Semantic Graph & Dialog Systems

Notes:

Semantic graphs are a type of data structure that is used to represent the meaning of natural language texts. They are composed of nodes and edges that represent concepts or entities and the relationships between them.

In dialog systems, semantic graphs are used to represent the meaning of the user’s input and the system’s response. The graph can be used to identify the key concepts and entities in the user’s input, as well as the relationships between them. This information can then be used to generate an appropriate response from the system, or to determine the next action for the dialog.

One of the main benefits of using semantic graphs in dialog systems is that they can provide a more accurate representation of the user’s intent, which can improve the system’s understanding of the user’s input. Additionally, semantic graphs can be used to provide a more natural and contextually-aware dialog experience, by allowing the system to understand the user’s input in the context of previous interactions.

Another way of using semantic graph in dialog system is to represent the dialog state, and during the dialogue, the system will modify the graph based on the information shared between the user and the system. The graph can be used to track the entities and concepts that were mentioned, and how they are related. The representation of state in a semantic graph can help the system to understand the context and maintain the coherence of the dialogue.

There are various techniques for generating semantic graphs from natural language texts, such as named entity recognition, dependency parsing, and semantic role labeling, which allow to extract the entities, concepts, and relationships from natural language.

Semantic graph builder is a software module or tool that is used to construct a semantic graph from a natural language text. It can use a combination of techniques such as named entity recognition, dependency parsing, and semantic role labeling to extract the entities, concepts, and relationships from the text and represent them in the graph.
Semantic graph builder module is a specific implementation of a semantic graph builder, designed to be integrated into a larger system such as a natural language processing toolkit or a dialog system.
Semantic parsing is the process of converting natural language text into a structured representation that captures the meaning of the text. This representation is often in the form of a semantic graph, but can also be represented using formal languages such as predicate logic or frame-semantic representations.
Syntactic graph, also known as a parse tree, is a tree-like graph representation of the syntactic structure of a sentence. This structure is represented by the relationships between the words and phrases in the sentence and their corresponding parts of speech. The main difference between a semantic graph and a syntactic graph is that the former is focused on the meaning of the text while the latter on the grammatical structure.

Wikipedia:

Semantic Graph Clustering for POMDP-Based Spoken Dialog Systems. F Pinault, F Lefèvre – INTERSPEECH, 2011 – lia.univ-avignon.fr Abstract Dialog managers (DM) in spoken dialogue systems make decisions in highly uncertain conditions, due to errors from the speech recognition and spoken language understanding (SLU) modules. In this work a framework to interface efficient probabilistic … Cited by 7 Related articles All 2 versions

Exploiting the semantic web for unsupervised spoken language understanding L Heck, D Hakkani-Tur – Spoken Language Technology …, 2012 – ieeexplore.ieee.org … systems in an unsupervised manner that cover the knowledge represented in the semantic graph. … very close to the semantic ontologies used in goal-oriented natural dialog systems. … Enriching Semantic Graphs with NL Surface Forms Given the structured knowledge-bases of … Cited by 21 Related articles All 7 versions

Leveraging knowledge graphs for web-scale unsupervised semantic parsing. LP Heck, D Hakkani-Tür, G Tür – INTERSPEECH, 2013 – msr-waypoint.net … Semantic graphs are defined by a schema and composed of nodes and branches connecting the … on relation modeling to target a greater number of the relations of the semantic graph. … and D. Takegoshi, “Framework for the devel- opment of spoken dialogue system based in … Cited by 17 Related articles All 8 versions

Probabilistic enrichment of knowledge graph entities for relation detection in conversational understanding D Hakkani-Tür, A Celikyilmaz… – Proceedings of …, 2014 – mazsola.iit.uni-miskolc.hu … monly used for interpretation of natural language user queries in spoken dialog systems [2, 3, 4]. Entity lists/gazetteers can be formed from triples in semantic graphs, mined from … ambi- guity and investigate three methods for introducing weights to semantic graph entity types … Cited by 9 Related articles All 8 versions

Knowledge Graph Inference For Spoken Dialog Systems Y Ma, PA Crook, R Sarikaya, E Fosler-Lussier – research.microsoft.com … graphs into Markov Random Fields in order to create user goal track- ing models that could form part of a spoken dialog system. … Using a large semantic graph that contains all businesses in Bellevue, WA, extracted from Microsoft Satori, we demon- strate that the proposed …

Analysis And Synthesis Of Goals Of Complex Industrial Systems L Lukyanova – Methods and Instruments of Artificial Intelligence, 2010 – foibg.com … and semantic graphs: ac G, c cGN, c cGK; In24–a graphic man-machine interface based on goal-wordings and semantic graphs: ac G … Conclusion Thus the knowledge-based dialog system of analysis and synthesis of goals allows decision-makers to build a system of goals and … Related articles All 6 versions

Using Semantic and Syntactic Graphs for Call Classification DHTG Tur, A Chotimongkol – ssli.ee.washington.edu … Abstract In this paper, we introduce a new data representation format for language pro- cessing, the syntactic and semantic graphs (SSGs), and show its use for call classifi- cation in spoken dialog systems. For each sentence … Related articles All 2 versions

What is left to be understood in ATIS? G Tur, D Hakkani-Tur, L Heck – Spoken Language Technology …, 2010 – ieeexplore.ieee.org … 14, no. 1, pp. 213–222, 2006. [16] D. Hakkani-Tür, G. Tur, and A. Chotimongkol, “Using syntac- tic and semantic graphs for call classification,” in Proceed- ings … taking a spoken dialog system to the real world,” in Proceedings of the Interspeech, Lisbon, Portugal, September 2005. … Cited by 25 Related articles All 9 versions

Identifying Various Kinds of Event Mentions in K-Parser Output A Sharma, NH Vo, S Aditya, C Baral – public.asu.edu … Similar to K-Parser, TRIPS (Allen et al., 2007) translates text into a semantic graph. … 2007. Deep linguistic processing for spoken dialogue systems. In Proceedings of the Workshop on Deep Linguistic Processing, pages 49– 56. Association for Computational Linguistics. …

Sentence simplification for spoken language understanding G Tur, D Hakkani-Tur, L Heck… – Acoustics, Speech and …, 2011 – ieeexplore.ieee.org … Spoken language understanding (SLU) in human/machine spoken dialog systems aims to automatically identify the intent of the user as … in our previous work we have presented an approach populating heterogeneous features from syn- tactic and semantic graphs of utterances … Cited by 13 Related articles All 10 versions

Rapidly Building Domain-Specific Entity-Centric Language Models Using Semantic Web Knowledge Sources M Akbacak, D Hakkani-Tür, G Tur – Fifteenth Annual Conference of the …, 2014 – 193.6.4.39 … al. used domain-specific entities in the semantic graph [12], and Wang et al. used both [13]. … books). Furthermore, it is a time-consuming and very involved process before one can test-drive a dialog system for the desired domain. … Related articles All 9 versions

A variational Bayesian model for user intent detection Y Ji, D Hakkani-Tur, A Celikyilmaz… – … , Speech and Signal …, 2014 – ieeexplore.ieee.org … In our previous work [15], for each relation type in the semantic graph, we leveraged the … The ontology of user intents for such queries are usually defined by dialog system designers and … logs to discover new user intents in addition to the ones that appear in the semantic graphs. … Related articles All 4 versions

Combining the Best of Two Worlds: NLP and IR for Intranet Search S Adindla, U Kruschwitz – Proceedings of the 2011 IEEE/WIC/ACM …, 2011 – dl.acm.org … Figure 2 shows a screenshot of our dialogue system. Results from the search engine are presented alongside a graph of extracted knowledge related to the query. … Semantic graphs are starting to get used in assisted search, eg in question answering [24]. … Cited by 1 Related articles All 4 versions

Towards Addressing the Winograd Schema Challenge-Building and Using a Semantic Parser and a Knowledge Hunting Module A Sharma, NH Vo, S Aditya, C Baral – public.asu.edu … The semantic graphs are translated into the ASP constructs by using quaternary predicate has … First step is to identify the similar chain of two transitive event nodes from commonsense sentence’s semantic graph by using … Deep linguistic pro- cessing for spoken dialogue systems. …

Personal knowledge graph population from user utterances in conversational understanding X Li, G Tur, D Hakkani-Tur, Q Li – … Technology Workshop (SLT), …, 2014 – ieeexplore.ieee.org … Knowledge en- coded in semantic graphs such as Freebase has been shown to benefit semantic parsing and interpretation of natural language … Get Price Slots: good: gas; cost relative: cheapest; location: (lat,long) Typically, spoken dialog queries to a dialog system may be …

Statistical language generation from semantic structures B Bohnet, S Mille, L Wanner – Proc. of International Conference …, 2011 – researchgate.net … dependency tree (ie, the Penn Treebank annotation) dsi of each sentence xi in the corpus breadth first and examine for each of dsi ‘s nodes n whether (i) it has a correspondence node n in dsi ‘s semantic structure si obtained from the original shallow semantic graph in stages 1 … Cited by 5 Related articles All 5 versions

Simulating human-robot interactions for dialogue strategy learning G Milliez, E Ferreira, M Fiore, R Alami… – Simulation, Modeling, and …, 2014 – Springer … Computer Speech and Language 24(4), 562–588 (2010) 21. Pinault, F., Lef`evre, F.: Unsupervised clustering of probability distributions of semantic graphs for pomdp based spoken dialogue systems with summary space. In: IJCAI 7th KRPDS Workshop (2011) 22. … Cited by 3 Related articles All 18 versions

Policy optimisation of POMDP-based dialogue systems without state space compression M Gašic, M Henderson, B Thomson… – Proceedings of …, 2012 – mi.eng.cam.ac.uk … [16] F Pinault and F Lef`evre, “Semantic graph clustering for POMDP-based spoken dialogue systems,” in Proceedings of Interspeech, 2011. [17] CE Rasmussen and CKI Williams, Gaussian Processes for Ma- chine Learning, MIT Press, Cambridge, Massachusetts, 2005. … Cited by 6 Related articles All 6 versions

One step further towards stochastic semantic sentence generation B Bohnet, S Mille, L Wanner – … Dependency Theory. Frontiers in …, 2013 – books.google.com … B. Bohnet et al./One Step Further Towards Stochastic Semantic Sentence Generation 103 Algorithm 2: Semantic generation //(xi, yi) semantic graph and the deep … models, as [6, 3 and 4]. Walker et al.[8] and Stent et al.[9] describe a trainable sentence planner for dialog systems. … Cited by 2 Related articles All 3 versions

Representing General Relational Knowledge in ConceptNet 5. R Speer, C Havasi – LREC, 2012 – redirect.subscribe.ru … ConceptNet is a knowledge representation project, provid- ing a large semantic graph that describes general human knowledge and how it is expressed in … build a system for analyzing the emotional con- tent of text (Cambria et al., 2010), to create a dialog system for improving … Cited by 49 Related articles All 5 versions

Identification of discriminative features for biological event extraction through linguistically informed feature selection X Zhang, J Xia, J Webster, AC Fang – Journal of Food, Agriculture & …, 2013 – world-food.net … Afterwards, edge detection predicts the edges of this semantic graph to extract event arguments. … based semantic post-processing is introduced to adjust the augment information in semantic graphs. … The authors would like to thank the Dialogue Systems Group at the Department … All 4 versions

Broad coverage multilingual deep sentence generation with a stochastic multi-level realizer B Bohnet, L Wanner, S Mille, A Burga – Proceedings of the 23rd …, 2010 – dl.acm.org … corpora. Each sentence xi of the corpus I, with i = 1,…,I|, is annotated with its dependency tree yi and its shallow semantic graph si. … defined. The Sem- Synt decoder constructs from a semantic graph the corresponding dependency tree. … Cited by 26 Related articles All 10 versions

Expert-based reward shaping and exploration scheme for boosting policy learning of dialogue management E Ferreira, F Lefevre – Automatic Speech Recognition and …, 2013 – ieeexplore.ieee.org … 1. INTRODUCTION Goal-oriented Interactive Systems (such as Spoken or Multimodal Dialogue Systems, SDSs) are designed to help a human to achieve a task. … 108 978-1-4799-2756-2/13/ $31.00 ©2013 IEEE ASRU 2013 Page 2. the initial performance of a dialogue system. … Cited by 2 Related articles

Grammar Representation Forms in Natural Language Interface for Robot Controlling L Kovács, P Barabás – Emergent Trends in Robotics and Intelligent …, 2015 – Springer … AESOP 3000 [8] is a surgical robot which is controlled by voice in heart surgery and does not provide a full dialog system. … The generation of the command text required usually 1-2 seconds, while the location of the corresponding semantic graph took only 0.2 seconds. … Related articles All 3 versions

Users’ Belief Awareness in Reinforcement Learning-based Situated Human-Robot Dialogue Management E Ferreira, G Milliez, F Lefevre, R Alami – uni-ulm.de … In ISRHIC, 2014. 14. F. Pinault and F. Lef`evre. Unsupervised clustering of probability distributions of semantic graphs for pomdp based spoken dialogue systems with summary space. In KRPDS, 2011. 15. N. Roy, J. Pineau, and S. Thrun. … Cited by 1 Related articles

ConceptNet 5: A large semantic network for relational knowledge R Speer, C Havasi – The People’s Web Meets NLP, 2013 – Springer … ConceptNet is a project that creates such a representation of crowd-sourced knowledge, providing a large semantic graph that describes general human … used, for example, to build a system for analyzing the emotional content of text [6], to create a dialog system for improving … Cited by 28 Related articles

Social signal and user adaptation in reinforcement learning-based dialogue management E Ferreira, F Lefèvre – Proceedings of the 2nd Workshop on Machine …, 2013 – dl.acm.org … 1. INTRODUCTION This article focuses on goal-oriented Interactive Systems (such as Spoken or multimodal Dialogue Systems, SDSs). … In goal-oriented dialogue systems, the user act corresponds to the sequence of concepts conveyed by the user to fulfil the task. … Cited by 5 Related articles

Speech Grammars for Textual Entailment Patterns in Multimodal Question Answering. D Sonntag, B Sacaleanu – LREC, 2010 – lrec.elra.info … Joost Geurts, Stefano Bocconi, Jacco Van Ossenbruggen and Lynda Hardman: Towards Ontology-driven Discourse: From Semantic Graphs to Multimedia Presentations … In: Proceedings of the 1st International Workshop on Spoken Dialogue Systems (IWSDS), Kloster Irsee, 2009 … Cited by 1 Related articles All 5 versions

An emotion understanding framework for intelligent agents based on episodic and semantic memories M Kazemifard, N Ghasem-Aghaee, BL Koenig… – Autonomous agents and …, 2014 – Springer … Its semantic memory is a lookup table of emotion-related facts combined with semantic graphs that learn through abstraction of additional relationships among emotions and actions from episodic memory. … Episodic memory Semantic graphs Semantic memory Agent analyzer … Cited by 2 Related articles All 6 versions

Language Learning via Unsupervised Corpus Analysis B Goertzel, C Pennachin, N Geisweiller – Engineering General Intelligence …, 2014 – Springer Page 1. Chapter 27 Language Learning via Unsupervised Corpus Analysis 27.1 Introduction The approach taken to NLP in the OpenCog project up through 2013, in practice, has involved engineering and integrating rule-based …

Improving human–agent communication using linguistic and ontological cues JPA Barthès – International Journal of Electronic Business, 2013 – Inderscience … the contact. The inverse link however bears no semantics. It is a simple means to traverse an arc of the semantic graph in the reverse direction when processing a request. 3.2.3 Attributes Attributes have associated values. All … Cited by 1 Related articles All 4 versions

[BOOK] Applied natural language processing: Identification, investigation, and resolution PM McCarthy, C Boonthum-Denecke – 2012 – igi-global.com Applied Natural Language Processing: Identification, Investigation and Resolution: 9781609607418: Computer Science and Information Technology Books. Cited by 5 Related articles All 2 versions

A semantic and language-based representation of an environmental scene JM Le Yaouanc, É Saux, C Claramunt – Geoinformatica, 2010 – Springer … 5). The semantic graph makes the difference between the node referencing the observer, and the ones that reference spatial entities quoted in the verbal description and represented by the linguistic view. More formally, the … Cited by 10 Related articles All 14 versions

Natural language generation and semantic web technologies N Bouayad-Agha, G Casamayor… – Semantic Web …, 2012 – semantic-web-journal.org … simpler architecture than a generator that takes as input large semantic graphs to generate … Type structured input data representation (eg, semantic graph, database) or unstructured input representation … In Janzen and Maas’s dialogue system [68], NLG starts from a layered OWL … Cited by 3 Related articles All 2 versions

Semantic parsing using word confusion networks with conditional random fields. G Tür, A Deoras, D Hakkani-Tür – INTERSPEECH, 2013 – msr-waypoint.net … Figure 3: Conceptual process of typical spoken dialog systems with cascaded speech recognition and understanding. Figure 4: Typical structures of lattices and WCNs. … [34] D. Hakkani-Tür, G. Tur, and A. Chotimongkol, “Using syntactic and semantic graphs for call classification … Cited by 9 Related articles All 8 versions

Reinforcement-learning based dialogue system for human–robot interactions with socially-inspired rewards E Ferreira, F Lefèvre – Computer Speech & Language, 2015 – Elsevier … Cover image Cover image. Reinforcement-learning based dialogue system for human–robot interactions with socially-inspired rewards ?. …

Dialogue POMDP components (Part II): learning the reward function H Chinaei, B Chaib-Draa – International Journal of Speech Technology, 2014 – Springer … This frame- work has been extensively used to model the uncertainty of SDSs (spoken dialogue systems) (Roy et al. 2000; Zhang et al. 2001a,b; Williams and Young 2007; Thomson 2009; Gašic 2011; Pinault and Lefèvre 2011). … Related articles All 4 versions

Unsupervised clustering of probability distributions of semantic frame graphs for POMDP-based spoken dialogue systems with summary space F Pinault, F Lefevre – … and Reasoning in Practical Dialogue Systems, 2011 – ida.liu.se … graphs and n-best lists are presented, including specific distance definitions. Practical application of the framework and results are finally analysed in Section 5 on a tourist information and hotel booking task. 2 Graphs of semantic frames Dialogue managers in dialogue systems … Cited by 6 Related articles All 2 versions

Multi-Modal Conversational Search and Browse. LP Heck, D Hakkani-Tür, M Chinthakunta… – SLAM@ …, 2013 – msr-waypoint.com … Index Terms: spoken dialog systems, spoken language under- standing, multi-modal fusion, conversational search, conversa- tional browsing. … detection for conversational brows- ing [17], as well as methods to exploit the combination of search logs and semantic graphs [18–21 … Cited by 11 Related articles All 10 versions

Sensee: A Semantic-Based Framework For Integration And Personalization Of Television Related Media P Bellekens, L Aroyo, GJ Houben – st.ewi.tudelft.nl … Thanks to the conversion of data to RDF/OWL in the CRS layer and the enrichments with extra domain ontologies, creating a package basically becomes nothing more than querying our semantic graph and ordering the results. … Related articles

Gaussian processes for POMDP-based dialogue manager optimisation M Ga²i, S Young – 2013 – mi.eng.cam.ac.uk … Various approximations allow such a model to be used for building real-world dialogue systems. … Page 2. Page 3. 1 Introduction Spoken dialogue systems enable human-computer interaction where the primary input is speech. As such they have innumerable benefits. … Related articles

Multilingual joint parsing of syntactic and semantic dependencies with a latent variable model J Henderson, P Merlo, I Titov, G Musillo – Computational Linguistics, 2013 – MIT Press … 2011), dialogue systems (Basili et al. … The problem we need to solve consists of producing a syntactic–semantic graph given an input word string. … Rather, it considers that the syntactic and the semantic graphs are only loosely coupled, and share only the vertices (the words). … Cited by 2 Related articles All 6 versions

Applying Semantic Technology To Business News Analysis I Novalija, D Mladeni? – Applied Artificial Intelligence, 2013 – Taylor & Francis … View all references) presents the user-interactive dialogue system for knowledge acquisition, in which the user is engaged in a natural-language mixed-initiative dialogue. Medelyan and Legg (200833. … 2009 . Question answering based on semantic graphs. … Related articles All 3 versions

Joint Morphological Generation and Syntactic Linearization L Song, Y Zhang, K Song, Q Liu – Twenty-Eighth AAAI …, 2014 – people.sutd.edu.sg … 2010): 1. syntactic generation: generating an unordered and lemma-formed syntactic tree from a semantic graph; 2. syntactic linearization: linearizing the unordered syntactic tree; 3. morphological generation: generating the inflection for each lemma in the string. … Cited by 2 Related articles All 2 versions

Multilinguization and Personalization of NL-based Systems N Hajlaoui, C Boitet – … of the 4th International Workshop on …, 2010 – lexitron.nectec.or.th … It is a kind of semantic graph with a UNL-like syntax (Uchida and Zhu 2005-2006). There are no vari- ables, but the dictionary is used as a type lattice allowing specialization and generalization. … A Natural Language Dialogue System for Impression-based Music-Retrieval. Proc. … Cited by 1 Related articles All 11 versions

Deep stochastic sentence generation S Mille – taln.upf.edu Page 1. Deep stochastic sentence generation Resources and strategies Simon Mille TESI DOCTORAL UPF / 2014 Director de la tesi Prof. Leo Wanner Department of Information and Communication Technologies Page 2. By … Related articles

Deep stochastic sentence generation: resources and strategies S Mille – 2014 – tesisenxarxa.net Page 1. Deep stochastic sentence generation Resources and strategies Simon Mille TESI DOCTORAL UPF / 2014 Director de la tesi Prof. Leo Wanner Department of Information and Communication Technologies Page 2. By … Related articles All 14 versions

Improved models of syntactic-semantic parsing, for English and French. L van der Plas, J Henderson, P Merlo – 2011 – wcms.inf.ed.ac.uk … competitive syntactic performance of [4] is not significantly degraded, we notice an improvement of 3% on the semantic graphs when using … as in time is not identified as a locative, whereas keyword-spotting techniques as those currently used in dialogue systems may produce … Related articles All 2 versions

Natural Language Generation from Graphs NT Dong, LB Holder – International Journal of Semantic Computing, 2014 – World Scientific Page 1. Natural Language Generation from Graphs Ngan T. Dong School of Electrical Engineering and Computer Science Washington State University Pullman, WA 99163, USA takura247@gmail.com Lawrence B. Holder School …

Jointly Modeling Inter-Slot Relations by Random Walk on Knowledge Graphs for Unsupervised Spoken Language Understanding YN Chen, WY Wang, AI Rudnicky – … of the 2015 Conference of the …, 2015 – researchgate.net … 1 Introduction An important requirement for building a success- ful spoken dialogue system (SDS) is to define a co- herent slot set and the corresponding slot-fillers for the spoken language understanding (SLU) compo- nent. … Cited by 1

Automated grammatical error detection for language learners C Leacock, M Chodorow, M Gamon… – Synthesis lectures on …, 2010 – morganclaypool.com … 2010 Spoken Dialogue Systems Kristiina Jokinen and Michael McTear 2009 … The MS-NLP system provides several additional levels of linguistic analysis on the basis of this initial parse, resulting in a logical form semantic graph: 1 … Cited by 106 Related articles All 6 versions

Pomdp-based statistical spoken dialog systems: A review S Young, M Gasic, B Thomson… – Proceedings of the …, 2013 – ieeexplore.ieee.org … Spoken Dialog Systems: A Review … I. INTRODUCTION Spoken dialog systems (SDSs) allow users to interact with a wide variety of information systems using speech as the primary, and often the only, communication medium [1]–[3]. Traditionally, SDSs have been mostly … Cited by 38 Related articles All 7 versions

Linguistic Approach to Information Extraction and Sentiment Analysis on Twitter S Nepal – 2012 – rave.ohiolink.edu Page 1. Page 2. Linguistic Approach to Information Extraction and Sentiment Analysis on Twitter by Srijan Nepal A thesis submitted in partial satisfaction of the requirements for the degree of Master of Science in Computer Science and Engineering in the … Related articles All 3 versions

A semantic model for actions and events in ambient intelligence MJ Santofimia, SE Fahlman, X del Toro, F Moya… – … Applications of Artificial …, 2011 – Elsevier … common practice. The work in Fujii and Suda (2004) describes a promising approach for dynamic service composition, in which the ontological model is represented by means of semantic graphs. The representation technology … Cited by 10 Related articles All 5 versions

Automated grammatical error detection for language learners C Leacock, M Chodorow, M Gamon… – Synthesis lectures on …, 2014 – morganclaypool.com … Semantic Role Labeling Martha Palmer, Daniel Gildea, and Nianwen Xue 2010 Spoken Dialogue Systems Kristiina Jokinen and Michael McTear 2009 Introduction to Chinese Natural Language Processing Kam-Fai Wong, Wenjie Li, Ruifeng Xu, and Zheng-sheng Zhang 2009 … Cited by 12 Related articles All 4 versions

Street-Level Geolocation From Natural Language Descriptions N Blaylock, J Allen, W de Beaumont, L Galescu, H Jung – Citeseer … is done by the TRIPS Parser system (Allen et al., 2008), which is the language understanding component of the TRIPS dialog system (Jung et … This component uses hand-built, semantic graph matching rules for SQWRL (O’Connor and Das, 2009) to find the subgraphs of the LF … Related articles All 6 versions

Generating tailored, comparative descriptions with contextually appropriate intonation M White, RAJ Clark, JD Moore – Computational Linguistics, 2010 – MIT Press … RYANAIR)rheme. related to Kruijff-Korbayová et al.’s (2003) use of theme phrases to link utterances with questions under discussion (Ginzburg 1996; Roberts 1996) in an information-state based dialogue system. An interesting … Cited by 16 Related articles All 15 versions

Learning Organized Knowledge for Unsupervised Spoken Language Understanding YNV Chen – 2015 – cs.cmu.edu … intention. However, spoken dialogue systems typically use manually predefined semantic elements to parse users’ utterances into unified semantic representations. … xi Page 18. xii Page 19. 1Introduction 1.1 Spoken Dialogue System A …

A Graph-Based Approach to String Regeneration M Horvat, W Byrne – 2013 – cl.cam.ac.uk … Other systems that generate text, such as abstract-like text Summarisation systems, Question Answering sys- tems, and Dialogue Systems, suffer from the same problem (Soricut and Marcu, 2005). The string regeneration problem is therefore often used as … Cited by 2 Related articles All 8 versions

Semi-supervised and unsupervised data extraction targeting speakers: From speaker roles to fame? C Lailler, G Dupuy, M Rouvier, S Meignier – In Proc. of SLAM, 2013 – Citeseer Page 78. Semi-Supervised and Unsupervised Data Extraction Targeting Speakers: From Speaker Roles to Fame? Carole Lailler, Grégor Dupuy, Mickael Rouvier, Sylvain Meignier LUNAM Université, LIUM, Le Mans, France first. lastname@ lium. univ-lemans. … Cited by 1 Related articles All 5 versions

Innovation Engine for Blog Spaces A Lorincz – 2011 – DTIC Document Page 1. AFRL-AFOSR-UK-TR-2011-0040 Innovation Engine for Blog Spaces Andras Lorincz Neumann János Számítógép-tudományi Társaság Eotvos Lorand University Department of Information Systems Pazmany Peter setany 1/C Budapest, Hungary H-1117 … Cited by 1 Related articles

Intra-lingual and Cross-lingual Prosody Modelling GK Anumanchipalli – 2013 – cs.cmu.edu Page 1. Intra-Lingual and Cross-Lingual Prosody Modelling Gopala Krishna Anumanchipalli CMU-LTI-13-009 Language Technologies Institute Departamento de Engenharia School of Computer Science Electrotécnica e de Computadores Carnegie Mellon University … Cited by 1 Related articles All 11 versions

Joint models for concept-to-text generation I Konstas – 2014 – era.lib.ed.ac.uk … of anaphoric expressions in subsequent references to them, later in the text. This is more common in the NLG part of dialogue systems, which need to keep track of what has been mentioned in each dialogue turn and update their state accordingly. Even in … Related articles All 4 versions

Revisiting User Simulation in Dialogue Systems. Do we still need them? Will imitation play the role of simulation? S Chandramohan – 2012 – metz.supelec.fr Page 1. Revisiting User Simulation in Dialogue Systems. Do we still need them? Will imitation play the role of simulation? … 9 Page 25. 10 Page 26. Chapter 2 Spoken Dialogue Systems Human Computer Interaction (HCI) is a field of study which focuses on designing … Related articles All 11 versions

[BOOK] Text Genres and Registers: The Computation of Linguistic Features CA Fang, J Cao – 2015 – books.google.com … 31541110215). The au- thors would also like to acknowledge supports received from the Dialogue Systems Group, Department of Linguistics and Translation, and the Halliday Centre for In- telligent Applications of Language Studies, City University of Hong Kong. …

Domain-And Language-Adaptive Natural Language Controlling Framework P Barabás – 2013 – iit.uni-miskolc.hu … My goal is to define and implement a natural language controlling framework using frame- based dialog system which can be applied for robot … This kind of semantic graph is widely used in computational linguistics where the verb is a central concept in the graph describing the … Related articles All 2 versions

[BOOK] New perspectives on computational and cognitive strategies for word sense disambiguation O Kwong – 2012 – books.google.com … Some of the topics covered in this series include the presentation of real life commercial deployment of spoken dialog systems, contemporary methods of speech parameterization, developments in information security for automated speech, forensic speaker recognition, use … Related articles All 7 versions

SpringerBriefs in Electrical and Computer Engineering A Neustein – Springer … Some of the topics covered in this series include the presentation of real life commercial deployment of spoken dialog systems, contemporary methods of speech parameterization, developments in information security for automated speech, forensic speaker recognition, use … Related articles All 2 versions