A Neural Joint Model with BERT for Burmese Syllable Segmentation, Word Segmentation, and POS Tagging

2021 ◽  
Vol 20 (4) ◽  
pp. 1-23
Author(s):  
Cunli Mao ◽  
Zhibo Man ◽  
Zhengtao Yu ◽  
Shengxiang Gao ◽  
Zhenhan Wang ◽  
...  
Keyword(s):  
Error Propagation ◽  
Joint Model ◽  
Word Segmentation ◽  
Joint Learning ◽  
Pos Tagging ◽  
Part Of Speech ◽  
Proposed Model ◽  
Syllable Segmentation ◽  
Benchmark Datasets ◽  
Fine Tune

The smallest semantic unit of the Burmese language is called the syllable. In the present study, it is intended to propose the first neural joint learning model for Burmese syllable segmentation, word segmentation, and part-of-speech ( POS ) tagging with the BERT. The proposed model alleviates the error propagation problem of the syllable segmentation. More specifically, it extends the neural joint model for Vietnamese word segmentation, POS tagging, and dependency parsing [28] with the pre-training method of the Burmese character, syllable, and word embedding with BiLSTM-CRF-based neural layers. In order to evaluate the performance of the proposed model, experiments are carried out on Burmese benchmark datasets, and we fine-tune the model of multilingual BERT. Obtained results show that the proposed joint model can result in an excellent performance.

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

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.

scholarly journals Introducing Various Semantic Models for Amharic: Experimentation and Evaluation with Multiple Tasks and Datasets

2021 ◽  
Vol 13 (11) ◽  
pp. 275
Author(s):  
Seid Muhie Yimam ◽  
Abinew Ali Ayele ◽  
Gopalakrishnan Venkatesh ◽  
Ibrahim Gashaw ◽  
Chris Biemann
Keyword(s):  
Machine Learning ◽  
Sentiment Classification ◽  
Network Embedding ◽  
Low Resource ◽  
Pos Tagging ◽  
Semitic Language ◽  
Semantic Models ◽  
Benchmark Datasets ◽  
Fine Tune ◽  
Better Than

The availability of different pre-trained semantic models has enabled the quick development of machine learning components for downstream applications. However, even if texts are abundant for low-resource languages, there are very few semantic models publicly available. Most of the publicly available pre-trained models are usually built as a multilingual version of semantic models that will not fit well with the need for low-resource languages. We introduce different semantic models for Amharic, a morphologically complex Ethio-Semitic language. After we investigate the publicly available pre-trained semantic models, we fine-tune two pre-trained models and train seven new different models. The models include Word2Vec embeddings, distributional thesaurus (DT), BERT-like contextual embeddings, and DT embeddings obtained via network embedding algorithms. Moreover, we employ these models for different NLP tasks and study their impact. We find that newly-trained models perform better than pre-trained multilingual models. Furthermore, models based on contextual embeddings from FLAIR and RoBERTa perform better than word2Vec models for the NER and POS tagging tasks. DT-based network embeddings are suitable for the sentiment classification task. We publicly release all the semantic models, machine learning components, and several benchmark datasets such as NER, POS tagging, sentiment classification, as well as Amharic versions of WordSim353 and SimLex999.

scholarly journals Sparse Coding of Neural Word Embeddings for Multilingual Sequence Labeling

2017 ◽  
Vol 5 ◽  
pp. 247-261 ◽  
Author(s):  
Gáabor Berend
Keyword(s):  
Sparse Coding ◽  
Named Entity Recognition ◽  
Training Data ◽  
Entity Recognition ◽  
Named Entity ◽  
Part Of Speech Tagging ◽  
Pos Tagging ◽  
Sequence Labeling ◽  
Part Of Speech ◽  
Proposed Model

In this paper we propose and carefully evaluate a sequence labeling framework which solely utilizes sparse indicator features derived from dense distributed word representations. The proposed model obtains (near) state-of-the art performance for both part-of-speech tagging and named entity recognition for a variety of languages. Our model relies only on a few thousand sparse coding-derived features, without applying any modification of the word representations employed for the different tasks. The proposed model has favorable generalization properties as it retains over 89.8% of its average POS tagging accuracy when trained at 1.2% of the total available training data, i.e. 150 sentences per language.

GreyReID: A Novel Two-stream Deep Framework with RGB-grey Information for Person Re-identification

2021 ◽  
Vol 17 (1) ◽  
pp. 1-22
Author(s):  
Lei Qi ◽  
Lei Wang ◽  
Jing Huo ◽  
Yinghuan Shi ◽  
Yang Gao
Keyword(s):  
Loss Function ◽  
Feature Representation ◽  
Query Image ◽  
Joint Learning ◽  
Ranking List ◽  
Generalization Ability ◽  
Feature Representations ◽  
Benchmark Datasets ◽  
Rgb Images ◽  
Fine Tune

In this article, we observe that most false positive images (i.e., different identities with query images) in the top ranking list usually have the similar color information with the query image in person re-identification (Re-ID). Meanwhile, when we use the greyscale images generated from RGB images to conduct the person Re-ID task, some hard query images can obtain better performance compared with using RGB images. Therefore, RGB and greyscale images seem to be complementary to each other for person Re-ID. In this article, we aim to utilize both RGB and greyscale images to improve the person Re-ID performance. To this end, we propose a novel two-stream deep neural network with RGB-grey information, which can effectively fuse RGB and greyscale feature representations to enhance the generalization ability of Re-ID. First, we convert RGB images to greyscale images in each training batch. Based on these RGB and greyscale images, we train the RGB and greyscale branches, respectively. Second, to build up connections between RGB and greyscale branches, we merge the RGB and greyscale branches into a new joint branch. Finally, we concatenate the features of all three branches as the final feature representation for Re-ID. Moreover, in the training process, we adopt the joint learning scheme to simultaneously train each branch by the independent loss function, which can enhance the generalization ability of each branch. Besides, a global loss function is utilized to further fine-tune the final concatenated feature. The extensive experiments on multiple benchmark datasets fully show that the proposed method can outperform the state-of-the-art person Re-ID methods. Furthermore, using greyscale images can indeed improve the person Re-ID performance in the proposed deep framework.

Out-domain Chinese new word detection with statistics-based character embedding

2019 ◽  
Vol 25 (2) ◽  
pp. 239-255
Author(s):  
Yuzhi Liang ◽  
Min Yang ◽  
Jia Zhu ◽  
S. M. Yiu
Keyword(s):  
Short Term Memory ◽  
Conditional Random Field ◽  
Word Segmentation ◽  
Training Data ◽  
Chinese Word ◽  
Chinese Word Segmentation ◽  
High Quality ◽  
Pos Tagging ◽  
Part Of Speech ◽  
Word Detection

AbstractUnlike English and other Western languages, many Asian languages such as Chinese and Japanese do not delimit words by space. Word segmentation and new word detection are therefore key steps in processing these languages. Chinese word segmentation can be considered as a part-of-speech (POS)-tagging problem. We can segment corpus by assigning a label for each character which indicates the position of the character in a word (e.g., “B” for word beginning, and “E” for the end of the word, etc.). Chinese word segmentation seems to be well studied. Machine learning models such as conditional random field (CRF) and bi-directional long short-term memory (LSTM) have shown outstanding performances on this task. However, the segmentation accuracies drop significantly when applying the same approaches to out-domain cases, in which high-quality in-domain training data are not available. An example of out-domain applications is the new word detection in Chinese microblogs for which the availability of high-quality corpus is limited. In this paper, we focus on out-domain Chinese new word detection. We first design a new method Edge Likelihood (EL) for Chinese word boundary detection. Then we propose a domain-independent Chinese new word detector (DICND); each Chinese character is represented as a low-dimensional vector in the proposed framework, and segmentation-related features of the character are used as the values in the vector.

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

2016 ◽  
Vol 26 (04) ◽  
pp. 1750060 ◽  
Author(s):  
Chengyao Lv ◽  
Huihua Liu ◽  
Yuanxing Dong ◽  
Fangyuan Li ◽  
Yuan Liang
Keyword(s):  
Natural Language ◽  
Language Processing ◽  
Uniform Design ◽  
Accuracy Rate ◽  
Pos Tagging ◽  
Part Of Speech ◽  
Proposed Model ◽  
Wide Range ◽  
Unknown Words ◽  
Pos Tagger

In natural language processing (NLP), a crucial subsystem in a wide range of applications is a part-of-speech (POS) tagger, which labels (or classifies) unannotated words of natural language with POS labels corresponding to categories such as noun, verb or adjective. This paper proposes a model of uniform-design genetic expression programming (UGEP) for POS tagging. UGEP is used to search for appropriate structures in function space of POS tagging problems. After the evolution of sequence of tags, GEP can find the best individual as solution. Experiments on Brown Corpus show that (1) in closed lexicon tests, UGEP model can get higher accuracy rate of 98.8% which is much better than genetic algorithm model, neural networks and hidden Markov model (HMM) model.; (2) in open lexicon tests, the proposed model can also achieve higher accuracy rate of 97.4% and a high accuracy rate on unknown words of 88.6%.

scholarly journals Segmenting Chinese Microtext: Joint Informal-Word Detection and Segmentation with Neural Networks

2017 ◽  
Author(s):  
Meishan Zhang ◽  
Guohong Fu ◽  
Nan Yu
Keyword(s):  
Neural Networks ◽  
State Of The Art ◽  
Joint Model ◽  
Word Segmentation ◽  
Chinese Word ◽  
Chinese Word Segmentation ◽  
Training Corpus ◽  
Standard Testing ◽  
Proposed Model ◽  
Word Detection

State-of-the-art Chinese word segmentation systems typically exploit supervised modelstrained on a standard manually-annotated corpus,achieving performances over 95% on a similar standard testing corpus.However, the performances may drop significantly when the same models are applied onto Chinese microtext.One major challenge is the issue of informal words in the microtext.Previous studies show that informal word detection can be helpful for microtext processing.In this work, we investigate it under the neural setting, by proposing a joint segmentation model that integrates the detection of informal words simultaneously.In addition, we generate training corpus for the joint model by using existing corpus automatically.Experimental results show that the proposed model is highly effective for segmentation of Chinese microtext.

Lexical Rule and Lexicon Effect for Part of Speech Tagging Bahasa Madura

2018 ◽  
Vol 18 (1) ◽  
pp. 65-72
Author(s):  
Nindian Puspa Dewi ◽  
Ubaidi Ubaidi
Keyword(s):  
Text Processing ◽  
Part Of Speech Tagging ◽  
Pos Tagging ◽  
Part Of Speech ◽  
Speech Tagging ◽  
Bahasa Indonesia

POS Tagging adalah dasar untuk pengembangan Text Processing suatu bahasa. Dalam penelitian ini kita meneliti pengaruh penggunaan lexicon dan perubahan morfologi kata dalam penentuan tagset yang tepat untuk suatu kata. Aturan dengan pendekatan morfologi kata seperti awalan, akhiran, dan sisipan biasa disebut sebagai lexical rule. Penelitian ini menerapkan lexical rule hasil learner dengan menggunakan algoritma Brill Tagger. Bahasa Madura adalah bahasa daerah yang digunakan di Pulau Madura dan beberapa pulau lainnya di Jawa Timur. Objek penelitian ini menggunakan Bahasa Madura yang memiliki banyak sekali variasi afiksasi dibandingkan dengan Bahasa Indonesia. Pada penelitian ini, lexicon selain digunakan untuk pencarian kata dasar Bahasa Madura juga digunakan sebagai salah satu tahap pemberian POS Tagging. Hasil ujicoba dengan menggunakan lexicon mencapai akurasi yaitu 86.61% sedangkan jika tidak menggunakan lexicon hanya mencapai akurasi 28.95 %. Dari sini dapat disimpulkan bahwa ternyata lexicon sangat berpengaruh terhadap POS Tagging.

scholarly journals Generation of Cross-Lingual Word Vectors for Low-Resourced Languages Using Deep Learning and Topological Metrics in a Data-Efficient Way

Electronics ◽  
2021 ◽  
Vol 10 (12) ◽  
pp. 1372
Author(s):  
Sanjanasri JP ◽  
Vijay Krishna Menon ◽  
Soman KP ◽  
Rajendran S ◽  
Agnieszka Wolk
Keyword(s):  
Deep Learning ◽  
Language Processing ◽  
Semantic Space ◽  
Semantic Interpretation ◽  
Learning Approaches ◽  
Qualitative Comparison ◽  
Bilingual Dictionary ◽  
Pos Tagging ◽  
Part Of Speech ◽  
Cross Lingual

Linguists have been focused on a qualitative comparison of the semantics from different languages. Evaluation of the semantic interpretation among disparate language pairs like English and Tamil is an even more formidable task than for Slavic languages. The concept of word embedding in Natural Language Processing (NLP) has enabled a felicitous opportunity to quantify linguistic semantics. Multi-lingual tasks can be performed by projecting the word embeddings of one language onto the semantic space of the other. This research presents a suite of data-efficient deep learning approaches to deduce the transfer function from the embedding space of English to that of Tamil, deploying three popular embedding algorithms: Word2Vec, GloVe and FastText. A novel evaluation paradigm was devised for the generation of embeddings to assess their effectiveness, using the original embeddings as ground truths. Transferability across other target languages of the proposed model was assessed via pre-trained Word2Vec embeddings from Hindi and Chinese languages. We empirically prove that with a bilingual dictionary of a thousand words and a corresponding small monolingual target (Tamil) corpus, useful embeddings can be generated by transfer learning from a well-trained source (English) embedding. Furthermore, we demonstrate the usability of generated target embeddings in a few NLP use-case tasks, such as text summarization, part-of-speech (POS) tagging, and bilingual dictionary induction (BDI), bearing in mind that those are not the only possible applications.

Sign in / Sign up

Export Citation Format

Share Document