Notes:
K-means is an algorithm for clustering data into groups, or “clusters,” based on their similarity. K-means is an unsupervised learning algorithm, which means that it does not require labeled data to work, and is often used to discover patterns and relationships in data that are not immediately apparent.
In the context of chatbots, K-means can be used to cluster user input into different categories based on their similarity. For example, a chatbot might use K-means to cluster user questions about a specific topic into different categories, such as “questions about product features,” “questions about pricing,” and “questions about availability.” This can help the chatbot to understand the user’s intent and generate more appropriate and relevant responses.
K-means can also be used to cluster user input based on other factors, such as the tone or sentiment of the user’s message. For example, a chatbot might use K-means to cluster user input into categories such as “positive feedback,” “negative feedback,” and “neutral feedback,” which could be used to improve the chatbot’s ability to understand the user’s sentiment and respond appropriately.
See also:
Cluster-based beam search for pointer-generator chatbot grounded by knowledge
YC Tam – Computer Speech & Language, 2020 – Elsevier
… to-end approach for knowledge-grounded response generation in Dialog System Technology Challenges … beam search strategy to improve response diversity driven by K-means clustering and … 1. The proposed system flowchart for knowledge-grounded conversational chatbot …
User attention-guided multimodal dialog systems
C Cui, W Wang, X Song, M Huang, XS Xu… – Proceedings of the 42nd …, 2019 – dl.acm.org
… Chatbot … To be more speci c, the multimodal encoder takes users’ and chatbots’ multimodal utterances as input and outputs the utterance … v to the common high dimensional space, respectively, ? denotes the element-wise product, and the function SumPoolin(x,k) means using …
CBET: design and evaluation of a domain-specific chatbot for mobile learning
Q Liu, J Huang, L Wu, K Zhu, S Ba – Universal Access in the Information …, 2019 – Springer
… We establish a domain-spe- cific gate based on k-means algorithm to extend the open- domain DeepQA … To enhance the chatbots applied in mobile learning, we pro- pose an intelligent chatbot for the field … This chatbot features a question-and-answer service in a specific domain …
Building a Production Model for Retrieval-Based Chatbots
K Swanson, L Yu, C Fox, J Wohlwend, T Lei – arXiv preprint arXiv …, 2019 – arxiv.org
… 1 Introduction Predicting a response given conversational con- text is a critical task for building open-domain chatbots and dialogue systems … The closest work to ours is Lu et al. (2017), who build a whitelist using a k-means clustering of responses …
A SURVEY To Chatbot System With Knowledge Base Database By Using Artificial Intelligence & Expert Systems
MNR Khante, MKN Hande – 2019 – academia.edu
… tricks: these are sentences, phrases, or even paragraphs available in Chatbots in order … The Development of this chatbot is done using Microsoft bot framework, which is using … 6. AMChandrashekhar, K. Raghuveer “Intrusion Detection techniques by using K-means, fuzzy …
Long Term Memory in Conversational Robots
J Olson, E Södergren – 2019 – diva-portal.org
… A chatbot with a long-term memory is likely to improve customer engagement [3], improve … updating algorithm of the cluster centroids after each iteration of the k-means algorithm … enabled by advances in technology, such as automated response systems and chatbots for instance …
An Ensemble Deep Active Learning Method for Intent Classification
L Zhang, L Zhang – Proceedings of the 2019 3rd International …, 2019 – dl.acm.org
… For these task- oriented dialogue systems, natural language understanding (NLU) plays a critical role and … speakers and customer service systems, we cannot deny the fact that chatbots can achieve … The methods usually utilize k-means and k-center [7] to choose the core-set …
SARG: A Novel Semi Autoregressive Generator for Multi-turn Incomplete Utterance Restoration
M Huang, F Li, W Zou, W Zhang – arXiv preprint arXiv:2008.01474, 2020 – arxiv.org
… Utterance 2 Chatbot: ?????????? Chatbot: You’ll have to ask Li Chunfeng about that … Table 1: An example of utterance restoration in human machine dialogue system … In the first column of label, D means the DELETE operation, K means the KEEP operation and the C …
Clustering Approach to Topic Modeling in Users Dialogue
E Feldina, O Makhnytkina – Proceedings of SAI Intelligent Systems …, 2020 – Springer
… User dialogue texts collected during a chatbot competition from real users [7] or … For deeper analysis Hierarchical k-means and Hierarchical agglomerative clustering was applied on best … Rudnicky, A.: RubyStar: A Non-Task-Oriented Mixture Model Dialog System (2017)Google …
Passive Diagnosis of Mental Health Disorders Incorporating an Empathic Dialogue System
F Delahunty, M Arcan, R Johansson – 2019 – thesiscommons.org
… 3Commonly known as chatbots … par- ticipants from the public domain who had a short conversation with our proposed empathic dialogue system … To evaluate Hypothesis 2, we randomly allocated recruited participants to have conversations with one of two dialogue systems …
Virtual Assistance in Any Context
J Antje, P Jens, RC Davinia, MH Breitner – Business & Information Systems …, 2020 – Springer
… empirically observable in any of the analyzed objects; (ii) merging redundant character- istics (ie, conversational chatbots and interactive chat- bots, (iii) disjoining … the new characteristics identified during the examination (ie, utility into the dimension motivation for chatbot use …
Towards a taxonomy of platforms for conversational agent design
S Diederich, AB Brendel, LM Kolbe – 2019 – aisel.aisnet.org
… In the second step, we used the chosen number of groups for a k-means clustering procedure … 25. Shawar, BE, Atwell, E.: Chatbots: Are they really useful … with artificial intelligence: A comparison between human-human online conversations and human-chatbot conversations …
An Industrial Application of Soft Computing for the Design of Personalized Call Centers
D Griol, JM Molina, A Sanchis – … Workshop on Soft Computing Models in …, 2019 – Springer
… companies identifying the prospective customers and preventing them stopping using again the chatbot … we employed the X-means clustering algorithm, a variation of K-means clustering that … The development of personalized chatbots is key in the pathway towards this scenario …
Dialogue breakdown detection robust to variations in annotators and dialogue systems
J Takayama, E Nomoto, Y Arase – Computer Speech & Language, 2019 – Elsevier
… For the variationality, different chat-bots show different characteristics in their responses. DBDC data consists of dialogues collected from three systems: a chat-bot API provided by NTT … First, the k-means clustering is employed to cluster annotators based on their annotation …
Intent Detection-Based Lithuanian Chatbot Created via Automatic DNN Hyper-Parameter Optimization
J Kapo?i?t?-Dzikien? – Frontiers in Artificial Intelligence and …, 2020 – books.google.com
… Stochastic Gradient Descent, Nearest Centroid, Multinomial Naive Bayes, Bernoulli Naive Bayes, K-means … J. An Information Retrieval-based Approach for Building Intuitive Chatbots for Large … Li Z, Zhou J. DocChat: An Information Retrieval Approach for Chatbot Engines Using …
Antje Janssen, Jens Passlick, Davinia Rodríguez Cardona & Michael
H Breitner – researchgate.net
… empirically observable in any of the analyzed objects; (ii) merging redundant character- istics (ie, conversational chatbots and interactive chat- bots, (iii) disjoining … the new characteristics identified during the examination (ie, utility into the dimension motivation for chatbot use …
Topic Detection from Conversational Dialogue Corpus with Parallel Dirichlet Allocation Model and Elbow Method
H Khalid, V Wade – arXiv preprint arXiv:2006.03353, 2020 – arxiv.org
… Almost fifty years ago, ELIZA [16] was created as the first conversational software and considered as an intelligent chat-bot … Modified K-Means for Better Initial Cluster Centres … His current research is focused on topic detection and topic modelling for dialog system with NLP …
A Literature Review of Quantitative Persona Creation
J Salminen, K Guan, SG Jung, SA Chowdhury… – Proceedings of the …, 2020 – dl.acm.org
… For example, Zhu et al. [90] cite several methods: affinity diagrams, decision trees, exploratory factor analysis (EFA), hierarchical clustering, k-means clustering, latent semantic analysis (LSA), multidimensional scaling analysis (MSA), and weighted graphs. Minichiello et al …
Sentiment Analysis and Deep Learning Based Chatbot for User Feedback
S Sankar – Intelligent Communication Technologies and Virtual …, 2019 – Springer
… 12] built multi-turn conversation chatbots which considers … They make use of modified approach which is based on both K-means clustering and Cuckoo search … Another important part of the future work is to build a speech recognizing chatbot which recognizes the user sentiment …
Remote cardiovascular health monitoring system with auto-diagnosis
B Bhattacharya, S Mohapatra… – … on Vision Towards …, 2019 – ieeexplore.ieee.org
… Chatbots are generally used in dialog systems for various practical purposes and use sophisticated Natural Language … Figure 5. Chatbot Questionnaire … D.5. K-Means Clustering with Naive Bayes (KMNB) KMNB algorithm is implemented by summing classification and clustering …
Extracting Dialog Structure and Latent Beliefs from Dialog Corpus.
A Chhabra, P Saini, C Anantaram – LaCATODA/BtG@ IJCAI, 2019 – ceur-ws.org
… It is observed that most of the time chatbots behave mechanically and do not take cus … on extracting the latent beliefs in the conversations that is required to tailor the chatbot inter- action … We use K-means clustering, where k value is determined by elbow method, to create clusters …
Unsupervised dialogue intent detection via hierarchical topic model
A Popov, V Bulatov, D Polyudova… – Proceedings of the …, 2019 – aclweb.org
… One of the challenges during a task- oriented chatbot development is the scarce availability of the labeled training data … More universal and robust dialogue systems should work without any supervision or defined rules … Second, we cluster this dataset via K-Means algorithm …
Reinforcement learning for Dialogue Systems optimization with user adaptation.
N Carrara – 2019 – tel.archives-ouvertes.fr
… The first proposed approach involves clustering of Dialogue Systems (tailored for their respective user) based on their behaviours … The second idea states that before using a dedicated Dialogue System, the first in- teractions with a user should be handled carefully by a safe …
Tod-bert: Pre-trained natural language understanding for task-oriented dialogues
CS Wu, S Hoi, R Socher, C Xiong – arXiv preprint arXiv:2004.06871, 2020 – arxiv.org
… test ToD-BERT on four common down- stream tasks of task-oriented dialogue systems, in- cluding … them are designed to cope with the response generation task for open- domain chatbots … This allows a single dialogue system to support a large number of services and facilitates …
Adaptive dialogue management using intent clustering and fuzzy rules
D Griol, Z Callejas, JM Molina, A Sanchis – Expert Systems, 2020 – Wiley Online Library
… in mobile devices and smart speakers, educational tutoring agents, entertainment chatbots in open … 2004) and has been used to develop hundreds of successful commercial dialogue systems … based approaches are also an efficient alternative when the dialogue system must be …
Intent Mining from past conversations for Conversational Agent
A Chatterjee, S Sengupta – arXiv preprint arXiv:2005.11014, 2020 – arxiv.org
… been a growing community and business interest in conversational systems (chatbots primarily) and … of supervised training mechanism, which is supported by many commercial chatbot building frameworks … Although K-Means is very fast and mostly used for clustering, it requires …
Multimodal Interaction System for Home Appliances Control.
H Fakhrurroja, C Machbub… – International Journal of …, 2020 – search.ebscohost.com
… Gesture recognition process with the K-Means Clustering method used C# code … This dialog system has text processing to understand the intent of the user … The dialogue system requires input slots in the form of verbs, appliances, adverbs, attributes, or adjectives to be able to …
Comparing the Performance of Feature Representations for the Categorization of the Easy-to-Read Variety vs Standard Language
M Santini, B Danielsson, A Jönsson – … of the 22nd Nordic Conference on …, 2019 – aclweb.org
… the retrieval of easy-to-read or patient-friendly medical information) and deep learning-based dialogue systems (eg customized chatbots for expert … an implementation of SVM, an imple- mentation of multilayer perceptron (MLP) and an implementation of K-Means for clustering …
A deep learning architecture for emotional aware chatbots
RH Grouls – 2020 – dspace.library.uu.nl
… EMOTIONAL AWARE CHATBOTS 3 … the dimensionality of the state space, it does the same for the action space if we expect the chatbot to use … answers (like ELIZA did: “oh interesting, tell me more…”) this sets high expectations for the grammatical skill level of the chat- bot …
Exploring machine learning and deep learning frameworks for task-oriented dialogue act classification
T Saha, S Srivastava, M Firdaus, S Saha… – … Joint Conference on …, 2019 – ieeexplore.ieee.org
… Applications such as online chat-bots that include the Problem Solving Agent, Conversational Agent, etc … tag-set is proposed which is more appropriate for building a chat-bot system … K-means [22] is one of the simplest unsupervised learning algorithms that solves the well known …
Affect-aware Conversational System
A Ekbal – 2020 – iitp.ac.in
… Page 12. Today’s Chatbot: A Long way from ELIZA ? Nowadays, Chatbots have grown into a full-blown industry with … Makes the Chatbot more human-like while generating responses … k-means clustering (k = 300) used to cluster these sentences ? Annotations …
Dissecting the components and factors of Neural Text Generation
KR Chandu, AW Black – arXiv preprint arXiv:2010.07279, 2020 – arxiv.org
… At each time step, Tam (2020) get the top 2b candidates and embed them by using averaged Glove representations. Cluster them us- ing k-means to get k clusters. And then, they pick the top b/k candidates from each cluster to get b candidates in total for that time step …
A hybrid retrieval-generation neural conversation model
L Yang, J Hu, M Qiu, C Qu, J Gao, WB Croft… – Proceedings of the 28th …, 2019 – dl.acm.org
… Retrieval (IR), Natural Language Processing (NLP) and Machine Learning (ML) communities, leading to a rapidly growing field referred to as Conversational AI [7]. Typical task-oriented dialog systems use a … Session: Long – Question Answering and Dialogue Systems I …
A comparative study of social bot classification techniques
F Örnbratt, J Isaksson, M Willing – 2019 – diva-portal.org
… Vector Machines or k-means. Additionally, a plethora of different machine learning libraries and tools … Web Robots (crawlers) ? Chatbots (natural language based dialog system) ? Spambots (bots that advertise and post spam on online messaging platforms) …
Latest Developments in Deep Learning in Finance 8th November 2019
NYU Courant – 2019 – pdfs.semanticscholar.org
… Machine Learning in Finance Page 6. k-Means, FuzzyC-Means UNSUPERVISED CLUSTERING … Machine translation • Spoken dialog systems • Complex question answering NLP in Industry … Speech recognition • Chatbots / Dialog agents • Automating customer support …
Automatic Ontology Population Using Deep Learning for Triple Extraction
MH Su, CH Wu, PC Shih – 2019 Asia-Pacific Signal and …, 2019 – ieeexplore.ieee.org
… Therefore, ontology is useful for a chatbot system [14]-[15 … The subscript k means the ?? ??? feature function, and each feature function has a … Mehta, R. Gupta, A. Raux, D. Ramachandran, and S. Krawczyk, “Probabilistic ontology trees for belief tracking in dialog systems,” Proc …
A discrete cvae for response generation on short-text conversation
J Gao, W Bi, X Liu, J Li, G Zhou, S Shi – arXiv preprint arXiv:1911.09845, 2019 – arxiv.org
… Deep reinforcement learning is also applied to model future reward in chatbot after an encoder-decoder model converges (Li et al., 2016c, 2017) … We use the K-means clustering algorithm to group z’s us- ing a pre-trained embedding corpus (Song et al., 2018) …
Improving neural conversational models with entropy-based data filtering
R Csaky, P Purgai, G Recski – arXiv preprint arXiv:1905.05471, 2019 – arxiv.org
… K-means proved inferior to the Mean Shift algorithm, which is a density-based clustering al- gorithm … As mentioned in Section 2, automatic evaluation of chatbots is an open research problem … at the validation loss minimum of a model, however in the case of chatbot models loss …
Learning Multi-Party Turn-Taking Models from Dialogue Logs
MG de Bayser, P Cavalin, C Pinhanez… – arXiv preprint arXiv …, 2019 – arxiv.org
… The expert chatbots are not only able to give answers related to investments but can also … human-machine interactions and is more topic-oriented in a way that each chatbot interacts only … Then, the utterance vectors are given as input to a K-means clustering algorithm [19] …
Automating Template Creation for Ranking-Based Dialogue Models
J Chen, H Elfardy, S Wang, A Kahn… – Proceedings of the 2nd …, 2020 – aclweb.org
… For K-means, we use the centroid as the represen- tation of the cluster, while for other algorithms, we take the mean pooling for … Alime chat: A sequence to sequence and rerank based chatbot engine … Multi-turn response selection for chatbots with deep attention matching network …
Comparison of diverse decoding methods from conditional language models
D Ippolito, R Kriz, M Kustikova, J Sedoc… – arXiv preprint arXiv …, 2019 – arxiv.org
… condense and remove meaningless responses from chatbots. Specifi- cally, at each decoding step t, this method initially considers the top 2?b candidates. From there, each candidate sequence is embedded3, and the embed- dings are clustered into c clusters using K-means …
Artificial Intelligence acceptance: morphological elements of the acceptance of Artificial Intelligence
MM Figueiredo – 2019 – repositorio.ucp.pt
… Logically, one of the biggest applications of unsupervised learning is clustering (such as k-means clustering algorithm for example) … Duolingo is a very well-known chatbot that allows people to learn and … to chatbots ranging from virtual agents and dialogue systems to machine …
Automatic Labeled Dialogue Generation for Nursing Record Systems
T Mairittha, N Mairittha, S Inoue – Journal of Personalized Medicine, 2020 – mdpi.com
… As we can see, well-known chatbot platforms (eg, Amazon Lex (https://aws.amazon.com/lex), Google Dialogflow (https … First, we explain the basic concept of a task-oriented dialogue system, NLU components, and related works involving entity … [38] used the k-means algorithm to …
Integrating a cognitive assistant within a critique-based recommender system
M Güell, M Salamó, D Contreras, L Boratto – Cognitive Systems Research, 2020 – Elsevier
… Kucherbaev et al., 2017 outlined their vision of chatbots that facilitate interaction … an overall architecture for developing a recommender system interacting with a dialogue system … PageRank algorithm) in a movie recommendation scenario, implemented as a Telegram chatbot …
Cluster-based information retrieval using pattern mining
Y Djenouri, A Belhadi, D Djenouri, JCW Lin – Applied Intelligence, 2020 – Springer
… [34] proposed an end-to-end approach for knowledge-grounded response generation in dialog system technology challenges. The k-means algorithm was adopted to enable dynamically grouping the similar partial hypotheses at each decoding step under a fixed beam budget …
Contextual Out-of-domain Utterance Handling with Counterfeit Data Augmentation
S Lee, I Shalyminov – ICASSP 2019-2019 IEEE International …, 2019 – ieeexplore.ieee.org
… Recently, there has been a surge of excitement in developing chatbots for various purposes in research … To study the effect of OOD input on dialog system’s perfor- mance, we use three task … P@K means Precision@K. OOD F1 denotes f1-score for OOD detection over utterances …
A survey of natural language generation techniques with a focus on dialogue systems-past, present and future directions
S Santhanam, S Shaikh – arXiv preprint arXiv:1906.00500, 2019 – arxiv.org
… Keywords: deep learning, language generation, dialog systems … 1993) found issues with using RST when they tried to use the individual seg- ments and rhetorical relations between segments to construct a text plan for their dialogue system … (2013) used k-means clustering to …
MSc in Computer Science
RB Sulaiman – researchgate.net
… CHAPTER INFORMATION IN THIS CHAPTER ? Overview ? Chatbot system ? Chatbot technology ? Types of chatbot ? Comparison of chatbots ? Functions of chatbot ? Syntactic analysis ? Vector space model ? Machine learning models ? Support vector machines (SVM) …
What Is Artificial Intelligence and How to Exploit It?
RT Kreutzer, M Sirrenberg – Understanding Artificial Intelligence, 2020 – Springer
… In these, the algorithm should independently recognize a structure. For this purpose, the algorithm identifies data groups that exhibit a similar behavior or similar characteristics. Here, the methods hierarchical and K-Means clustering are used …
A Study of Information Bots and Knowledge Bots
A Hatua – 2020 – aquila.usm.edu
… their diffusion. On the other hand, chatbots are used for the study of Knowledge bots. Knowledge base plays the most critical role in developing a Goal-Oriented (GO) chatbot. A GO chatbot is as good as its knowledge base …
Augmenting advanced analytics into enterprise systems: A focus on post-implementation activities
A Elragal, HED Hassanien – Systems, 2019 – mdpi.com
… Additionally, the illustration shows how the purposefully designed spoken dialogue system (SDS) or chatbot helps users to manually interact with the AAE for problem identification and solution-confirmation purposes. System …
Do Massively Pretrained Language Models Make Better Storytellers?
A See, A Pappu, R Saxena, A Yerukola… – arXiv preprint arXiv …, 2019 – arxiv.org
Page 1. Do Massively Pretrained Language Models Make Better Storytellers? Abigail See, Aneesh Pappu?, Rohun Saxena?, Akhila Yerukola?, Christopher D. Manning Stanford University {abisee,apappu,rohun,akhilay,manning}@cs.stanford.edu Abstract …
Courteously Yours: Inducing courteous behavior in Customer Care responses using Reinforced Pointer Generator Network
H Golchha, M Firdaus, A Ekbal… – Proceedings of the 2019 …, 2019 – aclweb.org
… Thus, it is imperative for customer care agents and chat- bots engaging with humans to be … Such systems have high applications in many areas/companies that employ chatbots to deal with the … We use the K-Means clustering(Aggarwal and Zhai, 2012)(k = 300) to cluster these …
Statistical natural language processing methods for intelligent process automation
A Moiseeva – 2020 – edoc.ub.uni-muenchen.de
… Wie bereits erwähnt, sind Chat- bots eine der zentralen Anwendungen für die IPA-Domäne, da … applications of NLP within the IPA domain – are conversational interfaces (eg, chatbots) that are … In a conventional chat- bot system, a user provides input in a natural language, the …
Query Intent Detection from the SEO Perspective
S Mohammadi, M Chapon, A Frémond – European Conference on …, 2020 – Springer
… applications in Natural Language Processing (NLP) tasks such as question answering, chatbots, and search … C., Spink, A.: Classifying the user intent of web queries using k-means clustering … Y., Lin, M.: Review of intent detection methods in the human-machine dialogue system …
On the Impact of Voice Encoding and Transmission on the Predictions of Speaker Warmth and Attractiveness
LF Gallardo, R Sanchez-Iborra – ACM Transactions on Knowledge …, 2019 – dl.acm.org
… Chatbots are becoming increasingly predominant, especially for customer service and personal companions and … Adaptive human- machine spoken dialog systems are already able to react to changes in … K-means clustering has then been applied to the factor scores of the first …
Transforming the communication between citizens and government through AI-guided chatbots
A Androutsopoulou, N Karacapilidis, E Loukis… – Government Information …, 2019 – Elsevier
… in the proposed solution builds on various well-tried algorithms and techniques, including Neural Networks, K-means, Decision Trees … blocks, the abovementioned services add intelligence to the functionality and user interfaces of existing chatbots (and chatbot builders), the …
Embeddings in Natural Language Processing: Theory and Advances in Vector Representations of Meaning
MT Pilehvar… – Synthesis Lectures on …, 2020 – morganclaypool.com
… 2020 Conversational AI: Dialogue Systems, Conversational Agents, and Chatbots Michael McTear 2020 Natural Language Processing for Social Media, Third Edition Anna Atefeh Farzindar and Diana Inkpen 2020 Statistical …
Understanding Artificial Intelligence
RT Kreutzer, M Sirrenberg – 2020 – Springer
Page 1. Management for Professionals Understanding Artificial Intelligence Ralf T. Kreutzer · Marie Sirrenberg Fundamentals, Use Cases and Methods for a Corporate AI Journey Page 2. Management for Professionals Page 3 …
Ambient Assisted Living with Deep Learning
E Merdivan – 2019 – tel.archives-ouvertes.fr
… important components: improving activity recognition, addressing privacy concerns and developing intelligent dialogue systems for AAL systems, with an emphasis on a framework which is flexible and scalable for real-world applications. Page 20. Chapter 1. Introduction 3 …
Incorporating Politeness across Languages in Customer Care Responses: Towards building a Multi-lingual Empathetic Dialogue Agent
M Firdaus, A Ekbal, P Bhattacharyya – Proceedings of The 12th …, 2020 – aclweb.org
… Such systems are highly prevalent nowadays in the form of chatbots and personal assistants like Ap … language generation is one of the core components of every dialogue system (Shen et al., 2018 … We then use the K-means clus- tering algorithm (Aggarwal and Zhai, 2012) with k …
Named Entity Recognition and Relation Detection for Biomedical Information Extraction
N Perera, M Dehmer, F Emmert-Streib – Frontiers in Cell and …, 2020 – frontiersin.org
The number of scientific publications in the literature is steadily growing, containing our knowledge in the biomedical, health, and clinical sciences. Since there is currently no automatic archiving of the obtained results, much of this information remains buried in textual details not …
User Intention Recognition and Requirement Elicitation Method for Conversational AI Services
J Tian, Z Tu, Z Wang, X Xu, M Liu – arXiv preprint arXiv:2009.01509, 2020 – arxiv.org
… II. RELATED WORK A. The status of chat-bot … Artificial design of semantic slots is the most commonly used way for intention understanding of chat-bots … Baseline and Evaluation The experiment defines the k- means method as a traditional pruning strategy to simulate the whole …
Value Co-Creation in Smart Services: A Functional Affordances Perspective on Smart Personal Assistants
R Knote, A Janson, M Söllner… – Journal of the …, 2020 – alexandria.unisg.ch
Page 1. Value Co-Creation in Smart Services: A Functional Affordances Perspective on Smart Personal Assistants* Robin Knote1, Andreas Janson1, Matthias Söllner2, Jan Marco Leimeister1,3 University of Kassel 1 Information …
Diving Deep into Deep Learning: History, Evolution, Types and Applications
HCA Deekshith Shetty, MJ Varma, S Navi, MR Ahmed – researchgate.net
… Regression Support Vector Machine (SVM) Support Vector Regression Kernel SVM Decision Tree Regression Naive Bayes Decision Tree Classification Random Forest Classification Unsupervised Learning Clustering Dimensionality Reduction K-Means Principal Component …
Neural Language Generation: Formulation, Methods, and Evaluation
C Garbacea, Q Mei – arXiv preprint arXiv:2007.15780, 2020 – arxiv.org
… Examples of attributes used for conditioning the generated text are the source sentence in machine translation, the con- versational history in dialogue systems, the input document in text summarization and text simpli- fication, the input question in question answering systems …
Natural Language Processing Advancements By Deep Learning: A Survey
A Torfi, RA Shirvani, Y Keneshloo, N Tavvaf… – arXiv preprint arXiv …, 2020 – arxiv.org
… tion of a high-dimensional data space. Several approaches such as K-means clustering and principal component analysis have been proposed and successfully implemented to this end. With the advent of deep learning and …
Critical Infrastructures Security: Improving Defense Against Novel Malware and Advanced Persistent Threats
G Laurenza – 2020 – iris.uniroma1.it
Page 1. Critical Infrastructures Security: Improving Defense Against Novel Malware and Advanced Persistent Threats Department of Computer, Control, and Management Engineering Antonio Ruberti, Sapienza – University of Rome …
Novel Computational Linguistic Measures, Dialogue System and the Development of SOPHIE: Standardized Online Patient for Healthcare Interaction Education
MR Ali, T Sen, B Kane, S Bose, TM Carroll… – arXiv preprint arXiv …, 2020 – arxiv.org
… Page 9. Novel Computational Linguistic Measures, Dialogue System and the Development of SOPHIE: Standardized Online Patient for Healthcare Interaction Education • 111:9 … sentiment among the transcripts, we applied the k-means clustering algorithm ([24]) …
Complexity-weighted loss and diverse reranking for sentence simplification
R Kriz, J Sedoc, M Apidianaki, C Zheng… – arXiv preprint arXiv …, 2019 – arxiv.org
… the-art performance on a variety of NLP tasks, in- cluding machine translation (Vaswani et al., 2017) and dialogue systems (Vinyals and … into a document embedding using Paragraph Vector (Le and Mikolov, 2014), cluster the vec- tor representations using k-means, and select …
Adaptace jazykového modelu na téma v reálném ?ase
J Lehe?ka – 2019 – otik.uk.zcu.cz
… days. Typical applications, in which ASR is indispensable, are: (1) chatbots, virtual assis- tants and dialogue systems, where people are conversing with computers, (2) dictating systems, where people need to note a large amount of information without typing it …
Evaluating the Evaluation of Diversity in Natural Language Generation
G Tevet, J Berant – arXiv preprint arXiv:2004.02990, 2020 – arxiv.org
… For ex- ample, a dialog system (Adiwardana et al., 2020) should permit many responses for the prompt … Du and Black (2019) suggest to cluster the embedded sentences with k-means, then use its … (2019) let crowd- sourcing workers interact with a dialog chat-bot, then asked …
Cognitive Computing Recipes
A Masood, A Hashmi – Springer
Page 1. Cognitive Computing Recipes Artificial Intelligence Solutions Using Microsoft Cognitive Services and TensorFlow — Adnan Masood Adnan Hashmi Foreword by Matt Winkler Page 2. Cognitive Computing Recipes Artificial Intelligence Solutions Using …
A Systematic Approach for Automatically Answering General-Purpose Objective and Subjective Questions
LP Acharya – 2019 – repository.lib.fit.edu
… 1960s by the MIT Artificial Intelligence Laboratory to demonstrate the communication between humans and machines. Similar to a chatbot, ELIZA uses pattern matching and substitution methodologies to simulate conversations. DOCTOR is an example of a script …
DEEP NEURAL NETWORK MODELS FOR SEQUENCE LABELING AND COREFERENCE TASKS
BM Sergeevich – mipt.ru
… 86 3.9 Annotating step of a voice-enabled chatbot … groups in data (eg, k-Means, Hierarchical Cluster Analysis, Expectation Maximization) … attention from researchers and widely covered in the media. 1966 ELIZA ELIZA was one of the earliest chatbots, developed by Joseph …
AI and IoT in Healthcare
S Singla – Internet of Things Use Cases for the Healthcare …, 2020 – Springer
… proposed bunching dependent on continued bisecting k-means with the objective of obtaining patient … Woebot is an AI-sponsored chatbot that enables individuals to examine their tension and … that can play out these underlying analytic evaluations—regularly as chatbots over a …
Lithium-Ion Batteries
B Writer – A Machine-Generated Summary of Current Research …, 2019 – Springer
… weather forecast (data-to-text), automated medical reviews and not to forget the remarkable progress in dialog systems (chat bots, smart speakers … The document clusters, ie document to chapter assignments, are produced by k-means clustering on the term-document matrix with …
Opinion Analysis in Interactions: From Data Mining to Human-Agent Interaction
C Clavel – 2019 – books.google.com
… 8 1.3.2. The WoZ H–A negotiation corpus . . . . . 9 1.3.3. The UE-HRI human–robot corpus . . . . . 10 1.4. Written H–A corpus: chatbot . . . . . 15 1.5. Comparative study of different corpora …
The bottleneck simulator: A model-based deep reinforcement learning approach
IV Serban, C Sankar, M Pieper, J Pineau… – Journal of Artificial …, 2020 – jair.org
Page 1. Journal of Artificial Intelligence Research 69 (2020) 571-612 Submitted 07/2018; published 10/2020 The Bottleneck Simulator: A Model-Based Deep Reinforcement Learning Approach Iulian Vlad Serban iulian.vlad.serban@umontreal.ca Chinnadhurai Sankar …
Response Retrieval in Information-seeking Conversations
L Yang – 2019 – scholarworks.umass.edu
Page 1. University of Massachusetts Amherst ScholarWorks@UMass Amherst Doctoral Dissertations Dissertations and Theses 2019 Response Retrieval in Information-seeking Conversations Liu Yang College of Information and Computer Sciences, UMass Amherst …
Era of Intelligent Systems in Healthcare
S Belciug, F Gorunescu – … Decision Support Systems—A Journey to …, 2020 – Springer
The aim of this chapter is to prepare the reader for the outstanding trip that she/he embarked when starting reading this book. At first, we shall try to look for answers to some of the most…
Towards Socially Interactive Agents: Learning Generative Models of Social Interactions Via Crowdsourcing
D Feng – 2020 – search.proquest.com
Page 1. 8/31/20 Page 2. Page 3. Towards Socially Interactive Agents: Learning Generative Models of Social Interactions via Crowdsourcing A Dissertation Presented by Dan Feng to Khoury College of Computer Sciences in partial fulfillment of the requirements for the degree of …
Unsupervised Text Representation Learning with Interactive Language
H Cheng – 2019 – digital.lib.washington.edu
… 37 4.7 t-SNE visualization of response trigger vectors clustered using k-means … tion scenario takes place between a human user and a dialogue system powered by conversational … (aka chatbots) have been developed for entertainment, companionship and education purpose …
A Companion Robot for Modeling the Expressive Behavior of Persons with Parkinson’s Disease
AP Valenti – 2020 – search.proquest.com
… 107 Chapter 6 Improving Natural Language Understanding in Spoken Dialogue Systems 109 6.1 Introduction … 72 4.5 k-means clustering identified center-points of the three classes: nega … xix Page 21. 6.1 Typical components of a spoken dialogue system. At each turn t …
ICTAI 2019
YM Boumarafi, Y Salhi – computer.org
… 186 Gabriel Hartmann (Ariel university, Israel), Zvi Shiller (Ariel university, Israel), and Amos Azaria (Ariel university, Israel) Shallow Deep Learning: Embedding Verbatim K-Means in Deep Neural Networks 194 Len Du (Australian National University) …
Intelligent Decision Support Systems: A Journey to Smarter Healthcare
S Belciug, F Gorunescu – 2020 – Springer
Page 1. Intelligent Systems Reference Library 157 Smaranda Belciug Florin Gorunescu Intelligent Decision Support Systems–A Journey to Smarter Healthcare Page 2. Intelligent Systems Reference Library Volume 157 Series Editors …
Machine learning in mental health: A systematic review of the HCI literature to support the development of effective and implementable ML systems
A Thieme, D Belgrave… – ACM Trans. Comput …, 2020 – designandwellbeing.com
Page 1. 34 Machine Learning in Mental Health: A Systematic Review of the HCI Literature to Support the Development of Effective and Implementable ML Systems ANJA THIEME and DANIELLE BELGRAVE, Microsoft Research GAVIN DOHERTY, Trinity College Dublin …
Designing and evaluating recommender systems with the user in the loop
M Jugovac – 2019 – eldorado.tu-dortmund.de
Page 1. Designing and Evaluating Recommender Systems With the User in the Loop Dissertation zur Erlangung des Grades eines Doktors der Naturwissenschaften der Technischen Universität Dortmund an der Fakultät für Informatik von Michael Jugovac Dortmund 2019 …
Machine Learning in Mental Health: A Systematic Review of the HCI Literature to Support the Development of Effective and Implementable ML Systems
A Thieme, D Belgrave, G Doherty – ACM Transactions on Computer …, 2020 – dl.acm.org
Page 1. 34 Machine Learning in Mental Health: A Systematic Review of the HCI Literature to Support the Development of Effective and Implementable ML Systems ANJA THIEME and DANIELLE BELGRAVE, Microsoft Research GAVIN DOHERTY, Trinity College Dublin …
Evaluation of Methods for Data-Driven Tools that Empower Mental Health Professionals
OA Demasi – 2019 – escholarship.org
… Novice counselors are unable to assume full responsibility for a crisis situation until they have some experience. Some organizations are considering the use of automated interactive agents (chatbots) to replace human counselors …
Artificial Intelligence in Management: Self-learning and Autonomous Systems as Key Drivers of Value Creation
A Wodecki – 2020 – books.google.com
… Lapan, M. (2020), Deep Reinforcement Learning Hands-On: Apply Modern RL Methods to Practical Problems of Chatbots, Robotics, Discrete Optimization, Web Automation, and More, 2nd ed., Birmingham: Packt Publishing …