paper-with-me

홈 › Papers

DualNER: A Dual-Teaching framework for Zero-shot Cross-lingual Named Entity Recognition

2022-11-15 · Jiali Zeng, Yufan Jiang, Yongjing Yin, Xu Wang, Binghuai Lin, Yunbo Cao

We present DualNER, a simple and effective framework to make full use of both annotated source language corpus and unlabeled target language text for zero-shot cross-lingual named entity recognition (NER). In particular, we combine two complementary learning paradigms of NER, i.e., sequence labeling and span prediction, into a unified multi-task framework. After obtaining a sufficient NER model trained on the source data, we further train it on the target data in a {\it dual-teaching} manner, in which the pseudo-labels for one task are constructed from the prediction of the other task. Moreover, based on the span prediction, an entity-aware regularization is proposed to enhance the intrinsic cross-lingual alignment between the same entities in different languages. Experiments and analysis demonstrate the effectiveness of our DualNER. Code is available at https://github.com/lemon0830/dualNER.

📄 PDF Abstract BibTeX arXiv:2211.08104

Code (0)

등록된 구현이 없습니다.

Tasks

named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NERPrediction

Similar Papers 제목 키워드 기반

DualNeRF: Text-Driven 3D Scene Editing via Dual-Field Representation

2025-02-22 · Yuxuan Xiong, Yue Shi, Yishun Dou, Bingbing Ni

Recently, denoising diffusion models have achieved promising results in 2D image generation and editing. Instruct-NeRF2NeRF (IN2N) introduces the success of diffusion into 3D scene editing through an "Iterative dataset u…

3D scene EditingDenoisingImage GenerationNeRF

Unsupervised Prompt Tuning for Text-Driven Object Detection

2023-01-01 · ICCV 2023 1 · Weizhen He, WeiJie Chen, Binbin Chen, Shicai Yang 외

Grounded language-image pre-trained models have shown strong zero-shot generalization to various downstream object detection tasks. Despite their promising performance, the models rely heavily on the laborious prompt…

Data AugmentationObjectobject-detectionObject Detection+2

Zero-Shot Cross-Lingual Abstractive Sentence Summarization through Teaching Generation and Attention

2019-07-01 · ACL 2019 7 · Xiangyu Duan, Mingming Yin, Min Zhang, Boxing Chen 외

Abstractive Sentence Summarization (ASSUM) targets at grasping the core idea of the source sentence and presenting it as the summary. It is extensively studied using statistical models or neural models based on the large…

SentenceSentence SummarizationTranslation

Dual Teaching: A Practical Semi-supervised Wrapper Method

2016-11-12 · Fuqaing Liu, Chenwei Deng, Fukun Bi, Yiding Yang

Semi-supervised wrapper methods are concerned with building effective supervised classifiers from partially labeled data. Though previous works have succeeded in some fields, it is still difficult to apply semi-supervise…

CountCLIP -- [Re] Teaching CLIP to Count to Ten

2024-06-05 · Harshvardhan Mestha, Tejas Agrawal, Karan Bania, Shreyas V 외

Large vision-language models (VLMs) are shown to learn rich joint image-text representations enabling high performances in relevant downstream tasks. However, they fail to showcase their quantitative understanding of obj…

zero-shot-classificationZero-Shot CountingZero-Shot Learning