Research on plug-and-play correlation enhancement modules in deep multi-label learning.

Like any other science, research in natural language processing (NLP) depends on the ability to draw correct conclusions from experiments. A key tool for this is statistical significance testing: We use it to judge whether a result provides meaningful, generalizable findings or should be taken with a pinch of salt. When comparing new methods against others, performance metrics often differ by only small amounts, so researchers turn to significance tests to show that improved models are genuinely better. Unfortunately, this reasoning often fails because we choose inappropriate significance tests or carry them out incorrectly, making their outcomes meaningless. Or, the test we use may fail to indicate a significant result when a more appropriate test would find one. NLP researchers must avoid these pitfalls to ensure that their evaluations are sound and ultimately avoid wasting time and money through incorrect conclusions.This book guides NLP researchers through the whole process of significance testing, making it easy to select the right kind of test by matching canonical NLP tasks to specific significance testing procedures. As well as being a handbook for researchers, the book provides theoretical background on significance testing, includes new methods that solve problems with significance tests in the world of deep learning and multidataset benchmarks, and describes the open research problems of significance testing for NLP.The book focuses on the task of comparing one algorithm with another. At the core of this is the p-value, the probability that a difference at least as extreme as the one we observed could occur by chance. If the p-value falls below a predetermined threshold, the result is declared significant. Leaving aside the fundamental limitation of turning the validity of results into a binary question with an arbitrary threshold, to be a valid statistical significance test, the p-value must be computed in the right way. The book describes the two crucial properties of an appropriate significance test: The test must be both valid and powerful. Validity refers to the avoidance of type 1 errors, in which the result is incorrectly declared significant. Common mistakes that lead to type 1 errors include deploying tests that make incorrect assumptions, such as independence between data points. The power of a test refers to its ability to detect a significant result and therefore to avoid type 2 errors. Here, knowledge of the data and experiment must be used to choose a test that makes the correct assumptions. There is a trade-off between validity and power, but for the most common NLP tasks (language modeling, sequence labeling, translation, etc.), there are clear choices of tests that provide a good balance.Beginning with a detailed background on significance testing, the book then shows the reader how to carry out tests for specific NLP tasks. There is a mix of styles, with the first four chapters providing reference material that will be extremely useful to both new and experienced researchers. Here, it is easy to find the material related to a given NLP task. The next two chapters discuss more recent research into the application of significance tests to deep neural networks and for testing across multiple datasets. Alongside open research questions, these later chapters provide clear guidelines on how to apply the proposed methods. It is this mix of background material and reference guidelines that I believe makes this book so compelling and nicely self-contained.The introduction in Chapter 1 motivates the need for a comprehensive textbook and outlines challenges that the later chapters address more deeply. The theoretical background material begins in Chapter 2, which introduces core concepts, including hypothesis testing, type 1 and type 2 errors, validity and power, and p-values. The reader does not need to have any prior knowledge of statistical significance tests to follow this part. However, experienced readers could still benefit from reading this chapter, as concepts such as p-values are widely misunderstood and misused (Amrhein, Greenland, and McShane 2019).The significance tests themselves are introduced in Chapter 3, categorized into parametric and nonparametric tests. The chapter begins with the intuitively simple paired z-test, then builds up to more commonly-applied techniques, showing the connections and assumptions that each test makes. Step-by-step algorithms help the reader to implement each test. Although the chapter does cite uses of tests in NLP research, the main purpose is to present the theory behind each test and point out their differences.Chapter 4 provides perhaps the most handy part of the book for reference: a correspondence between common NLP tasks and statistical tests. Each task is discussed in terms of the evaluation metrics used, then a decision tree is introduced to guide the reader toward a choice between a parametric test, bootstrap or randomization test, or sampling-free nonparametric test. Section 4.3 then links each NLP evaluation measure to a specific significance test, presenting a large table that helps readers identify which test they need for a specific task. Particular considerations for each task are also pointed out to provide more detail about the appropriate options. The final part of this chapter describes the issue of p-hacking, in which dataset sizes are increased until a significance threshold is reached without consideration for biases in the data (discussed, for example, in Hofmann [2015]). The chapter proposes a simple solution to ensure robust significance testing with large datasets.Where Chapter 4 presents well-established methods, Chapter 5 introduces the current research question of how best to apply statistical significance testing to deep learning. Non-convex loss functions, stochastic optimization, random initialization, and a multitude of hyperparameters limit the conclusions we can draw from a single test run of a deep neural network (DNN). This chapter, which is based on the authors’ ACL paper (Dror, Shlomov, and Reichart 2019), explains how the comparison process can be overhauled to provide more meaningful evaluations. Beginning by explaining the difficulties of evaluating DNNs, the chapter then introduces criteria for a comparison framework, then discusses the limitations of current methods. Reimers and Gurevych (2018) have previously tackled this problem, but their approach has limited power and does not provide a confidence score. Other works, such as Clark et al. (2011), compare DNNs using a collection of statistics, such as the mean or standard deviation of performance across runs. This book shows how such an approach violates the assumptions of the significance tests. The authors propose almost stochastic dominance as the basis for a better alternative. The chapter explains how to use the proposed method, evaluates it in an empirical case study, and finally analyzes the errors made by each testing approach.Large NLP models are often tested across a range of datasets, which presents another problem for standard significance testing. Chapter 6 discusses the challenges of assessing two questions: (1) On how many datasets does algorithm A outperform algorithm B? (2) On which datasets does A outperform B? Applying standard significance tests individually to each dataset and counting the number of significant results is likely to overestimate the total number of significant results, as this chapter explains. The authors then present a new framework for replicability analysis, based on partial conjunction testing, and discuss two variants (Bonferroni and Fisher) for when the datasets are independent or dependent. They introduce a method based on Benjamini and Heller (2008) to count the number of datasets where one method outperforms another, then show how to use the Holm procedure (Holm 1979) to identify which datasets these are. Chapter 6 provides a lot of detailed background on the proposed replicability analysis framework, and the later sections again link the process to specific NLP case studies, and step-by-step summaries help the reader to apply the methodology. Extensive empirical results illustrate the very substantial differences in outcomes between the proposed approach and standard procedures.The final two chapters present open problems and conclude, showing that the topic has many interesting research questions of its own, such as problems when performing cross-validation, and the limited statistical power of replicability analysis.Overall, I highly recommend this book to a wide range of NLP researchers, from new students to seasoned experts who wish to ensure that they compare methods effectively. The book is excellent as both an introduction to the topic of significance testing and as a reference to use when evaluating your results. For anyone with further interest in the topic, it also points the way to future work. If one could level any criticism at this book at all, it is that it does not deeply discuss the basic flaws of significance testing or what the alternatives might be. For now, though, significance testing is an integral part of NLP research and this book provides a great resource for researchers who wish to perform it correctly and painlessly.

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.

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.

Annotation quality and quantity positively affect the learning performance of sequence labeling, a vital task in Natural Language Processing. Hiring domain experts to annotate a corpus is very costly in terms of money and time. Crowdsourcing platforms, such as Amazon Mechanical Turk (AMT), have been deployed to assist in this purpose. However, the annotations collected this way are prone to human errors due to the lack of expertise of the crowd workers. Existing literature in annotation aggregation assumes that annotations are independent and thus faces challenges when handling the sequential label aggregation tasks with complex dependencies. To conquer the challenges, we propose an optimization-based method that infers the ground truth labels using annotations provided by workers for sequential labeling tasks. The proposed Aggregation method for Sequential Labels from Crowds (AggSLC) jointly considers the characteristics of sequential labeling tasks, workers’ reliabilities, and advanced machine learning techniques. Theoretical analysis on the algorithm’s convergence further demonstrates that the proposed AggSLC halts after a finite number of iterations. We evaluate AggSLC on different crowdsourced datasets for Named Entity Recognition (NER) tasks and Information Extraction tasks in biomedical (PICO), as well as a simulated dataset. Our results show that the proposed method outperforms the state-of-the-art aggregation methods. To achieve insights into the framework, we study the effectiveness of AggSLC’s components through ablation studies.

Sequence labeling is a basic task in natural language processing, which is of great help to processing text information. Conventional sequence labeling approaches heavily rely on hand-crafted or language-specific features, which requires a lot of time. Therefore, most of the existing methods are based on the BiLSTM-CRF model, but how to use a neural network to extract useful information for each unit or segment in the input sequence becomes the main factor limiting the efficiency. Several BiLSTM-CRF based models for sequence labeling have been presented, but the major limitation is how to use neural networks for extracting useful representations for each unit or segment in the input sequence. In response to this problem, this paper proposes a sequence labeling algorithm based on hierarchical features and attention mechanism, which uses a hierarchical structure to integrate character-level and word-level information, and applies different attention mechanisms to these two layers of information. According to the structural characteristics of different levels, excavate more potential information. Finally, the previously captured and guided features are used for sequence tag prediction using CRF. Finally, the proposed model is subjected to comparative experiments and the results obtained are analyzed.

Position-aware self-attention based neural sequence labeling

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.

In this paper, we present the preliminary results on the analysis of deep learning terms used for natural language processing (NLP) tasks. We propose a statistical analysis of papers published from 2012 to 2015 in the main ACL conferences. Our aim is investigating which DL term, and consequently which DL method, is mostly used for each specific NLP task, since its introduction in the field. In order to do this, our first contribution is the development of two terminological lists, referring respectively to DL methods for text analysis and NLP tasks. The list of deep learning terms contains 41 terms and acronyms, as well as a NLP term list contains 145 terms and acronyms. From our corpus, the frequencies of various terms have been extracted with respect to the ACL conference and the publication year. After the preliminary data analysis, we decided to restrict the extraction process to abstract texts. We applied multivariate techniques called correspondence analysis in order to visualize and evaluate the joint behavior of our variables.

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

Many tasks in natural language processing like offensive, toxic, or emotional text classification are subjective by nature. Humans tend to perceive textual content in their own individual way. Existing methods commonly rely on the agreed output values, the same for all consumers. Here, we propose personalized solutions to subjective tasks. Our four new deep learning models take into account not only the content but also the specificity of a given human. The models represent different approaches to learning the representation and processing data about text readers. The experiments were carried out on four datasets: Wikipedia discussion texts labelled with attack, aggression, and toxicity, as well as opinions annotated with ten numerical emotional categories. Emotional data was considered as multivariate regression (multitask), whereas Wikipedia data as independent classifications. All our models based on human biases and their representations significantly improve the prediction quality in subjective tasks evaluated from the individual’s perspective.

Text-based Question Answering (QA) is an essential task in natural language processing that aims to provide relevant and accurate answers to users’ queries. Traditional approaches to QA relied on rule-based systems and hand-crafted features. However, recent advancements in information retrieval and deep learning have shown promising results in improving the performance of QA systems. The combination of IR and deep learning techniques has led to significant improvements in QA performance. Hybrid models, such as the bi-encoder and tri-encoder architectures, have been proposed to leverage the strengths of both IR and deep learning models. Additionally, pre-training techniques, such as BERT and RoBERTa, have been shown to improve the performance of QA systems by providing pre-trained contextualized word embeddings. This study provides a brief overview of the QA system and its different domains and subdomains. This study also provides review of different proposed models and different datasets available for the task and evaluate their performance using some performance metrics. A comparison between various techniques are employed using the obtained result.

Deep learning models have been the state-of-the-art for a variety of challenging tasks in natural language processing, but to achieve good results they often require big labeled datasets. Deep active learning algorithms were designed to reduce the annotation cost for training such models. Current deep active learning algorithms, however, aim at training a good deep learning model with as little labeled data as possible, and as such are not useful in scenarios where the full dataset must be labeled. As a solution to this problem, this work investigates deep active-self learning algorithms that employ self-labeling using the trained model to help alleviate the cost of annotating full datasets for named entity recognition tasks. The experiments performed indicate that the proposed deep active-self learning algorithm is capable of reducing manual annotation costs for labeling the complete dataset for named entity recognition with less than 2\% of the self labeled tokens being mislabeled. We also investigate an early stopping technique that doesn't rely on a validation set, which effectively reduces even further the annotation costs of the proposed active-self learning algorithm in real world scenarios.

In this study, we explore the potential of machine learning (ML) models after different text representation methods on the balanced IMDB dataset, which is widely regarded as a gold standard in sentiment analysis, one of the Natural Language processing (NLP) tasks. On the open source IMDB movie reviews dataset, we first undertake data cleaning and text representation with data preprocessing steps. Then, we apply sentiment classification using different ML models. In order to evaluate the models, we used precision (P), recall (R), F1-score (F1), and area under curve (AUC), as well as receiver operating characteristic (ROC). It is worth noting that text feature extraction with Bidirectional Encoder Representations from Transformers (BERT) provided the highest performance in all models, with the SVM model offering particularly promising results. In this model, we observed the following results: ACC 0.9033, F1 0.9308, R 0.9015, R 0.9015, P 0.9072, AUC 0.9638, and ROC 0.96. These findings suggest that NLP techniques and, in particular, machine learning models that employ BERT may offer high levels of accuracy and reliability in text classification problems. It would be beneficial for future studies to validate these findings using BERT on different NLP tasks. This would help to evaluate the effectiveness and applicability of the models in practice.

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.

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