scholarly journals Attentive Tensor Product Learning

2019 ◽  
Vol 33 ◽  
pp. 1344-1351 ◽  
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.

Part-of-Speech (POS) Tagging Using Deep Learning-Based Approaches on the Designed Khasi POS Corpus

2022 ◽  
Vol 21 (3) ◽  
pp. 1-24
Author(s):  
Sunita Warjri ◽  
Partha Pakray ◽  
Saralin A. Lyngdoh ◽  
Arnab Kumar Maji
Keyword(s):  
Deep Learning ◽  
Natural Language ◽  
Computational Linguistics ◽  
Language Processing ◽  
Research Work ◽  
Pos Tagging ◽  
Part Of Speech ◽  
Corpus Size ◽  
Increase In Accuracy ◽  
Pos Tagger

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.

scholarly journals Deep Learning Based Part-of-Speech Tagging for Malayalam Twitter Data (Special Issue: Deep Learning Techniques for Natural Language Processing)

2019 ◽  
Vol 28 (3) ◽  
pp. 423-435 ◽  
Author(s):  
S. Kumar ◽  
M. Anand Kumar ◽  
K.P. Soman
Keyword(s):  
Deep Learning ◽  
Language Processing ◽  
Short Term Memory ◽  
Sequential Model ◽  
Pos Tagging ◽  
Part Of Speech ◽  
Word Level ◽  
Twitter Data ◽  
Gated Recurrent Units ◽  
Hidden States

Abstract The paper addresses the problem of part-of-speech (POS) tagging for Malayalam tweets. The conversational style of posts/tweets/text in social media data poses a challenge in using general POS tagset for tagging the text. For the current work, a tagset was designed that contains 17 coarse tags and 9915 tweets were tagged manually for experiment and evaluation. The tagged data were evaluated using sequential deep learning methods like recurrent neural network (RNN), gated recurrent units (GRU), long short-term memory (LSTM), and bidirectional LSTM (BLSTM). The training of the model was performed on the tagged tweets, at word level and character level. The experiments were evaluated using measures like precision, recall, f1-measure, and accuracy. During the experiment, it was found that the GRU-based deep learning sequential model at word level gave the highest f1-measure of 0.9254; at character-level, the BLSTM-based deep learning sequential model gave the highest f1-measure of 0.8739. To choose the suitable number of hidden states, we varied it as 4, 16, 32, and 64, and performed training for each. It was observed that the increase in hidden states improved the tagger model. This is an initial work to perform Malayalam Twitter data POS tagging using deep learning sequential models.

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.

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

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.

scholarly journals COVID-19 ChatBot

2021 ◽  
Vol 9 (11) ◽  
pp. 44-49
Author(s):  
Satish Tirumalapudi
Keyword(s):  
Deep Learning ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Short Term Memory ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory ◽  
And Control ◽  
Prediction Problems

Abstract: Chat bots are software applications that help users to communicate with the machine and get the required result, this is where Natural Language Processing (NLP) comes into the picture. Natural language processing is based on deep learning that enables computers to acquire meaning from inputs given by the users. Natural language processing techniques can make possible the use of natural language to express ideas, thus drastically increasing accessibility. NLP engines rely on the elements of intent, utterance, entity, context, and session. Here in this project, we will be using Deep learning techniques which will be trained on the dataset which contains categories, patterns, and responses. Long Short-Term Memory (LSTM) is a Recurrent Neural Network that is capable of learning order dependence in sequence prediction problems. One of the most popular RNN approaches is LSTM to identify and control a dynamic system. We use an RNN to classify the category user’s message belongs to and then will give a response from the list of responses. Keywords: NLP – Natural Language Processing, LSTM – Long Short Term Memory, RNN – Recurrent Neural Networks.

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

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.

scholarly journals Penerapan Convolutional Long Short-Term Memory untuk Klasifikasi Teks Berita Bahasa Indonesia

2021 ◽  
Vol 10 (4) ◽  
pp. 354-361
Author(s):  
Yudi Widhiyasana ◽  
Transmissia Semiawan ◽  
Ilham Gibran Achmad Mudzakir ◽  
Muhammad Randi Noor
Keyword(s):  
Deep Learning ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Short Term Memory ◽  
Learning Rate ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory ◽  
Bahasa Indonesia

Klasifikasi teks saat ini telah menjadi sebuah bidang yang banyak diteliti, khususnya terkait Natural Language Processing (NLP). Terdapat banyak metode yang dapat dimanfaatkan untuk melakukan klasifikasi teks, salah satunya adalah metode deep learning. RNN, CNN, dan LSTM merupakan beberapa metode deep learning yang umum digunakan untuk mengklasifikasikan teks. Makalah ini bertujuan menganalisis penerapan kombinasi dua buah metode deep learning, yaitu CNN dan LSTM (C-LSTM). Kombinasi kedua metode tersebut dimanfaatkan untuk melakukan klasifikasi teks berita bahasa Indonesia. Data yang digunakan adalah teks berita bahasa Indonesia yang dikumpulkan dari portal-portal berita berbahasa Indonesia. Data yang dikumpulkan dikelompokkan menjadi tiga kategori berita berdasarkan lingkupnya, yaitu “Nasional”, “Internasional”, dan “Regional”. Dalam makalah ini dilakukan eksperimen pada tiga buah variabel penelitian, yaitu jumlah dokumen, ukuran batch, dan nilai learning rate dari C-LSTM yang dibangun. Hasil eksperimen menunjukkan bahwa nilai F1-score yang diperoleh dari hasil klasifikasi menggunakan metode C-LSTM adalah sebesar 93,27%. Nilai F1-score yang dihasilkan oleh metode C-LSTM lebih besar dibandingkan dengan CNN, dengan nilai 89,85%, dan LSTM, dengan nilai 90,87%. Dengan demikian, dapat disimpulkan bahwa kombinasi dua metode deep learning, yaitu CNN dan LSTM (C-LSTM),memiliki kinerja yang lebih baik dibandingkan dengan CNN dan LSTM.

Learning Syllables Using Conv-LSTM Model for Swahili Word Representation and Part-of-speech Tagging

2021 ◽  
Vol 20 (4) ◽  
pp. 1-25
Author(s):  
Casper Shikali Shivachi ◽  
Refuoe Mokhosi ◽  
Zhou Shijie ◽  
Liu Qihe
Keyword(s):  
Language Processing ◽  
Short Term Memory ◽  
Language Model ◽  
Word Embeddings ◽  
Short Term ◽  
Term Memory ◽  
Pos Tagging ◽  
Part Of Speech ◽  
Word Representation ◽  
Long Short Term Memory

The need to capture intra-word information in natural language processing (NLP) tasks has inspired research in learning various word representations at word, character, or morpheme levels, but little attention has been given to syllables from a syllabic alphabet. Motivated by the success of compositional models in morphological languages, we present a Convolutional-long short term memory (Conv-LSTM) model for constructing Swahili word representation vectors from syllables. The unified architecture addresses the word agglutination and polysemous nature of Swahili by extracting high-level syllable features using a convolutional neural network (CNN) and then composes quality word embeddings with a long short term memory (LSTM). The word embeddings are then validated using a syllable-aware language model ( 31.267 ) and a part-of-speech (POS) tagging task ( 98.78 ), both yielding very competitive results to the state-of-art models in their respective domains. We further validate the language model using Xhosa and Shona, which are syllabic-based languages. The novelty of the study is in its capability to construct quality word embeddings from syllables using a hybrid model that does not use max-over-pool common in CNN and then the exploitation of these embeddings in POS tagging. Therefore, the study plays a crucial role in the processing of agglutinative and syllabic-based languages by contributing quality word embeddings from syllable embeddings, a robust Conv–LSTM model that learns syllables for not only language modeling and POS tagging, but also for other downstream NLP tasks.

scholarly journals Is Deep-Learning and Natural Language Processing Transcending the Financial Forecasting? Investigation Through Lens of News Analytic Process

2021 ◽  
Author(s):  
Faisal Khalil ◽  
Gordon Pipa
Keyword(s):  
Deep Learning ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Short Term Memory ◽  
High Tech ◽  
Long Term Memory ◽  
Term Memory ◽  
Hourly Data ◽  
Analytic Models

AbstractThis study tries to unravel the stock market prediction puzzle using the textual analytic with the help of natural language processing (NLP) techniques and Deep-learning recurrent model called long short term memory (LSTM). Instead of using count-based traditional sentiment index methods, the study uses its own sum and relevance based sentiment index mechanism. Hourly price data has been used in this research as daily data is too late and minutes data is too early for getting the exclusive effect of sentiments. Normally, hourly data is extremely costly and difficult to manage and analyze. Hourly data has been rarely used in similar kinds of researches. To built sentiment index, text analytic information has been parsed and analyzed, textual information that is relevant to selected stocks has been collected, aggregated, categorized, and refined with NLP and eventually converted scientifically into hourly sentiment index. News analytic sources include mainstream media, print media, social media, news feeds, blogs, investors’ advisory portals, experts’ opinions, brokers updates, web-based information, company’ internal news and public announcements regarding policies and reforms. The results of the study indicate that sentiments significantly influence the direction of stocks, on average after 3–4 h. Top ten companies from High-tech, financial, medical, automobile sectors are selected, and six LSTM models, three for using text-analytic and other without analytic are used. Every model includes 1, 3, and 6 h steps back. For all sectors, a 6-hour steps based model outperforms the other models due to LSTM specialty of keeping long term memory. Collective accuracy of textual analytic models is way higher relative to non-textual analytic models.

Sign in / Sign up

Export Citation Format

Share Document