Using Uniform-Design GEP for Part-of-Speech Tagging

Part-of-speech (POS) tagging is one of the research challenging fields in natural language processing (NLP). It requires good knowledge of a particular language with large amounts of data or corpora for feature engineering, which can lead to achieving a good performance of the tagger. Our main contribution in this research work is the designed Khasi POS corpus. Till date, there has been no form of any kind of Khasi corpus developed or formally developed. In the present designed Khasi POS corpus, each word is tagged manually using the designed tagset. Methods of deep learning have been used to experiment with our designed Khasi POS corpus. The POS tagger based on BiLSTM, combinations of BiLSTM with CRF, and character-based embedding with BiLSTM are presented. The main challenges of understanding and handling Natural Language toward Computational linguistics to encounter are anticipated. In the presently designed corpus, we have tried to solve the problems of ambiguities of words concerning their context usage, and also the orthography problems that arise in the designed POS corpus. The designed Khasi corpus size is around 96,100 tokens and consists of 6,616 distinct words. Initially, while running the first few sets of data of around 41,000 tokens in our experiment the taggers are found to yield considerably accurate results. When the Khasi corpus size has been increased to 96,100 tokens, we see an increase in accuracy rate and the analyses are more pertinent. As results, accuracy of 96.81% is achieved for the BiLSTM method, 96.98% for BiLSTM with CRF technique, and 95.86% for character-based with LSTM. Concerning substantial research from the NLP perspectives for Khasi, we also present some of the recently existing POS taggers and other NLP works on the Khasi language for comparative purposes.

Download Full-text

A Hidden Markov Model-based Part of Speech Tagger for Shekki’noono Language

International Journal of Computing ◽

10.47839/ijc.20.4.2448 ◽

2021 ◽

pp. 587-595

Author(s):

Alebachew Chiche ◽

Hiwot Kadi ◽

Tibebu Bekele

Keyword(s):

Natural Language Processing ◽

Natural Language ◽

Markov Model ◽

Hidden Markov Model ◽

Language Processing ◽

Hidden Markov ◽

Parts Of Speech ◽

Pos Tagging ◽

Part Of Speech ◽

Pos Tagger

Natural language processing plays a great role in providing an interface for human-computer communication. It enables people to talk with the computer in their formal language rather than machine language. This study aims at presenting a Part of speech tagger that can assign word class to words in a given paragraph sentence. Some of the researchers developed parts of speech taggers for different languages such as English Amharic, Afan Oromo, Tigrigna, etc. On the other hand, many other languages do not have POS taggers like Shekki’noono language. POS tagger is incorporated in most natural language processing tools like machine translation, information extraction as a basic component. So, it is compulsory to develop a part of speech tagger for languages then it is possible to work with an advanced natural language application. Because those applications enhance machine to machine, machine to human, and human to human communications. Although, one language POS tagger cannot be directly applied for other languages POS tagger. With the purpose for developing the Shekki’noono POS tagger, we have used the stochastic Hidden Markov Model. For the study, we have used 1500 sentences collected from different sources such as newspapers (which includes social, economic, and political aspects), modules, textbooks, Radio Programs, and bulletins. The collected sentences are labeled by language experts with their appropriate parts of speech for each word. With the experiments carried out, the part of speech tagger is trained on the training sets using Hidden Markov model. As experiments showed, HMM based POS tagging has achieved 92.77 % accuracy for Shekki’noono. And the POS tagger model is compared with the previous experiments in related works using HMM. As a future work, the proposed approaches can be utilized to perform an evaluation on a larger corpus.

Download Full-text

Part-of-Speech Tagging via Deep Neural Networks for Northern-Ethiopic Languages

Information Technology And Control ◽

10.5755/j01.itc.49.4.26808 ◽

2020 ◽

Vol 49 (4) ◽

pp. 482-494

Author(s):

Jurgita Kapočiūtė-Dzikienė ◽

Senait Gebremichael Tesfagergish

Keyword(s):

Neural Network ◽

Neural Networks ◽

Language Processing ◽

Deep Neural Networks ◽

Short Term Memory ◽

Parameter Tuning ◽

Feed Forward Neural Network ◽

Pos Tagging ◽

Part Of Speech ◽

Pos Tagger

Deep Neural Networks (DNNs) have proven to be especially successful in the area of Natural Language Processing (NLP) and Part-Of-Speech (POS) tagging—which is the process of mapping words to their corresponding POS labels depending on the context. Despite recent development of language technologies, low-resourced languages (such as an East African Tigrinya language), have received too little attention. We investigate the effectiveness of Deep Learning (DL) solutions for the low-resourced Tigrinya language of the Northern-Ethiopic branch. We have selected Tigrinya as the testbed example and have tested state-of-the-art DL approaches seeking to build the most accurate POS tagger. We have evaluated DNN classifiers (Feed Forward Neural Network – FFNN, Long Short-Term Memory method – LSTM, Bidirectional LSTM, and Convolutional Neural Network – CNN) on a top of neural word2vec word embeddings with a small training corpus known as Nagaoka Tigrinya Corpus. To determine the best DNN classifier type, its architecture and hyper-parameter set both manual and automatic hyper-parameter tuning has been performed. BiLSTM method was proved to be the most suitable for our solving task: it achieved the highest accuracy equal to 92% that is 65% above the random baseline.

Download Full-text

Improving Brill's tagger lexical and transformation rule for Afaan Oromo language

10.7287/peerj.preprints.1225v1 ◽

2015 ◽

Author(s):

Abraham G Ayana

Keyword(s):

Natural Language Processing ◽

Natural Language ◽

Language Processing ◽

Transformation Rule ◽

Initial State ◽

Training Corpus ◽

Part Of Speech Tagging ◽

Pos Tagging ◽

Part Of Speech ◽

Speech Tagging

Natural Language Processing (NLP) refers to Human-like language processing which reveals that it is a discipline within the field of Artificial Intelligence (AI). However, the ultimate goal of research on Natural Language Processing is to parse and understand language, which is not fully achieved yet. For this reason, much research in NLP has focused on intermediate tasks that make sense of some of the structure inherent in language without requiring complete understanding. One such task is part-of-speech tagging, or simply tagging. Lack of standard part of speech tagger for Afaan Oromo will be the main obstacle for researchers in the area of machine translation, spell checkers, dictionary compilation and automatic sentence parsing and constructions. Even though several works have been done in POS tagging for Afaan Oromo, the performance of the tagger is not sufficiently improved yet. Hence,the aim of this thesis is to improve Brill’s tagger lexical and transformation rule for Afaan Oromo POS tagging with sufficiently large training corpus. Accordingly, Afaan Oromo literatures on grammar and morphology are reviewed to understand nature of the language and also to identify possible tagsets. As a result, 26 broad tagsets were identified and 17,473 words from around 1100 sentences containing 6750 distinct words were tagged for training and testing purpose. From which 258 sentences are taken from the previous work. Since there is only a few ready made standard corpuses, the manual tagging process to prepare corpus for this work was challenging and hence, it is recommended that a standard corpus is prepared. Transformation-based Error driven learning are adapted for Afaan Oromo part of speech tagging. Different experiments are conducted for the rule based approach taking 20% of the whole data for testing. A comparison with the previously adapted Brill’s Tagger made. The previously adapted Brill’s Tagger shows an accuracy of 80.08% whereas the improved Brill’s Tagger result shows an accuracy of 95.6% which has an improvement of 15.52%. Hence, it is found that the size of the training corpus, the rule generating system in the lexical rule learner, and moreover, using Afaan Oromo HMM tagger as initial state tagger have a significant effect on the improvement of the tagger.

Download Full-text

Improving accuracy of Part-of-Speech (POS) tagging using hidden markov model and morphological analysis for Myanmar Language

International Journal of Electrical and Computer Engineering (IJECE) ◽

10.11591/ijece.v10i2.pp2023-2030 ◽

2020 ◽

Vol 10 (2) ◽

pp. 2023

Author(s):

Dim Lam Cing ◽

Khin Mar Soe

Keyword(s):

Language Processing ◽

High Performance ◽

Markov Models ◽

Hidden Markov ◽

Morphological Structure ◽

Word Segmentation ◽

Pos Tagging ◽

Part Of Speech ◽

Improving Accuracy ◽

Pos Tagger

In Natural Language Processing (NLP), Word segmentation and Part-of-Speech (POS) tagging are fundamental tasks. The POS information is also necessary in NLP’s preprocessing work applications such as machine translation (MT), information retrieval (IR), etc. Currently, there are many research efforts in word segmentation and POS tagging developed separately with different methods to get high performance and accuracy. For Myanmar Language, there are also separate word segmentors and POS taggers based on statistical approaches such as Neural Network (NN) and Hidden Markov Models (HMMs). But, as the Myanmar language's complex morphological structure, the OOV problem still exists. To keep away from error and improve segmentation by utilizing POS data, segmentation and labeling should be possible at the same time.The main goal of developing POS tagger for any Language is to improve accuracy of tagging and remove ambiguity in sentences due to language structure. This paper focuses on developing word segmentation and Part-of- Speech (POS) Tagger for Myanmar Language. This paper presented the comparison of separate word segmentation and POS tagging with joint word segmentation and POS tagging.

Download Full-text

QUASE: AN Ontology-Based Domain Specific Natural Language Question Answering System

International Journal of Recent Technology and Engineering - 2 ◽

10.35940/ijrte.d6773.118419 ◽

2019 ◽

Vol 8 (4) ◽

pp. 261-268

Keyword(s):

Natural Language ◽

Language Processing ◽

Question Answering ◽

Closed Domain ◽

Question Answering System ◽

Pos Tagging ◽

Part Of Speech ◽

Natural Language Question ◽

Finite Set ◽

Language Question

Since early days Question Answering (QA) has been an intuitive way of understanding the concept by humans. Considering its inevitable importance it has been introduced to children from very early age and they are promoted to ask more and more questions. With the progress in Machine Learning & Ontological semantics, Natural Language Question Answering (NLQA) has gained more popularity in recent years. In this paper QUASE (QUestion Answering System for Education) question answering system for answering natural language questions has been proposed which help to find answer for any given question in a closed domain containing finite set of documents. Th e QA s y st em m a inl y focuses on factoid questions. QUASE has used Question Taxonomy for Question Classification. Several Natural Language Processing techniques like Part of Speech (POS) tagging, Lemmatization, Sentence Tokenization have been applied for document processing to make search better and faster. DBPedia ontology has been used to validate the candidate answers. By application of this system the learners can gain knowledge on their own by getting precise answers to their questions asked in natural language instead of getting back merely a list of documents. The precision, recall and F measure metrics have been taken into account to evaluate the performance of answer type evaluation. The metric Mean Reciprocal Rank has been considered to evaluate the performance of QA system. Our experiment has shown significant improvement in classifying the questions in to correct answer types over other methods with approximately 91% accuracy and also providing better performance as a QA system in closed domain search.

Download Full-text

MulTed: a multilingual aligned and tagged parallel corpus

Applied Computing and Informatics ◽

10.1016/j.aci.2018.12.003 ◽

2020 ◽

Vol ahead-of-print (ahead-of-print) ◽

Cited By ~ 2

Author(s):

Imad Zeroual ◽

Abdelhak Lakhouaja

Keyword(s):

Language Processing ◽

Corpus Linguistics ◽

Statistical Machine Translation ◽

Language Recognition ◽

Parallel Corpora ◽

Pos Tagging ◽

Part Of Speech ◽

Language Studies ◽

Mapping Process ◽

Pos Tagger

Recently, more data-driven approaches are demanding multilingual parallel resources primarily in the cross-language studies. To meet these demands, building multilingual parallel corpora are becoming the focus of many Natural Language Processing (NLP) scientific groups. Unlike monolingual corpora, the number of available multilingual parallel corpora is limited. In this paper, the MulTed, a corpus of subtitles extracted from TEDx talks is introduced. It is multilingual, Part of Speech (PoS) tagged, and bilingually sentence-aligned with English as a pivot language. This corpus is designed for many NLP applications, where the sentence-alignment, the PoS tagging, and the size of corpora are influential such as statistical machine translation, language recognition, and bilingual dictionary generation. Currently, the corpus has subtitles that cover 1100 talks available in over 100 languages. The subtitles are classified based on a variety of topics such as Business, Education, and Sport. Regarding the PoS tagging, the Treetagger, a language-independent PoS tagger, is used; then, to make the PoS tagging maximally useful, a mapping process to a universal common tagset is performed. Finally, we believe that making the MulTed corpus available for a public use can be a significant contribution to the literature of NLP and corpus linguistics, especially for under-resourced languages.

Download Full-text

Attentive Tensor Product Learning

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v33i01.33011344 ◽

2019 ◽

Vol 33 ◽

pp. 1344-1351 ◽

Cited By ~ 1

Author(s):

Qiuyuan Huang ◽

Li Deng ◽

Dapeng Wu ◽

Chang Liu ◽

Xiaodong He

Keyword(s):

Deep Learning ◽

Natural Language ◽

Tensor Product ◽

Language Processing ◽

Short Term Memory ◽

Feedforward Neural Networks ◽

Grammatical Structure ◽

Symbolic Model ◽

Pos Tagging ◽

Part Of Speech

This paper proposes a novel neural architecture — Attentive Tensor Product Learning (ATPL) — to represent grammatical structures of natural language in deep learning models. ATPL exploits Tensor Product Representations (TPR), a structured neural-symbolic model developed in cognitive science, to integrate deep learning with explicit natural language structures and rules. The key ideas of ATPL are: 1) unsupervised learning of role-unbinding vectors of words via the TPR-based deep neural network; 2) the use of attention modules to compute TPR; and 3) the integration of TPR with typical deep learning architectures including long short-term memory and feedforward neural networks. The novelty of our approach lies in its ability to extract the grammatical structure of a sentence by using role-unbinding vectors, which are obtained in an unsupervised manner. Our ATPL approach is applied to 1) image captioning, 2) part of speech (POS) tagging, and 3) constituency parsing of a natural language sentence. The experimental results demonstrate the effectiveness of the proposed approach in all these three natural language processing tasks.

Download Full-text

POS Tagging Bahasa Madura dengan Menggunakan Algoritma Brill Tagger

Jurnal Teknologi Informasi dan Ilmu Komputer ◽

10.25126/jtiik.2020722449 ◽

2020 ◽

Vol 7 (6) ◽

pp. 1121

Author(s):

Nindian Puspa Dewi ◽

Ubaidi Ubaidi

Keyword(s):

Natural Language Processing ◽

Natural Language ◽

Digital Media ◽

Language Processing ◽

Text Processing ◽

Pos Tagging ◽

Part Of Speech ◽

Average Accuracy ◽

Conducting Research ◽

Regional Languages

Bahasa Madura adalah bahasa daerah yang selain digunakan di Pulau Madura juga digunakan di daerah lainnya seperti di kota Jember, Pasuruan, dan Probolinggo. Sebagai bahasa daerah, Bahasa Madura mulai banyak ditinggalkan khususnya di kalangan anak muda. Beberapa penyebabnya adalah adanya rasa gengsi dan tingkat kesulitan untuk mempelajari Bahasa Madura yang memiliki ragam dialek dan tingkat bahasa. Berkurangnya penggunaan Bahasa Madura dapat mengakibatkan punahnya Bahasa Madura sebagai salah satu bahasa daerah yang ada di Indonesia. Oleh karena itu, perlu adanya usaha untuk mempertahankan dan memelihara Bahasa Madura. Salah satunya adalah dengan melakukan penelitian tentang Bahasa Madura dalam bidang Natural Language Processing sehingga kedepannya pembelajaran tentang Bahasa Madura dapat dilakukan melalui media digital. Part Of Speech (POS) Tagging adalah dasar penelitian text processing, sehingga perlu untuk dibuat aplikasi POS Tagging Bahasa Madura untuk digunakan pada penelitian Natural Languange Processing lainnya. Dalam penelitian ini, POS Tagging dibuat dengan menggunakan Algoritma Brill Tagger dengan menggunakan corpus yang berisi 10.535 kata Bahasa Madura. POS Tagging dengan Brill Tagger dapat memberikan kelas kata yang sesuai pada kata dengan menggunakan aturan leksikal dan kontekstual. Brill Tagger merupakan algoritma dengan tingkat akurasi yang paling baik saat diterapkan dalam Bahasa Inggris, Bahasa Indonesia dan beberapa bahasa lainnya. Dari serangkaian percobaan dengan beberapa perubahan nilai threshold tanpa memperhatikan OOV (Out Of Vocabulary), menunjukkan rata-rata akurasi mencapai lebih dari 80% dengan akurasi tertinggi mencapai 86.67% dan untuk pengujian dengan memperhatikan OOV mencapai rata-rata akurasi 67.74%. Jadi dapat disimpulkan bahwa Brill Tagger dapat digunakan untuk Bahasa Madura dengan tingkat akurasi yang baik. Abstract Bahasa Madura is regional language which is not only used on Madura Island but is also used in other areas such as in several regions in Jember, Pasuruan, and Probolinggo. Today, Bahasa Madura began to be abandoned, especially among young people. One reason is sense of pride and also quite difficult to learn Bahasa Madura because it has a variety of dialects and language levels. The reduced use of Bahasa Madura can lead to the extinction of Bahasa Madura as one of the regional languages in Indonesia. Therefore, there needs to be an effort to maintain Madurese Language. One of them is by conducting research on Madurese Language in the field of Natural Language Processing so that in the future learning about Madurese can be done through digital media. Part of Speech (POS) Tagging is the basis of text processing research, so the Madura Language POS Tagging application needs to be made for use in other Natural Language Processing research. This study uses Brill Tagger by using a corpus containing 10,535 words. POS Tagging with Brill Tagger Algorithm can provide the appropriate word class to word using lexical and contextual rule. The reason for using Brill Tagger is because it is the algorithm that has the best accuracy when implemented in English, Indonesian and several other languages. The experimental results with Brill Tagger show that the average accuracy without OOV (Out Of Vocabulary) obtained is 86.6% with the highest accuracy of 86.94% and the average accuracy for OOV words reached 67.22%. So it can be concluded that the Brill Tagger Algorithm can also be used for Bahasa Madura with a good degree of accuracy.

Download Full-text

Improving Brill's tagger lexical and transformation rule for Afaan Oromo language

10.7287/peerj.preprints.1225 ◽

2015 ◽

Author(s):

Abraham G Ayana

Keyword(s):

Natural Language Processing ◽

Natural Language ◽

Language Processing ◽

Transformation Rule ◽

Initial State ◽

Training Corpus ◽

Part Of Speech Tagging ◽

Pos Tagging ◽

Part Of Speech ◽

Speech Tagging

Natural Language Processing (NLP) refers to Human-like language processing which reveals that it is a discipline within the field of Artificial Intelligence (AI). However, the ultimate goal of research on Natural Language Processing is to parse and understand language, which is not fully achieved yet. For this reason, much research in NLP has focused on intermediate tasks that make sense of some of the structure inherent in language without requiring complete understanding. One such task is part-of-speech tagging, or simply tagging. Lack of standard part of speech tagger for Afaan Oromo will be the main obstacle for researchers in the area of machine translation, spell checkers, dictionary compilation and automatic sentence parsing and constructions. Even though several works have been done in POS tagging for Afaan Oromo, the performance of the tagger is not sufficiently improved yet. Hence,the aim of this thesis is to improve Brill’s tagger lexical and transformation rule for Afaan Oromo POS tagging with sufficiently large training corpus. Accordingly, Afaan Oromo literatures on grammar and morphology are reviewed to understand nature of the language and also to identify possible tagsets. As a result, 26 broad tagsets were identified and 17,473 words from around 1100 sentences containing 6750 distinct words were tagged for training and testing purpose. From which 258 sentences are taken from the previous work. Since there is only a few ready made standard corpuses, the manual tagging process to prepare corpus for this work was challenging and hence, it is recommended that a standard corpus is prepared. Transformation-based Error driven learning are adapted for Afaan Oromo part of speech tagging. Different experiments are conducted for the rule based approach taking 20% of the whole data for testing. A comparison with the previously adapted Brill’s Tagger made. The previously adapted Brill’s Tagger shows an accuracy of 80.08% whereas the improved Brill’s Tagger result shows an accuracy of 95.6% which has an improvement of 15.52%. Hence, it is found that the size of the training corpus, the rule generating system in the lexical rule learner, and moreover, using Afaan Oromo HMM tagger as initial state tagger have a significant effect on the improvement of the tagger.

Download Full-text