Papers with Code 아카이브
Named Entity Recognition (NER)
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 13
- 평가표
- 76
- 보존된 평가 기록
- 439
Named Entity Recognition (NER) is a task of Natural Language Processing (NLP) that involves identifying and classifying named entities in a text into predefined categories such as person names, organizations, locations, and others. The goal of NER is to extract structured information from unstructured text data and represent it in a machine-readable format. Approaches typically use BIO notation, which differentiates the beginning (B) and the inside (I) of entities. O is used for non-entity tokens.
Example:
| Mark | Watney | visited | Mars |
|---|---|---|---|
| B-PER | I-PER | O | B-LOC |
<span style="color:grey; opacity: 0.6">( Image credit: Zalando )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/huspacy/huspacy
공식 코드Advancing Hungarian Text Processing with HuSpaCy: Efficient and Accurate NLP Pipelines
https://github.com/hynky1999/czech-news-classification-dataset
공식 코드A Dataset and Strong Baselines for Classification of Czech News Texts
https://github.com/hysonlab/videberta
공식 코드ViDeBERTa: A powerful pre-trained language model for Vietnamese
https://github.com/iacercalixto/visualsem
공식 코드Endowing Language Models with Multimodal Knowledge Graph Representations
https://github.com/ialab-puc/BioNLP-StressTest
공식 코드https://github.com/ibraheem-moosa/xlm-indic
공식 코드https://github.com/ibrahimself/fewtopner
공식 코드https://github.com/icescentral/MASK_public
공식 코드MASK: A flexible framework to facilitate de-identification of clinical texts
https://github.com/idiap/atco2-corpus
공식 코드https://github.com/iesl/dilated-cnn-ner
공식 코드Fast and Accurate Entity Recognition with Iterated Dilated Convolutions
https://github.com/iid-ulaval/FIJO-dataset
공식 코드https://github.com/iid-ulaval/fijo-code
공식 코드https://github.com/ijauregiCMCRC/healthNER
공식 코드https://github.com/ikergarcia1996/context-enriched-ner
공식 코드https://github.com/ink-usc/fewner
공식 코드Good Examples Make A Faster Learner: Simple Demonstration-based Learning for Low-resource NER
https://github.com/is2ai/kaznerd
공식 코드https://github.com/ishan00/meta-learning-for-multi-task-multilingual
공식 코드Meta-Learning for Effective Multi-task and Multilingual Modelling
https://github.com/isi-boston/ed-pooling
공식 코드Impact of Subword Pooling Strategy on Cross-lingual Event Detection
https://github.com/ispras-texterra/pioner
공식 코드pioNER: Datasets and Baselines for Armenian Named Entity Recognition
https://github.com/ixa-ehu/ixa-pipe-nerc
공식 코드Robust Multilingual Named Entity Recognition with Shallow Semi-Supervised Features
https://github.com/izhx/CLasDA
공식 코드Crowdsourcing Learning as Domain Adaptation: A Case Study on Named Entity Recognition
https://github.com/izhx/ner-unlabeled-data-retrieval
공식 코드https://github.com/jacobkrantz/lstm-syllabify
공식 코드Language-Agnostic Syllabification with Neural Sequence Labeling
https://github.com/jacobvsdanniel/cross-ner
공식 코드Why Attention? Analyze BiLSTM Deficiency and Its Remedies in the Case of NER
https://github.com/jacobvsdanniel/cross_ner
공식 코드Why Attention? Analyze BiLSTM Deficiency and Its Remedies in the Case of NER
https://github.com/jbdel/vilmedic
공식 코드Improving the Factual Correctness of Radiology Report Generation with Semantic Rewards
https://github.com/jd-coderepos/contributions-ner-cs
공식 코드Computer Science Named Entity Recognition in the Open Research Knowledge Graph
https://github.com/jeniyat/StackOverflowNER
공식 코드https://github.com/jeniyat/WNUT_2020_NER
공식 코드WNUT-2020 Task 1 Overview: Extracting Entities and Relations from Wet Lab Protocols
https://github.com/jenlindadsouza/NLPContributions
공식 코드https://github.com/jetsunwhitton/rct-art
공식 코드https://github.com/jiangguochaogg/p-icl
공식 코드P-ICL: Point In-Context Learning for Named Entity Recognition with Large Language Models
https://github.com/jiangguochaogg/toner
공식 코드ToNER: Type-oriented Named Entity Recognition with Generative Language Model
https://github.com/jiesutd/LatticeLSTM
공식 코드https://github.com/jiesutd/NCRFpp
공식 코드Design Challenges and Misconceptions in Neural Sequence Labeling
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.