A Bootstrapping Approach for Training a NER with Conditional Random Fields

• Type: Article in International Conference Proceedings Book
• Date: 2011

Authors

teixeira, j (Author) FEUP; sarmento, l (Author) Other; oliveira, e (Author) FEUP

Conference proceedings International

Title: PROGRESS IN ARTIFICIAL INTELLIGENCE

Pages: 664-678

15th Portuguese Conference on Artificial Intelligence (EPIA 2011)

Lisbon, PORTUGAL, OCT 10-13, 2011

Indexing

ISI Proceedings

ISI Web of Knowledge - 2 Citations

Scopus - 1 Citation

Scientific classification

FOS: Natural sciences > Computer and information sciences

Other information

Authenticus ID: P-002-VZ3

DOI: 10.1007/978-3-642-24769-9_48

Abstract (EN): In this paper we present a bootstrapping approach for training a Named Entity Recognition (NER) system. Our method starts by annotating persons' names on a dataset of 50,000 news items. This is performed using a simple dictionary-based approach. Using such training set we build a classification model based on Conditional Random Fields (CRF). We then use the inferred classification model to perform additional annotations of the initial seed corpus, which is then used for training a new classification model. This cycle is repeated until the NER model stabilizes. We evaluate each of the bootstrapping iterations by calculating: (i) the precision and recall of the NER model in annotating a small gold-standard collection (HAREM); (ii) the precision and recall of the CRF bootstrapping annotation method over a small sample of news; and (iii) the correctness and the number of new names identified. Additionally, we compare the NER model with a dictionary-based approach, our baseline method. Results show that our bootstrapping approach stabilizes after 7 iterations, achieving high values of precision (83%) and recall (68%).

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 15