Named Entity Recognition with Word Embeddings and Wikipedia Categories for a Low-Resource Language

Abstract

In this article, we propose a word embedding--based named entity recognition (NER) approach. NER is commonly approached as a sequence labeling task with the application of methods such as conditional random field (CRF). However, for low-resource languages without the presence of sufficiently large training data, methods such as CRF do not perform well. In our work, we make use of the proximity of the vector embeddings of words to approach the NER problem. The hypothesis is that word vectors belonging to the same name category, such as a person’s name, occur in close vicinity in the abstract vector space of the embedded words. Assuming that this clustering hypothesis is true, we apply a standard classification approach on the vectors of words to learn a decision boundary between the NER classes. Our NER experiments are conducted on a morphologically rich and low-resource language, namely Bengali. Our approach significantly outperforms standard baseline CRF approaches that use cluster labels of word embeddings and gazetteers constructed from Wikipedia. Further, we propose an unsupervised approach (that uses an automatically created named entity (NE) gazetteer from Wikipedia in the absence of training data). For a low-resource language, the word vectors obtained from Wikipedia are not sufficient to train a classifier. As a result, we propose to make use of the distance measure between the vector embeddings of words to expand the set of Wikipedia training examples with additional NEs extracted from a monolingual corpus that yield significant improvement in the unsupervised NER performance. In fact, our expansion method performs better than the traditional CRF-based (supervised) approach (i.e., F-score of 65.4% vs. 64.2%). Finally, we compare our proposed approach to the official submission for the IJCNLP-2008 Bengali NER shared task and achieve an overall improvement of F-score 11.26% with respect to the best official system.

Combining the NER-OCR methods to improve information retrieval efficiency in the Indonesian posters

“…Pengambilan entitas informasi berbasis teknologi informasi banyak dilakukan menggunakan metode Named Entity Recognition (NER). NER pada penelitian sebelumnya mampu digunakan dalam pengambilan informasi di kartu nama [2], video tutorial [3], teks artikel [4], teks unggahan di media sosial [5]- [7], dan informasi entitas di dalam rekaman data BTS [8]. Saat ini, berbagai tools yang telah tersedia dapat digunakan untuk menerapkan metode ini.…”

“…Namun demikian, performa NER-tools pada poster berbahasa Indonesia masih mengalami kendala akurasi [9]- [11] karena bahasa Indonesia termasuk kategori bahasa dengan sumber daya rendah (low-resource language), seperti halnya bahasa Bengali [4] dan Cina [12]. Salah satu penyebabnya adalah karena bahasa Indonesia bukan bahasa internasional seperti bahasa Inggris atau Prancis yang sudah memiliki korpus teks dengan jutaan perbendaharaan kata dan tersedia di Internet [9].…”

Hit or Miss? Evaluating the Potential of a Research Niche: A Case Study in the Field of Virtual Quality Management

“…According to Reference [28], "this is an important task because its performance directly affects the quality of many succeeding NLP applications such as information extraction". Its application recently gained popularity for processing semi-structured knowledge bases regarding entity disambiguation/mapping [29][30][31] and extracting/retrieving information [32] or for analyzing content generated on social media [33][34][35].…”

Information extraction using neural language models for the case of online job listings analysis

“…Примером данного подхода является [8], в котором авторы применяют Word2vec для генерации кластеров слов с близкими контекстами. Такой подход показывает лучшие результаты в сравнении с классическим CRF для языков с низким объемом размеченных корпусов (например, Бенгальский язык).…”