computation and Language · Computer Science 2022-11-29 Viktor Scherbakov , Vladimir Mayorov

Pre-trained Language Models (PLMs) can be accurately fine-tuned for downstream text processing tasks. Recently, researchers have introduced several parameter-efficient fine-tuning methods that optimize input prompts or adjust a small number…

Computation and Language · Computer Science 2024-06-07 Saeed Najafi , Alona Fyshe

Due to the limited availability of data, existing few-shot learning methods trained from scratch fail to achieve satisfactory performance. In contrast, large-scale pre-trained models such as CLIP demonstrate remarkable few-shot and…

Computer Vision and Pattern Recognition · Computer Science 2023-11-20 Kun Song , Huimin Ma , Bochao Zou , Huishuai Zhang , Weiran Huang

Pre-trained masked language models have demonstrated remarkable ability as few-shot learners. In this paper, as an alternative, we propose a novel approach to few-shot learning with pre-trained token-replaced detection models like ELECTRA.…

Computation and Language · Computer Science 2023-03-22 Zicheng Li , Shoushan Li , Guodong Zhou

We study clinical Named Entity Recognition (NER) on the CADEC corpus and compare three families of approaches: (i) BERT-style encoders (BERT Base, BioClinicalBERT, RoBERTa-large), (ii) GPT-4o used with few-shot in-context learning (ICL)…

Computation and Language · Computer Science 2025-10-28 Andrei Baroian