Bagging-based active learning model for named entity recognition with distant supervision

Lee, Sung‐Hee; Song, Yeongkil; Choi, Maengsik; Kim, Harksoo

doi:10.1109/bigcomp.2016.7425938

Cited by 10 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To construct NER's training data automatically, Jingbo et al applied named-entity dictionary refinement and developed a deep-learning-based NER by mapping the result [8]. In [9], the initial NER training data were automatically constructed through dictionary mapping of named entities and raw data from Wikipedia. The study reduced the number of errors in the initial NER training data by applying active learning with a bagging method and a conditional random field (CRF) method; thus, the NER system's performance was improved.…”

Section: A Automatic Construction Of Training Data Using Distant Supmentioning

confidence: 99%

Named-Entity Recognition Using Automatic Construction of Training Data From Social Media Messaging Apps

Lee

2020

IEEE Access

View full text Add to dashboard Cite

Section: A Automatic Construction Of Training Data Using Distant Supmentioning

confidence: 99%

Named-Entity Recognition Using Automatic Construction of Training Data From Social Media Messaging Apps

Lee

2020

IEEE Access

View full text Add to dashboard Cite

“…Furthermore, we use a bagging-based active learning process to refine noises in the corpus (i.e., words tannotated with incorrect NE classes), which refines the NER accuracy of our system. A preliminary discussion of our model was presented in [19] as a short paper. The preliminary model did not consider that most of entry words in a NE dictionary can have multiple NE classes during the distant supervision phase.…”

Section: Previous Workmentioning

confidence: 99%

Low-Cost Implementation of a Named Entity Recognition System for Voice-Activated Human-Appliance Interfaces in a Smart Home

Park

Kim

2018

Sustainability

Self Cite

View full text Add to dashboard Cite

When we develop voice-activated human-appliance interface systems in smart homes, named entity recognition (NER) is an essential tool for extracting execution targets from natural language commands. Previous studies on NER systems generally include supervised machine-learning methods that require a substantial amount of human-annotated training corpus. In the smart home environment, categories of named entities should be defined according to voice-activated devices (e.g., food names for refrigerators and song titles for music players). The previous machine-learning methods make it difficult to change categories of named entities because a large amount of the training corpus should be newly constructed by hand. To address this problem, we present a semi-supervised NER system to minimize the time-consuming and labor-intensive task of constructing the training corpus. Our system uses distant supervision methods with two kinds of auto-labeling processes: auto-labeling based on heuristic rules for single-class named entity corpus generation and auto-labeling based on a pre-trained single-class NER model for multi-class named entity corpus generation. Then, our system improves NER accuracy by using a bagging-based active learning method. In our experiments that included a generic domain that featured 11 named entity classes and a context-specific domain about baseball that featured 21 named entity classes, our system demonstrated good performances in both domains, with F1-measures of 0.777 and 0.958, respectively. Since our system was built from a relatively small human-annotated training corpus, we believe it is a viable alternative to current NER systems in smart home environments.

show abstract

“…Previous studies of Korean NER systems focused on the morphological-level text that is made using morphological analysis and handcrafted features (Na et al 2019;Yu and Ko 2017;Lee et al 2016) while there are various studies about character-level tagger (Kuru, Can, and Yuret 2016) or using sub-character information in Chinese (Dong et al 2016). Although morphological-level NER has advantages in utilizing richer linguistic information such as part-of-speech (POS) tags and word boundaries, it suffers from the potential issue of error propagation that error of morphological analysis results commonly lead to NER errors.…”

Section: Introductionmentioning

confidence: 99%

Learning Sub-Character level representation for Korean Named Entity Recognition

Kim

Kim²

2021

FLAIRS

View full text Add to dashboard Cite

Most of the previous studies on the Korean Named Entity Recognition (NER) topic focused on utilizing morphological-level information because the language is rich in character diversity. This paper illustrates an improved unigram-level Korean NER model with sub-character level representation, jamo, which can represent a unique linguistic structure of Korean and its syntactic properties and morphological variations. The experimental result shows that exploiting sub-character gives us a boost of + (avg) 2 F1, also, our proposed C-GRAM model outperformed about 3 F1 comparing with the baseline.

show abstract

Bagging-based active learning model for named entity recognition with distant supervision

Cited by 10 publications

References 7 publications

Named-Entity Recognition Using Automatic Construction of Training Data From Social Media Messaging Apps

Named-Entity Recognition Using Automatic Construction of Training Data From Social Media Messaging Apps

Low-Cost Implementation of a Named Entity Recognition System for Voice-Activated Human-Appliance Interfaces in a Smart Home

Learning Sub-Character level representation for Korean Named Entity Recognition

Contact Info

Product

Resources

About