{"id":24,"date":"2023-12-30T04:53:52","date_gmt":"2023-12-30T04:53:52","guid":{"rendered":"https:\/\/shawpence.com\/?p=24"},"modified":"2024-01-02T01:01:42","modified_gmt":"2024-01-02T01:01:42","slug":"a-retrospective-on-chatbots-history-technologies-and-applications","status":"publish","type":"post","link":"https:\/\/shawpence.com\/?p=24","title":{"rendered":"A Retrospective on Chatbots: History, Technologies and Applications"},"content":{"rendered":"\n<pre class=\"wp-block-verse\"><em>This is one of my course reports at first sumbitted in April, 2023 and published here in Dec, 2023.<\/em><\/pre>\n\n\n\n<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_68_1 counter-hierarchy ez-toc-counter ez-toc-grey ez-toc-container-direction\">\n<div class=\"ez-toc-title-container\">\n<p class=\"ez-toc-title \" >Table of Contents<\/p>\n<span class=\"ez-toc-title-toggle\"><a href=\"#\" class=\"ez-toc-pull-right ez-toc-btn ez-toc-btn-xs ez-toc-btn-default ez-toc-toggle\" aria-label=\"Toggle Table of Content\"><span class=\"ez-toc-js-icon-con\"><span class=\"\"><span class=\"eztoc-hide\" style=\"display:none;\">Toggle<\/span><span class=\"ez-toc-icon-toggle-span\"><svg style=\"fill: #999;color:#999\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" class=\"list-377408\" width=\"20px\" height=\"20px\" viewBox=\"0 0 24 24\" fill=\"none\"><path d=\"M6 6H4v2h2V6zm14 0H8v2h12V6zM4 11h2v2H4v-2zm16 0H8v2h12v-2zM4 16h2v2H4v-2zm16 0H8v2h12v-2z\" fill=\"currentColor\"><\/path><\/svg><svg style=\"fill: #999;color:#999\" class=\"arrow-unsorted-368013\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"10px\" height=\"10px\" viewBox=\"0 0 24 24\" version=\"1.2\" baseProfile=\"tiny\"><path d=\"M18.2 9.3l-6.2-6.3-6.2 6.3c-.2.2-.3.4-.3.7s.1.5.3.7c.2.2.4.3.7.3h11c.3 0 .5-.1.7-.3.2-.2.3-.5.3-.7s-.1-.5-.3-.7zM5.8 14.7l6.2 6.3 6.2-6.3c.2-.2.3-.5.3-.7s-.1-.5-.3-.7c-.2-.2-.4-.3-.7-.3h-11c-.3 0-.5.1-.7.3-.2.2-.3.5-.3.7s.1.5.3.7z\"\/><\/svg><\/span><\/span><\/span><\/a><\/span><\/div>\n<nav><ul class='ez-toc-list ez-toc-list-level-1 ' ><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/shawpence.com\/?p=24\/#History\" title=\"History\">History<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/shawpence.com\/?p=24\/#Technology\" title=\"Technology\">Technology<\/a><ul class='ez-toc-list-level-3' ><li class='ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"https:\/\/shawpence.com\/?p=24\/#Pattern_matching_and_rule-based_approach\" title=\"Pattern matching and rule-based approach\">Pattern matching and rule-based approach<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"https:\/\/shawpence.com\/?p=24\/#Retrieval-based_approach\" title=\"Retrieval-based approach\">Retrieval-based approach<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"https:\/\/shawpence.com\/?p=24\/#Generation-based_approach\" title=\"Generation-based approach\">Generation-based approach<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-6\" href=\"https:\/\/shawpence.com\/?p=24\/#Slot_filling_approach_for_intent-oriented_chatbots\" title=\"Slot filling approach for intent-oriented chatbots\">Slot filling approach for intent-oriented chatbots<\/a><\/li><\/ul><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-7\" href=\"https:\/\/shawpence.com\/?p=24\/#Applications\" title=\"Applications\">Applications<\/a><ul class='ez-toc-list-level-3' ><li class='ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-8\" href=\"https:\/\/shawpence.com\/?p=24\/#FAQ_chatbots_and_knowledge_retrieval_chatbots\" title=\"FAQ chatbots and knowledge retrieval chatbots\">FAQ chatbots and knowledge retrieval chatbots<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-9\" href=\"https:\/\/shawpence.com\/?p=24\/#Tasks-oriented_or_intent-based_chatbots\" title=\"Tasks-oriented or intent-based chatbots\">Tasks-oriented or intent-based chatbots<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-10\" href=\"https:\/\/shawpence.com\/?p=24\/#Free_chat_chatbots\" title=\"Free chat chatbots\">Free chat chatbots<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-11\" href=\"https:\/\/shawpence.com\/?p=24\/#Future_What_is_possible_and_what_is_impossible\" title=\"Future: What is possible and what is impossible?\">Future: What is possible and what is impossible?<\/a><\/li><\/ul><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-12\" href=\"https:\/\/shawpence.com\/?p=24\/#Reference\" title=\"Reference\">Reference<\/a><\/li><\/ul><\/nav><\/div>\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"History\"><\/span>History<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>When ChatGPT has been introduced months ago, the current dynamics of chatbots advances Alan Turing (1950)\u2019s ideal, where he proposed the question \u201cCan machines think\u201d. This retrospective will look back at the history of chatbots, from the early days of chatbots to the present day, highlighting the past milestones that have shaped today\u2019s more powerful chatbots.<\/p>\n\n\n\n<p>The first chatbot is called <strong>ELIZA<\/strong> (Weizenbaum, 1966) as a response to the Turing test (Shum et al., 2018). ELIZA was invented by Weizenbaum in the Artificial Intelligence Laboratory of MIT in 1964 (Skrebeca et al., 2021). This machine, named DOCTOR at that time, worked as a Rogerian psychotherapist to answer emotions-related questions. Because Weizenbaum only used a rule-based approach and limited patterns to generate answers in ELIZA, it is evident that these utterances deviate from humans\u2019 words, especially from professional therapists.<\/p>\n\n\n\n<p><strong>PARRY<\/strong> is another robot in the early years created by Kenneth Colby, a Stanford psychiatrist as well as computer scientist, in 1972 (Colby, 1976). As a part of psychology research, this work assumes the role of a simulated paranoid schizophrenic patient rather than a doctor as ELIZA, equipping with effective emotion variables like anger, fear, and mistrust. Compared with ELIZA, beyond the similar pattern and rule-based approach shared by both of them, PARRY is more well-engineered with a more advanced structure (Thorat &amp; Jadhav, 2020).<\/p>\n\n\n\n<p><strong>Ractor<\/strong> is another notable chatbot (Chamberlain, 1984). It was developed by William Chamberlain and Thomas Etter in 1983 for Amiga, Apple II, Macintosh platforms (Zem\u010d\u00edk, 2019). The main function of Ractor is to create proses like the following one:<\/p>\n\n\n\n<!--more-->\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p>\u201c<em>A crow is a bird, an eagle is a bird, a dove is a bird. They all fly in the night and in the day. They fly when the sky is red and when the heaven is blue. They fly through the atmosphere. We cannot fly. We are not like a crow or an eagle or a dove. We are not birds. But we can dream about them. You can.<\/em>\u201d <\/p>\n<cite>(Chamberlain, 1984)<\/cite><\/blockquote>\n\n\n\n<p>Some literature see it as a chatbots (Skrebeca et al., 2021; Zem\u010d\u00edk, 2019), it mainly works, however, in generating texts, rather engaging in a conversation. Given that text generating is a crucial part of todays\u2019 chatbots, Ractor is considered as a pioneer in this retrospective.<\/p>\n\n\n\n<p><strong>A.L.I.C.E <\/strong>(Artificial Linguistic Internet Computer Entity), created in 1995, is another influential chatbots in the whole history of the development of chatbots because of numerous innovations in this work (Adamopoulou &amp; Moussiades, 2020). It is a practice adopted AIML (Artificial Intelligence Markup Language, Figure 1), an XML-based markup language (Thorat &amp; Jadhav, 2020) facilitating pattern recognition in the development of AI agents (Bruno Marietto et al., 2013). Inspired by ELIZA, ALICE extends the development of pattern machine approch and the knowledge to 40, 000 categories (only about 200 for ELIZA) (Wallace, 2009). However, ALICE did not have enough intelligent to generate human-like answers with emotions (Adamopoulou &amp; Moussiades, 2020).<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"834\" height=\"369\" src=\"https:\/\/shawpence.com\/wp-content\/uploads\/2023\/12\/an_example_of_aiml.png\" alt=\"An Example Of Aiml\" class=\"wp-image-41\" srcset=\"https:\/\/shawpence.com\/wp-content\/uploads\/2023\/12\/an_example_of_aiml.png 834w, https:\/\/shawpence.com\/wp-content\/uploads\/2023\/12\/an_example_of_aiml-300x133.png 300w, https:\/\/shawpence.com\/wp-content\/uploads\/2023\/12\/an_example_of_aiml-768x340.png 768w\" sizes=\"auto, (max-width: 834px) 100vw, 834px\" \/><\/figure>\n\n\n\n<p><a><\/a><a>Figure <\/a>1 An example of AIML<\/p>\n\n\n\n<p>Chatbots discussed above are technological explorations and pioneers, where most are only laboratory products. When it comes to 2000s later, commercially used or mass-oriented chatbots started to sprout with the help of the Internet and big companies\u2019 involvement. <strong>SmarterChild<\/strong>, developed in 2001, was available on messaging apps like AOL and MSN (Molnar &amp; Szuts, 2018). As a commercial product, you could even some advertisements and sponsors\u2019 information within the chats. Microsoft also attempts to launch a Chatbot, and then named as <strong>XiaoIce<\/strong> in 2014 (Shum et al., 2018). This is only the first attempt for this big company. In recent years, almost all tech giants, like Apple Siri, IBM Watson, Google Now, Microsoft Cortana, tried to build their chatbot products. Although chatbots nowadays seems so profitable, customers are reluctant to engage with them (Van Pinxteren et al., 2020), until the ChatGPT came into being in 2022 with peoples\u2019 astonishing and welcoming.<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"867\" height=\"599\" src=\"https:\/\/shawpence.com\/wp-content\/uploads\/2023\/12\/SmartChild_user_interface.png\" alt=\"Smartchild User Interface\" class=\"wp-image-42\" srcset=\"https:\/\/shawpence.com\/wp-content\/uploads\/2023\/12\/SmartChild_user_interface.png 867w, https:\/\/shawpence.com\/wp-content\/uploads\/2023\/12\/SmartChild_user_interface-300x207.png 300w, https:\/\/shawpence.com\/wp-content\/uploads\/2023\/12\/SmartChild_user_interface-768x531.png 768w\" sizes=\"auto, (max-width: 867px) 100vw, 867px\" \/><\/figure>\n\n\n\n<p>Figure 2 SmartChild user interface<\/p>\n\n\n\n<p>Since the first electronic computer was introduced, it only took 19 years to bring the first chatbot ELIZA to the reality. Computer scientists\u2019 determined endeavor and enthusiasm to engineer a more powerful chatbot from that time onwards finally becomes more realistic than ever when the ChatGPT was launched by OpenAI and keeping evolved.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Technology\"><\/span>Technology<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<h3 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Pattern_matching_and_rule-based_approach\"><\/span>Pattern matching and rule-based approach<span class=\"ez-toc-section-end\"><\/span><\/h3>\n\n\n\n<p>Pattern matching is a work to recognize whether a string is similar to a pattern in which a text sequence defines a string set by given fixed and free text positions.This technology is widely used in Natural Language Processing especially at early ages before Chomsky\u2019s linguistic knowledge impacted computing linguistics and mathematical grammar models (e.g., CNF, CKY parsing, POS) were proposed. Regular Expression is the most popular and simple pattern matching method in nowadays. Both ELIZA and ALICE employed pattern matching in their system.<\/p>\n\n\n\n<p>ELIZA is based on 200 patterns and rules. The rules are comprises decomposition template (Weizenbaum, 1966), the pattern for parsing users\u2019 input, and reassembly rule, the pattern to generate output sentence. Both of these two patterns use numbers to mark the functions for specific words. The decomposition template is like \u201c0 YOU 0 ME\u201d where the digit 0 means a place for indefinite words. The reassembly rule is defined as \u201cWHAT MAKES YOU THINK I 3 YOU\u201d where the digit 3 represents the third word in the input sentence. By embedding the third word in the reassembly rule, a response is generated. When the sentence is long and complicated, it might fires multiple rules. When there is no pattern matched, ELIZA will respond a non-commital response like \u201cI SEE\u201d, \u201cPLEASE GO ON\u201d, \u201cTHAT\u2019S VERY INTERESTING.\u201d<\/p>\n\n\n\n<p>While ELIZA\u2019s architecture is easy and looks like it executes copy and paste only, as a chatbot at the early age, it even did not adopt the word \u201cpattern\u201d, it is an impactful work for the whole chatbot development. After about three decades, A.L.I.C.E. adopted a more complicated pattern matching.<\/p>\n\n\n\n<p>A.L.I.C.E. is an implementation of Artificial Intelligence Markup Language, which is a specified format of XML file to define patterns. Enlightened by ELIZA, AIML shares some principles in defining patterns, such as digits marked blank position for tentative sentence parts. In AIML, basically, all the patterns are stored in a tree structure called Graphmaster (Wallace, 2009) for pattern matching. The structure of Graphmaster is shown as Figure 3.<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"503\" height=\"199\" src=\"https:\/\/shawpence.com\/wp-content\/uploads\/2023\/12\/graphmaster.png\" alt=\"Graphmaster\" class=\"wp-image-43\" srcset=\"https:\/\/shawpence.com\/wp-content\/uploads\/2023\/12\/graphmaster.png 503w, https:\/\/shawpence.com\/wp-content\/uploads\/2023\/12\/graphmaster-300x119.png 300w\" sizes=\"auto, (max-width: 503px) 100vw, 503px\" \/><\/figure>\n\n\n\n<p><a>Figure <\/a>3 Graphmaster (Wallace, 2014)<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Retrieval-based_approach\"><\/span>Retrieval-based approach<span class=\"ez-toc-section-end\"><\/span><\/h3>\n\n\n\n<p>The retrieval-based approach regards users\u2019 input as query and find the most similar response in a corpus. A tradition strategy is to use cosine similarity to calculate as the equation below.<\/p>\n\n\n\n\\(\\) \\begin{aligned}\nresponse(q, C)=argmax \\frac{q \\cdot r}{|q||r|} \\quad r \\in C\n\\end{aligned}\n\n\n\n<p>Where q and r represent tf-idf for query and candidate response respectively. Using encoder, like BERT (Devlin et al., 2019), to calculate the similarity is a more advanced approach. This method requires transform users\u2019 input and candidate response to embeddings. Via input these embeddings into the BERT, we will get two representations. Furtherly, we can calculate the similarity by dot product on these two representations (Jurafsky &amp; Martin, 2023).<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Generation-based_approach\"><\/span>Generation-based approach<span class=\"ez-toc-section-end\"><\/span><\/h3>\n\n\n\n<p>Sequence to sequence model is a commonly used text generation model. This kind of models regards text as a sequential data, and then input these data into a sequential data-oriented neural network (RNN, GRU, LSTM). Generation model always trained with paired database to simulate human conversations. Google harnesses the seq2seq model in their translation product, which significantly improved the performance compared with all the other published methods (Sutskever et al., 2014). Microsoft Xiaoice is a foremost user of seq2seq model in chatbot system. The Neural Response Generator of Xiaoice is based on a GRU-RNN model where the model can linearly combine the users\u2019 input query, the features of chatbot itself (Xiaoice) and users\u2019 features into a vector representation (Zhou et al., 2020, figure 4) to generate text in the decoder.<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"951\" height=\"559\" src=\"https:\/\/shawpence.com\/wp-content\/uploads\/2023\/12\/neural.png\" alt=\"Neural\" class=\"wp-image-44\" srcset=\"https:\/\/shawpence.com\/wp-content\/uploads\/2023\/12\/neural.png 951w, https:\/\/shawpence.com\/wp-content\/uploads\/2023\/12\/neural-300x176.png 300w, https:\/\/shawpence.com\/wp-content\/uploads\/2023\/12\/neural-768x451.png 768w\" sizes=\"auto, (max-width: 951px) 100vw, 951px\" \/><\/figure>\n\n\n\n<p>Figure 4 Neural Response Generator of Xiaoice<\/p>\n\n\n\n<p>Since Transformer (Vaswani et al., 2017) proposed and became evident, it is also utilized in chatbot. ChatGPT harness the transformer in its decoder to predict the next token of the output texts (OpenAI, 2023) and make great impact in recent months.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Slot_filling_approach_for_intent-oriented_chatbots\"><\/span>Slot filling approach for intent-oriented chatbots<span class=\"ez-toc-section-end\"><\/span><\/h3>\n\n\n\n<p>Slot filling is a simple method for intent-oriented chatbots. This is a classification task on word embeddings targeting to identity all words in the user input whether it belongs to a specific slot where it is called BIO labels. BERT is the popular model in nowadays to address this classification task with a better performance than other encoders like RNN, GRU, or LSTM (Chen et al., 2019). The architecture is shown in figure 5 (Jurafsky &amp; Martin, 2023).<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"865\" height=\"373\" src=\"https:\/\/shawpence.com\/wp-content\/uploads\/2023\/12\/slot_filling.png\" alt=\"Slot Filling\" class=\"wp-image-45\" srcset=\"https:\/\/shawpence.com\/wp-content\/uploads\/2023\/12\/slot_filling.png 865w, https:\/\/shawpence.com\/wp-content\/uploads\/2023\/12\/slot_filling-300x129.png 300w, https:\/\/shawpence.com\/wp-content\/uploads\/2023\/12\/slot_filling-768x331.png 768w\" sizes=\"auto, (max-width: 865px) 100vw, 865px\" \/><\/figure>\n\n\n\n<p>Figure 5 The architecture of slot filling task<\/p>\n\n\n\n<p>We revisited four types of Chatbot technology in this section: rule-based, retrieval-based, generation approach and slot filling. In practice, these four technologies are not used discretely. In a large, business chatbot, two or more strategies are always required to adopt all together. In Xiaoice\u2019s research, a hybrid model is stronger than one way approach (Zhou et al., 2020). And intent-oriented chatbots are always combine the slot filling and rule-based approach.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Applications\"><\/span>Applications<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>Given that chatbot applications have varied so transiently since the dynamic after Transformers are introduced, especially ChatGPT triumphs in the market, people, not only those in academic or computer science industry professionals but also all kinds of individuals regardless of disciplines, jobs, or purposes, are so touched that they are now all engaging in exploring the new applications of chatbot and publishing their discoveries on social media and open source software platform which pushes the past research on the taxonomy of chatbot application obsolete so fast. We already knew that some promising applications would emerge soon, maybe tomorrow, which may challenge our discussions here. Therefore, it will be a better time to recall chatbot applications in a sorted way in the future. In the last of this passage, some chatbot applications will be presented individually in a tentative sort as a retrospective. Furthermore, we can also discuss the future of applications of chatbots.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"FAQ_chatbots_and_knowledge_retrieval_chatbots\"><\/span>FAQ chatbots and knowledge retrieval chatbots<span class=\"ez-toc-section-end\"><\/span><\/h3>\n\n\n\n<p>Institutions constantly encounter intensively consultations, so they collect frequently asked questions from the history records and list them in a web page. This is a conventional approach to address this problem. Chatbot can also retrieve FAQs as a response to users\u2019 queries (Ranoliya et al., 2017) to alleviate the workload of administrative staff (Lee et al., 2019). In this kind of application, chatbot assumes a role of the interface between users and database. By replacing clicks on windows and webpages, user can use their own words to fulfill their wishes to knowledge.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Tasks-oriented_or_intent-based_chatbots\"><\/span>Tasks-oriented or intent-based chatbots<span class=\"ez-toc-section-end\"><\/span><\/h3>\n\n\n\n<p>Businesses deploy tasks-oriented chatbots to receive and execute users\u2019 instructions, like Siri and Google Now when they are asked to check the weather, find a path or a location and control smart appliances. Although it is believed that they are enabled to complete multiple tasks with the help of both sequential models and slot filling approaches, they are regarded as not intelligent enough due to functional defects like poor voice recognition, unnatural dialogue responses, and an inability to support mixed-language speech recognition (Bogers et al., 2019).<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Free_chat_chatbots\"><\/span>Free chat chatbots<span class=\"ez-toc-section-end\"><\/span><\/h3>\n\n\n\n<p>When it is proposed, the first cohort of users surging into Xiaoice tried to test the chatbot with free chat questions. People crave for chatbots to be more humanoid with understanding human\u2019s emotions and responding correctly. When it comes to this objective, it is quite a magic.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Future_What_is_possible_and_what_is_impossible\"><\/span>Future: What is possible and what is impossible?<span class=\"ez-toc-section-end\"><\/span><\/h3>\n\n\n\n<p>All in all, chatbot is a human-computer interface which is capable, theoretically, replacing any other user interface could do and do more. Imagine that I am typing in a document, and you are designing a slide for tomorrow\u2019s presentation, what about, leaving our mice and keyboards, just giving instructions by our voice. It is now being more realistic after Microsoft launched its Microsoft 365 copilot. And technically it is also possible by training a GPT model on a pairwise training dataset combining users\u2019 linguistic inputs and a series instruction in the software.<\/p>\n\n\n\n<p>However, there is something it couldn\u2019t be practical in a foreseeable future. One instance is chatbots\u2019 attempts to play a role as psychological therapist. We have failed since engineers\u2019 first attempt bringing ELIZA to the world. It did not replace any therapist, but only resulting people\u2019s surprises and motivations to develop more powerful chatbots. Emotional intelligent is too complicated to be complete by a robot because people can easily manipulate their input no matter facial expression or utterance.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Reference\"><\/span>Reference<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>Adamopoulou, E., &amp; Moussiades, L. (2020). Chatbots: History, technology, and applications. <em>Machine Learning with Applications<\/em>, <em>2<\/em>, 100006. https:\/\/doi.org\/10.1016\/j.mlwa.2020.100006<\/p>\n\n\n\n<p>Bogers, T., Al-Basri, A. A. A., Ostermann Rytlig, C., Bak M\u00f8ller, M. E., Juhl Rasmussen, M., Bates Michelsen, N. K., &amp; Gerling J\u00f8rgensen, S. (2019). <em>A Study of Usage and Usability of Intelligent Personal Assistants in Denmark<\/em> (N. G. Taylor, C. Christian-Lamb, M. H. Martin, &amp; B. Nardi, Trans.). 79\u201390.<\/p>\n\n\n\n<p>Bruno Marietto, M. das G., Aguiar, R. V., Barbosa, G. de O., Botelho, W. T., Pimentel, E., Franca, R. dos S., &amp; da Silva, V. L. (2013). Artificial Intelligence Markup Language: A Brief Tutorial. <em>International Journal of Computer Science &amp; Engineering Survey<\/em>, <em>4<\/em>(3), 1\u201320. https:\/\/doi.org\/10.5121\/ijcses.2013.4301<\/p>\n\n\n\n<p>Chamberlain, W. (1984). <em>The Policeman\u2019s Beard is Half Constructed: Computer Prose and Poetry<\/em>. Warner Books.<\/p>\n\n\n\n<p>Chen, Q., Zhuo, Z., &amp; Wang, W. (2019). <em>BERT for Joint Intent Classification and Slot Filling<\/em> (arXiv:1902.10909). arXiv. http:\/\/arxiv.org\/abs\/1902.10909<\/p>\n\n\n\n<p>Colby, K. (1976). Artificial paranoia: A computer simulation of paranoid processes. <em>Behavior Therapy<\/em>, <em>7<\/em>(1), 146. https:\/\/doi.org\/10.1016\/S0005-7894(76)80257-2<\/p>\n\n\n\n<p>Devlin, J., Chang, M.-W., Lee, K., &amp; Toutanova, K. (2019). <em>BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding<\/em> (arXiv:1810.04805). arXiv. http:\/\/arxiv.org\/abs\/1810.04805<\/p>\n\n\n\n<p>Jurafsky, D., &amp; Martin, J. H. (2023). <em>Speech and Language Processing<\/em>. Stanford.<\/p>\n\n\n\n<p>Lee, K., Jo, J., Kim, J., &amp; Kang, Y. (2019). <em>Can Chatbots Help Reduce the Workload of Administrative Officers? &#8211; Implementing and Deploying FAQ Chatbot Service in a University<\/em> (C. Stephanidis, Trans.). 348\u2013354.<\/p>\n\n\n\n<p>Molnar, G., &amp; Szuts, Z. (2018). The Role of Chatbots in Formal Education. <em>2018 IEEE 16th International Symposium on Intelligent Systems and Informatics (SISY)<\/em>, 000197\u2013000202. https:\/\/doi.org\/10.1109\/SISY.2018.8524609<\/p>\n\n\n\n<p>OpenAI. (2023). <em>GPT-4 Technical Report<\/em> (arXiv:2303.08774). arXiv. http:\/\/arxiv.org\/abs\/2303.08774<\/p>\n\n\n\n<p>Ranoliya, B. R., Raghuwanshi, N., &amp; Singh, S. (2017). Chatbot for university related FAQs. <em>2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI)<\/em>, 1525\u20131530. https:\/\/doi.org\/10.1109\/ICACCI.2017.8126057<\/p>\n\n\n\n<p>Shum, H., He, X., &amp; Li, D. (2018). From Eliza to XiaoIce: Challenges and opportunities with social chatbots. <em>Frontiers of Information Technology &amp; Electronic Engineering<\/em>, <em>19<\/em>(1), 10\u201326. https:\/\/doi.org\/10.1631\/FITEE.1700826<\/p>\n\n\n\n<p>Skrebeca, J., Kalniete, P., Goldbergs, J., Pitkevica, L., Tihomirova, D., &amp; Romanovs, A. (2021). Modern Development Trends of Chatbots Using Artificial Intelligence (AI). <em>2021 62nd International Scientific Conference on Information Technology and Management Science of Riga Technical University (ITMS)<\/em>, 1\u20136. https:\/\/doi.org\/10.1109\/ITMS52826.2021.9615258<\/p>\n\n\n\n<p>Sutskever, I., Vinyals, O., &amp; Le, Q. V. (2014). <em>Sequence to Sequence Learning with Neural Networks<\/em>.<\/p>\n\n\n\n<p>Thorat, S. A., &amp; Jadhav, V. (2020). A Review on Implementation Issues of Rule-based Chatbot Systems. <em>SSRN Electronic Journal<\/em>. https:\/\/doi.org\/10.2139\/ssrn.3567047<\/p>\n\n\n\n<p>Van Pinxteren, M. M. E., Pluymaekers, M., &amp; Lemmink, J. G. A. M. (2020). Human-like communication in conversational agents: A literature review and research agenda. <em>Journal of Service Management<\/em>, <em>31<\/em>(2), 203\u2013225. https:\/\/doi.org\/10.1108\/JOSM-06-2019-0175<\/p>\n\n\n\n<p>Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, \u0141., &amp; Polosukhin, I. (2017). Attention is all you need. <em>Advances in Neural Information Processing Systems<\/em>, <em>30<\/em>.<\/p>\n\n\n\n<p>Wallace, R. S. (2009). <em>The anatomy of ALICE<\/em>. Springer.<\/p>\n\n\n\n<p>Wallace, R. S. (2014, March 9). <em>AIML 2.0 Working Draft<\/em>. Gist. https:\/\/gist.github.com\/onlurking\/f6431e672cfa202c09a7c7cf92ac8a8b<\/p>\n\n\n\n<p>Weizenbaum, J. (1966). ELIZA\u2014a computer program for the study of natural language communication between man and machine. <em>Communications of the ACM<\/em>, <em>9<\/em>(1), 36\u201345.<\/p>\n\n\n\n<p>Zem\u010d\u00edk, Mgr. T. (2019). A Brief History of Chatbots. <em>DEStech Transactions on Computer Science and Engineering<\/em>, <em>aicae<\/em>. https:\/\/doi.org\/10.12783\/dtcse\/aicae2019\/31439<\/p>\n\n\n\n<p>Zhou, L., Gao, J., Li, D., &amp; Shum, H.-Y. (2020). The Design and Implementation of XiaoIce, an Empathetic Social Chatbot. <em>Computational Linguistics<\/em>, <em>46<\/em>(1), 53\u201393. https:\/\/doi.org\/10.1162\/coli_a_00368<\/p>\n","protected":false},"excerpt":{"rendered":"<p>This is one of my course reports at first sumbitted in April, 2023 and published here in Dec, 2023. History When ChatGPT has been introduced months ago, the current dynamics of chatbots advances Alan Turing (1950)\u2019s ideal, where he proposed the question \u201cCan machines think\u201d. This retrospective will look back at the history of chatbots, [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"slim_seo":[],"footnotes":""},"categories":[4],"tags":[],"class_list":["post-24","post","type-post","status-publish","format-standard","hentry","category-report"],"_links":{"self":[{"href":"https:\/\/shawpence.com\/index.php?rest_route=\/wp\/v2\/posts\/24","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/shawpence.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/shawpence.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/shawpence.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/shawpence.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=24"}],"version-history":[{"count":22,"href":"https:\/\/shawpence.com\/index.php?rest_route=\/wp\/v2\/posts\/24\/revisions"}],"predecessor-version":[{"id":51,"href":"https:\/\/shawpence.com\/index.php?rest_route=\/wp\/v2\/posts\/24\/revisions\/51"}],"wp:attachment":[{"href":"https:\/\/shawpence.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=24"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/shawpence.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=24"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/shawpence.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=24"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}