Improving Part-of-Speech Tagging with Relative Positional Encoding in Transformer Models and Basic Rules

Setswana is an under-resourced Bantu African language that is morphologically rich with the disjunctive writing system. Developing NLP pipeline tools for such a language could be challenging, due to the need to balance the linguistics semantics robustness of the tool with computational parsimony. A Part-of-Speech (POS) tagger is one such NLP tool for assigning lexical categories like noun, verb, pronoun, and so on, to each word in a text corpus. POS tagging is an important task in Natural Language Processing (NLP) applications such as information extraction, Machine Translation, Word prediction, etc. Developing a POS tagger for a morphologically rich language such as Setswana has computational linguistics challenges that could affect the effectiveness of the entire NLP system. This is due to some contextual semantics features of the language, that demand a fine-grained granularity level for the required POS tagset, with the need to balance tool semantic robustness with computational parsimony. In this paper, a context-driven corpus-based model for text segmentation and POS tagging for the language is presented. The tagger is developed using the Apache OpenNLP tool and returns the accuracy of 96.73%.

The Malay language is an Austronesian language spoken in most countries in the South East Asia region that includes Malaysia, Indonesia, Singapore, Brunei and Thailand. Traditional linguistics is well developed for Malay but there are very limited resources and tools that are available or made accessible for computer linguistic analysis of Malay language. Assigning part of speech (POS) to running words in a sentence for Malay language is one of the pipeline processes in Natural Language Processing (NLP) tasks and it is not well investigated. This paper outlines an approach to perform the Part of Speech (POS) tagging for Malay text articles. We apply a simple Rule-based Part of Speech (RPOS) tagger to perform the tagging operation on Malay text articles. POS tagging can be described as a task of performing automatic annotation of syntactic categories for each word in a text document. A rule-based POS tagger generally involves a POS tag dictionary and a set of rules in order to identify the words that are considered parts of speech. In this paper, we propose a framework that applies Malay affixing rules to identify the Malay POS tag and the relation between words in order to select the best POS tag for words that have two or more valid POS tags. The results show that the performance accuracy of the ruled-based POS tagger is higher compared to a statistical POS tagger. This indicates that the proposed RPOS tagger is able to predict any unknown word’s POS at some promising accuracy.

Dependency parsing, which is a fundamental task in Natural Language Processing (NLP), has attracted a lot of interest in recent years. In general, it is a module in an NLP pipeline together with word segmentation and Part-Of-Speech (POS) tagging in real Chinese NLP application. The NLP pipeline, which is a cascade system, will lead to error propagation for the parsing. This paper proposes a global discriminative re-ranking model using non-local features from word segmentation, POS tagging and dependency parsing to re-rank the parse trees produced by an N-best enhanced NLP pipeline. Experimental results indicate that the proposed model can improve the performance of dependency parsing as well as word segmentation and POS tagging in an NLP pipeline.

<title>Abstract</title> The Tenyidie language, a.k.a Angami language, is a Tibeto-Burman Language of Nagaland in the north-eastern part of India. Tenyidie is a low-resource language spoken by the Tenyimia Community and is considered a major language in Nagaland. Tenyidie is a tonal, Subject-Object-Verb, and highly agglutinative language. Among the many Natural Language Processing (NLP) tasks, part-of-speech tagging is one of the primary tasks which is used in building many other NLP tasks, such as dependency parsing, named entity recognition, machine translation, etc. The main aim of this paper is to develop the Part-of-speech (POS) Tagset and Tagger for the Tenyidie Language. To the best of our knowledge, there is no reported work on POS Tagset and POS Tagger for the Tenyidie language. The main contributions of this research are: creation of POS tagset for the Tenyidielanguage, creation of POS annotated dataset (11,540 sentences), and the verification of the proposed POS tagset and annotated dataset using the Machine Learning/Deep Learning techniques such as CRF, BLSTM, etc., including the state-of-the-art model such as BERT.

The advances in deep learning have led to great achievements in many Natural Language Processing (NLP) tasks. With the nature of language, i.e., sequential data, most NLP tasks can be framed into the sequence learning framework, such as text generation. As one of the most important foundations for modern NLP techniques, autoregressive generation models have achieved dominant performance in a great deal of NLP tasks. Therefore, this thesis emphasizes improving the autoregressive generation model for different NLP tasks. While many tasks can naturally fit into the sequence learning framework, some of them, e.g., building discourse parsing tree, require sophisticated designs to fit into neural models. Therefore, this thesis firstly emphasizes a novel unified framework for discourse parsing, which builds a discourse tree in a top-down depth-first manner, and it frames the task as an autoregressive generation task with the goal of each step being the prediction of the node position given a piece of text. The proposed approach is proven effective with extensive empirical experiments. In addition, I extend the above framework by proposing a hierarchical decoder, which leverages the information from parents and siblings of the nodes that are currently processed. The proposed decoder utilizes the nature of the tree structure and further improves the experiment performance on both discourse parsing and dependency parsing tasks. On the other hand, the de facto strategies, i.e., cross entropy loss and teacher forcing, for training the autoregressive generation models have been shown problematic in certain aspects. For example, cross entropy loss, which is one of the widely leveraged training objective functions, often leads to text degeneration in text generation, and teacher forcing suffers from the exposure bias problem, where there exists a mismatch between the training and testing setup. For text degeneration, I introduce a class of diminishing attentions, which enforces the submodularity of the coverage calculated by cross attention in the sequence-to-sequence model. The proposed diminishing attentions achieve notable improvement on several neural text generation tasks, including text summarization, machine translation, and image paragraph generation. Further, I propose a novel training objective, ScaleGrad, to replace cross entropy, which significantly reduces the degeneration problem in different text generation tasks. In fact, ScaleGrad can be extended to problems beyond text degeneration. It provides wide flexibility to inject different inductive biases into the text generation model by directly modifying the gradient information in the output layer. Next, for the exposure bias problem, this thesis introduces a novel type of scheduled sampling based on training accuracy, which requires only minimal hyper-parameter tuning compared to existing scheduled sampling methods. Additionally, a novel imitation loss is proposed to further enforce the model’s generative behavior to match the teacher-forced behavior. Moreover, this thesis demonstrates that reducing exposure bias can improve the robustness of language models against repetition and toxic errors.

Text extraction is an important part of natural language processing (NLP) tasks. Most NLP tasks like text classification, machine translation, text-to-speech, text-based language identification, text summarization, and named-entity recognition involve the use of textual data. Such data is limited for low-resourced languages making it difficult to experiment advanced NLP techniques on these languages. This paper presents a Python-based toolkit for text analysis and text extraction from different types of images, documents, and audio files. The toolkit is built as a library that has functions that can be imported and utilized for text extraction.

Work orders, equipment information, technical records and best practices documents contain within them a wealth of insights related to Equipment Maintenance which can be unlocked with Natural Language Processing tasks like classification, clustering, named entity recognition or part of speech tagging. But obtaining large enough labelled data sets in Equipment Maintenance domain manually is prohibitive and very expensive. This lack of labeled Equipment Maintenance data can be overcome with Large Language Models (LLMs) such as GPT-3, BERT that are pretrained transformer networks, considered state-of-the-art when it comes to Natural Language Processing (NLP) tasks. However, the vocabulary understood by these LLMs are mostly from English Language and need to be fine-tuned to understand industry and organization specific vocabulary and acronyms. This paper explores the potential of a domain specific LLM model for oil and gas industries. Data that are of good quality and that provide a comprehensive overview of industry are collected. This corpus of text contains documents like work orders, equipment data and technical documents. A custom tokenizer is trained on this data to identify domain specific terminology. A comparative study is done with other off-the-shelf tokenizers: BERT and RoBERTa, to compare the effectiveness of the tokenization. With millions of work orders and equipment documents, training pipelines had to parallelized so that training can occur on multiple GPUs. A comprehensive study of multiple training methods is done in this paper. Model and tokenizer developed were packaged and archived to be consumed in machine learning pipelines to specific use-cases across the organization. For an organization adopting digital transformation, the availability of an organization specific LLM is an enabler to extract insights from millions of documents containing free text. The applicability of such models spans across multiple disciplines like Maintenance, Reliability, Safety etc. and streamlines the development of highly accurate and robust text analytics.

Automatic Parts of Speech(POS) tagging is one of the most fundamental tasks for a language in Natural Language Processing(NLP), which acts as a feature for solving advanced NLP tasks. Named Entity Recognition(NER) is another essential task of NLP for information retrieval. Researchers could not find up to the mark solution yet on these two tasks for Bangla language compared to other languages, for instance, English, Ger-man. Moreover, many solutions heavily depend on handcrafted features that require strong linguistic expertise. As these two sequence labeling tasks are similar, In this work, two different datasets of POS tagging and NER were prepared, and different deep neural network approaches studied for solving these two tasks separately. All of the approaches were end to end and did not need any handcrafted feature like word suffixes or affixes, gazetteers, dictionary. This study came up with an end to end solution using deep neural network-based model consisting of Bi-directional Long short-term memory(BLSTM), Convolutional Neural Network(CNN) and Conditional Random Field(CRF). The proposed model trained on respected datasets achieved an accuracy of 93.86% on POS tagging and a strict f1 score of 0.6285 on NER on prepared datasets, respectively.

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.

POS tagging is a basic Natural Language Processing (NLP) task that tags the words in an input text according to its grammatical values. Although POS Tagging is a fundamental application for very resourced languages, such as Limbu, is still unknown due to only few tagged datasets and linguistic resources. This research project uses deep learning techniques, transfer learning, and the BiLSTM-CRF model to develop an accurate POS-tagging system for the Limbu language. Using annotated and unannotated language data, we progress in achieving a small yet informative dataset of Limbu text. Skilled multilingual tutoring was modified to enhance success on low-resource language tests. The model as propose attains 90% accuracy, which is very much better than traditional rule-based and machine learning methods for Limbu POS tagging. The results indicate that deep learning methods can address linguistic issues facing low-resource languages even with limited data. In turn, this study provides a cornerstone for follow up NLP-based applications of Limbu and similar low-resource languages, demonstrating how deep learning can fill the gap where data is scarce.

Towards a Novel Weakly Supervised Joint Approach of Named Entity Recognition and Normalization for Noisy Text

Question answering over tables is a very popular semantic parsing task in natural language processing (NLP). However, few existing methods focus on table images, even though there are usually large-scale unstructured tables in practice (e.g., table images). Table parsing from images is nontrivial since it is closely related to not only NLP but also computer vision (CV) to parse the tabular structure from an image. In this demo, we present a question answering system for unstructured table images. The proposed system mainly consists of 1) a table recognizer to recognize the tabular structure from an image and 2) a table parser to generate the answer to a natural language question over the table. In addition, to train the model, we further provide table images and structure annotations for two widely used semantic parsing datasets. Specifically, the test set is used for this demo, from where the users can either choose from default questions or enter a new custom question.

Linguistic resources such as part-of-speech (POS) tags have been extensively used in statistical machine translation (SMT) frameworks and have yielded better performances. However, usage of such linguistic annotations in neural machine translation (NMT) systems has been left under-explored. In this work, we show that multi-task learning is a successful and a easy approach to introduce an additional knowledge into an end-to-end neural attentional model. By jointly training several natural language processing (NLP) tasks in one system, we are able to leverage common information and improve the performance of the individual task. We analyze the impact of three design decisions in multi-task learning: the tasks used in training, the training schedule, and the degree of parameter sharing across the tasks, which is defined by the network architecture. The experiments are conducted for an German to English translation task. As additional linguistic resources, we exploit POS information and named-entities (NE). Experiments show that the translation quality can be improved by up to 1.5 BLEU points under the low-resource condition. The performance of the POS tagger is also improved using the multi-task learning scheme.

Long Short-Term Memory (LSTM) networks are unique to exercise data in its memory cell with long-term memory as Natural Language Processing (NLP) tasks have inklings of intensive time and computational power due to their complex structures like magnitude language model Transformer required to pre-train and learn billions of data performing different NLP tasks. In this paper, a dynamic chaotic model is proposed for the objective of transforming neurons states in network with neural dynamic characteristics by restructuring LSTM as Chaotic Neural Oscillatory-Long-Short Term Memory (CNO-LSTM), where neurons in LSTM memory cells are weighed in substitutes by oscillatory neurons to speed up computational training of language model and improve text classification accuracy for real-world applications. From the implementation perspective, five popular datasets of general text classification including binary, multi classification and multi-label classification are used to compare with mainstream baseline models on NLP tasks. Results showed that the performance of CNO-LSTM, a simplified model structure and oscillatory neurons state in exercising different types of text classification tasks are above baseline models in terms of evaluation index such as Accuracy, Precision, Recall and F1. The main contributions are time reduction and improved accuracy. It achieved approximately 46.76% of the highest reduction training time and 2.55% accuracy compared with vanilla LSTM model. Further, it achieved approximately 35.86% in time reduction compared with attention model without oscillatory indicating that the model restructure has reduced GPU dependency to improve training accuracy.

Recently, transformer-based models have reshaped the landscape of Natural Language Processing (NLP), particularly in the domain of Machine Translation (MT). this study explores three revolutionary transformer models: Bidirectional Encoder Representations from Transformers (BERT), Generative Pretrained Transformer (GPT), and Text-to-Text Transfer Transformer (T5). The study delves into their architecture, capabilities, and applications in the context of translation technology. The study begins by discussing the evolution of machine translation from rule-based to statistical machine translation and finally to transformer models. The models have distinct architectures and purposes which pushed the limits of MT and have been instrumental in revolutionising the field. The study found significant contributions of the models in the advancement of NLP tasks including translation technology. Using comparative approach, the study further elaborates on each model’s design and utility. BERT is strong in excelling in tasks requiring a deep understanding of the context. GPT is excellent for tasks such as text generation, translation and creative writing. While the strengths of T5 is text-to-text framework by simplifying the taskspecific architectures, making it easy to perform different NLP tasks. Recognising these models’ unique features allows translators to select the best one for particular translation tasks and adjust them for better accuracy, fluency, and cultural relevance in translations. The study concludes that the models bridge language barriers, improve cross-cultural communication and pave way for more accurate and natural translations in the future. The study also points out that language processing models are continually evolving but understanding BERT, GPT, and T5’s specific features is key for ongoing development in translation technology.