paper-with-me

Papers

CoNLL#: Fine-grained Error Analysis and a Corrected Test Set for CoNLL-03 English

2024-05-20 · Andrew Rueda, Elena Álvarez Mellado, Constantine Lignos

Modern named entity recognition systems have steadily improved performance in the age of larger and more powerful neural models. However, over the past several years, the state-of-the-art has seemingly hit another plateau on the benchmark CoNLL-03 English dataset. In this paper, we perform a deep dive into the test outputs of the highest-performing NER models, conducting a fine-grained evaluation of their performance by introducing new document-level annotations on the test set. We go beyond F1 scores by categorizing errors in order to interpret the true state of the art for NER and guide future work. We review previous attempts at correcting the various flaws of the test set and introduce CoNLL#, a new corrected version of the test set that addresses its systematic and most prevalent errors, allowing for low-noise, interpretable error analysis.

📄 PDF Abstract BibTeX arXiv:2405.11865

Code (0)

등록된 구현이 없습니다.

Tasks

named-entity-recognitionNamed Entity RecognitionNER

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

CleanCoNLL: A Nearly Noise-Free Named Entity Recognition Dataset

2023-10-24 · Susanna Rücker, Alan Akbik

The CoNLL-03 corpus is arguably the most well-known and utilized benchmark dataset for named entity recognition (NER). However, prior works found significant numbers of annotation errors, incompleteness, and inconsistenc…

Entity Linkingnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)+1

Automatic Annotation and Evaluation of Error Types for Grammatical Error Correction

2017-07-01 · ACL 2017 7 · Christopher Bryant, Mariano Felice, Ted Briscoe

Until now, error type performance for Grammatical Error Correction (GEC) systems could only be measured in terms of recall because system output is not annotated. To overcome this problem, we introduce ERRANT, a grammati…

Annotated Code SearchGrammatical Error CorrectionNews AnnotationTable annotation+1

Reaching Human-level Performance in Automatic Grammatical Error Correction: An Empirical Study

2018-07-03 · Tao Ge, Furu Wei, Ming Zhou

Neural sequence-to-sequence (seq2seq) approaches have proven to be successful in grammatical error correction (GEC). Based on the seq2seq framework, we propose a novel fluency boost learning and inference mechanism. Flue…

Grammatical Error CorrectionSentence

Identifying Incorrect Labels in the CoNLL-2003 Corpus

2020-11-01 · CONLL 2020 · Frederick Reiss, Hong Xu, Bryan Cutler, Karthik Muthuraman 외

The CoNLL-2003 corpus for English-language named entity recognition (NER) is one of the most influential corpora for NER model research. A large number of publications, including many landmark works, have used this corpu…

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

A Self-Refinement Strategy for Noise Reduction in Grammatical Error Correction

2020-10-07 · Findings of the Association for Computational Linguistics 2020 · Masato Mita, Shun Kiyono, Masahiro Kaneko, Jun Suzuki 외

Existing approaches for grammatical error correction (GEC) largely rely on supervised learning with manually created GEC datasets. However, there has been little focus on verifying and ensuring the quality of the dataset…

DenoisingGrammatical Error Correction