LEADER 04316nam 22005175 450 001 9910337849403321 005 20200701172927.0 010 $a3-030-04299-5 024 7 $a10.1007/978-3-030-04299-8 035 $a(CKB)4100000007881186 035 $a(MiAaPQ)EBC5747381 035 $a(DE-He213)978-3-030-04299-8 035 $a(PPN)235670812 035 $a(EXLCZ)994100000007881186 100 $a20190404d2019 u| 0 101 0 $aeng 135 $aurcnu|||||||| 181 $ctxt$2rdacontent 182 $cc$2rdamedia 183 $acr$2rdacarrier 200 10$aDeveloping Enterprise Chatbots $eLearning Linguistic Structures /$fby Boris Galitsky 205 $a1st ed. 2019. 210 1$aCham :$cSpringer International Publishing :$cImprint: Springer,$d2019. 215 $a1 online resource (566 pages) 311 $a3-030-04298-7 327 $aIntroduction to Chatbots -- Social Chatbots and Development Platforms -- Chatbot Components and Architectures -- Providing Natural Language Access to a Database -- Chatbot Relevance at Syntactic Level -- Semantic Skeleton-based Search for Question and Answering Chatbots -- Relevance at the Level of Paragraph: Parse Thickets -- Chatbot Thesauri -- Content Processing Pipeline -- Achieving Rhetoric Agreement in a Conversation -- Discourse-level Dialogue Management,- Chatbots Providing and Accepting Argumentation. . 330 $aA chatbot is expected to be capable of supporting a cohesive and coherent conversation and be knowledgeable, which makes it one of the most complex intelligent systems being designed nowadays. Designers have to learn to combine intuitive, explainable language understanding and reasoning approaches with high-performance statistical and deep learning technologies. Today, there are two popular paradigms for chatbot construction: 1. Build a bot platform with universal NLP and ML capabilities so that a bot developer for a particular enterprise, not being an expert, can populate it with training data; 2. Accumulate a huge set of training dialogue data, feed it to a deep learning network and expect the trained chatbot to automatically learn ?how to chat?. Although these two approaches are reported to imitate some intelligent dialogues, both of them are unsuitable for enterprise chatbots, being unreliable and too brittle. The latter approach is based on a belief that some learning miracle will happen and a chatbot will start functioning without a thorough feature and domain engineering by an expert and interpretable dialogue management algorithms. Enterprise high-performance chatbots with extensive domain knowledge require a mix of statistical, inductive, deep machine learning and learning from the web, syntactic, semantic and discourse NLP, ontology-based reasoning and a state machine to control a dialogue. This book will provide a comprehensive source of algorithms and architectures for building chatbots for various domains based on the recent trends in computational linguistics and machine learning. The foci of this book are applications of discourse analysis in text relevant assessment, dialogue management and content generation, which help to overcome the limitations of platform-based and data driven-based approaches. Supplementary material and code is available at https://github.com/bgalitsky/relevance-based-on-parse-trees. 606 $aArtificial intelligence 606 $aComputational linguistics 606 $aSoftware engineering 606 $aArtificial Intelligence$3https://scigraph.springernature.com/ontologies/product-market-codes/I21000 606 $aComputational Linguistics$3https://scigraph.springernature.com/ontologies/product-market-codes/N22000 606 $aSoftware Engineering$3https://scigraph.springernature.com/ontologies/product-market-codes/I14029 615 0$aArtificial intelligence. 615 0$aComputational linguistics. 615 0$aSoftware engineering. 615 14$aArtificial Intelligence. 615 24$aComputational Linguistics. 615 24$aSoftware Engineering. 676 $a006.3 676 $a006.35 700 $aGalitsky$b Boris$4aut$4http://id.loc.gov/vocabulary/relators/aut$0860187 906 $aBOOK 912 $a9910337849403321 996 $aDeveloping Enterprise Chatbots$92513499 997 $aUNINA LEADER 01309nam0 22003253i 450 001 PUV0551133 005 20251003044314.0 010 $a0044450923 100 $a20210317d1988 ||||0itac50 ba 101 | $aeng 102 $agb 181 1$6z01$ai $bxxxe 182 1$6z01$an 183 1$6z01$anc$2RDAcarrier 200 1 $aCost-benefit analysis$ean informal introduction$fby E. J. Mishan 205 $a4. ed 210 $aLondon$cUnwin Hyman$d1988 215 $aXXX, 461 p.$d22 cm. 700 1$aMishan$b, Edward J.$3SBLV184979$4070$024593 790 1$aMishan$b, Ezra J.$3MILV201051$zMishan, Edward J. 790 1$aMishan$b, E. J.$3MILV201052$zMishan, Edward J. 790 1$aMishan$b, Edward Joshua$3UTOV565479$zMishan, Edward J. 801 3$aIT$bIT-000000$c20210317 850 $aIT-BN0095 901 $bNAP 01$cPOZZO LIB.$nVi sono collocati fondi di economia, periodici di ingegneria e scienze, periodici di economia e statistica e altri fondi comprendenti documenti di economia pervenuti in dono. 912 $aPUV0551133 950 0$aBiblioteca Centralizzata di Ateneo$c1 v.$d 01POZZO LIB.ECON MON 4129$e 0101 0000121215E VMA 1 v.$fB $h20210317$i20210317 977 $a 01 996 $aCost-benefit analysis$928376 997 $aUNISANNIO