Freebase & Dialog Systems 2014



See also:

100 Best AI & NLP Resources: RDF | CCG Parsers 2014DBpedia & Dialog SystemsDBpedia & Question Answering Systems 2014 | DeepDive | EntityCubeOpenCyc & Natural Language 2014 | RDFizersWordNet & Dialog Systems 2014 | YAGO-QAYAGO2

Leveraging semantic web search and browse sessions for multi-turn spoken dialog systems L Wang, L Heck, D Hakkani-Tur – Acoustics, Speech and Signal …, 2014 – … 1. Example fragments of a web search and browse session (S1) and a spoken dialog system session (S2). … With the emergence of large scale knowledge resources (eg Freebase, DBPedia), distant supervision has been proposed for re- lation extraction on formal text, such as … Cited by 7 Related articles All 8 versions

Building multimodal dialog user interfaces in the context of the internet of services D Porta, M Deru, S Bergweiler, G Herzog… – Towards the Internet of …, 2014 – Springer … the relevant details of each of the aforementioned eight general development and implementation steps that were conducted to build up the ODP-based multimodal dialog system CIRIUS. … Freebase, Yahoo Weather, and a data service provided by the ALEXANDRIA use case. … Cited by 5 Related articles All 3 versions

Dynamically supporting unexplored domains in conversational interactions by enriching semantics with neural word embeddings YN Chen, A Rudnicky – Spoken Language Technology …, 2014 – … For example, dialogue systems for smart- phone operation fail to respond when users ask for functions not supported by currently … The approach uses structured knowledge resources (eg Freebase, Wikipedia, FrameNet) to induce types of slots for generating semantic seeds … Cited by 3

Knowledge Acquisition Strategies for Goal-Oriented Dialog Systems A Pappu, AI Rudnicky – 15th Annual Meeting of the Special …, 2014 – … ACM, 2010. Kurt Bollacker, Colin Evans, Praveen Paritosh, Tim Sturge, and Jamie Taylor. Freebase: a collaboratively created graph database for structuring human knowledge. … Automatic acquisition of names using speak and spell mode in spo- ken dialogue systems. … Cited by 2 Related articles All 7 versions

Learning Situated Knowledge Bases through Dialog A Pappu, AI Rudnicky – Fifteenth Annual Conference of …, 2014 – … Knowledge bases such as NELL, Freebase, and Wordnet can help in expanding semantic context, thus improve text clas- sification in low … On the other hand, people that might interact with a dialog system pro- viding information access in a domain, can provide knowledge … Cited by 3 Related articles All 5 versions

Leveraging Frame Semantics and Distributional Semantics for Unsupervised Semantic Slot Induction in Spoken Dialogue Systems YN Chen, WY Wang, AI Rudnicky – … use probabilistic frame-semantic parsing to automatically induce and adapt the se- mantic ontology for designing spoken dialogue systems (SDS) in … We utilize continuous word em- beddings trained on very large external corpora (eg Google News and Freebase) to improve the … Cited by 5 Related articles All 3 versions

How domain-general can we be? Learning incremental Dialogue Systems without Dialogue Acts A Eshghi, O Lemon – … There’s also the work of (Kwiatkowski et al., 2013), who map open-domain CCG seman- tic parses to Freebase for question-answering. Here, an open-domain Question-Answering sys- tem (note: not a full dialogue system) is learned by using a wide-coverage CGG parser over … Cited by 1 Related articles

An end-to-end dialog system for TV program discovery D Ramachandran, PZ Yeh, W Jarrold… – … (SLT), 2014 IEEE, 2014 – … We start by giving an overview of the architecture of our end-to-end dialog system for TV program discovery, along with a brief … Recent work [8] uses freely available resources on the web — namely FreeBase relations and Bing result snippets — to generate training data for …

Rapidly scaling dialog systems with interactive learning JD Williams, NB Niraula, P Dasigi, A Lakshmiratan… – … Rapidly scaling dialog systems with interactive learning 7 … The developer added bag-of-n-gram features, specific n-grams like “director”, “movie”, and “who directed”, and also a class con- taining all movies names found in Freebase.2 The effort expended (in minutes) is shown in … Cited by 1 Related articles All 3 versions

Development Environment for a Multimodal Interactive System Based on Ontological Knowledge D Takegoshi, M Araki – Advanced Applied Informatics (IIAIAAI), …, 2014 – … problem, some dialogue systems use ontologies as background knowledge (eg [1], [4]). However, existing ontology-based dialogue systems were implemented … generates SPARQL queries that retrieve the contents of open semantic web resources, such as freebase or DBpedia … Related articles

Tutor Dialogue Planning with Contextual Information and Discourse Structure R Fisher, R Simmons – … Unlike a traditional knowledge base such as NELL [3] and FreeBase [1], a Contextual Knowledge Base includes information relative to the agent’s … A Contextual Knowledge Base is a set of facts about a user and the environ- ment [9]. In dialogue systems, examples of entries in a …

A Flexible Framework for Adaptive Knowledge Retrieval and Fusion for Kiosk Systems and Mobile Clients S Bergweiler – UBICOMM 2014, The Eighth International Conference …, 2014 – … Representational State Transfer (REST)- ful services calls, that binds factual knowledge extracted from Semantic Web Services like Freebase [3] or … principle of input-processing and output (IPO), as depicted in Figure 2. The interaction system (multimodal dialog system with its … Related articles

A Chinese Question Answering System for Specific Domain T Li, Y Hao, X Zhu, X Zhang – Web-Age Information Management, 2014 – Springer … In: TREC, vol. 7, p. 63 (2007) 7. Galibert, O., Illouz, G., Rosset, S.: Ritel: an open-domain, human-computer dialog system. … Association for Computational Linguistics (2010) 9. Berant, J., Chou, A., Frostig, R., Liang, P.: Semantic parsing on freebase from question-answer pairs. … Related articles

Probabilistic enrichment of knowledge graph entities for relation detection in conversational understanding D Hakkani-Tür, A Celikyilmaz… – Proceedings of …, 2014 – … Semantic knowledge graphs, such as Freebase[1], encode fac- tual world knowledge in triples of a pair of entities and their relation, for … movie names and actor names) have been com- monly used for interpretation of natural language user queries in spoken dialog systems [2, 3 … Cited by 9 Related articles All 8 versions

Deriving local relational surface forms from dependency-based entity embeddings for unsupervised spoken language understanding YN Chen, D Hakkani-Tur, G Tur – … Technology Workshop (SLT), …, 2014 – … Traditional spo- ken dialogue systems (SDS) are trained with annotated examples and support limited domains … utilized to obtain domain-related knowledge and help SLU for tackling open domain problems in SDSs [3, 4, 5, 6, 7]. Knowledge graphs, such as Freebase [1], usually … Cited by 3

Resolving referring expressions in conversational dialogs for natural user interfaces A Celikyilmaz, Z Feizollahi… – Proceedings of …, 2014 – … Unlike traditional over-the-phone spo- ken dialog systems (SDSs), user hears and sees the system’s response displayed on the screen as an … First, we obtain the meta information about the on-screen items using Freebase (Bollacker et al., 2008), the knowledge graph that … Cited by 3 Related articles All 5 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 – … New York, NY: John Wiley and Sons, 2011. [2] K. Bollacker, C. Evans, P. Paritosh, T. Sturge, and J. Tay- lor, “Freebase: a collaboratively created graph database … [8] D. Hakkani-Tur and M. Rahim, “Bootstrapping language models for spoken dialog systems from the world wide … Related articles All 9 versions

Personal knowledge graph population from user utterances in conversational understanding X Li, G Tur, D Hakkani-Tur, Q Li – … Technology Workshop (SLT), …, 2014 – … Furthermore, we enhance our data with web search queries which are inquiring similar information as dialog system users. … s, b)}, where includes(x, y) is a binary function that has a value of 1 if string x contains y 2 3 4In this …

A variational Bayesian model for user intent detection Y Ji, D Hakkani-Tur, A Celikyilmaz… – … , Speech and Signal …, 2014 – … clas- sification task, and investigated various classification methods [2, 3, 4, 5, 6, 7, 8]. Intents of spoken queries to a dialog system may be … informational queries can be formed based on the semantic web ontologies [10, 11, 12, 13], such as the ontology of Freebase or schema … Related articles All 4 versions

Deep learning of knowledge graph embeddings for semantic parsing of twitter dialogs L Heck, H Huang – IEEE Global Conference on Signal and …, 2014 – … 96–101. [7] “Freebase,”, 2014. … Rep. MSR-TR-2014-70, 2014. [16] L. Wang, L. Heck, and D. Hakkani-Tür, “Leveraging semantic web search and browse sessions for multi-turn spoken dialog systems,” in Proceedings of the International Conference on … Cited by 2 Related articles All 7 versions

Knowledge Discovery Through Spoken Dialog A Pappu – 2014 – … We propose a robust method for user goal prediction that uses open-domain knowledge bases viz., NELL, Word- net, to expand the semantic context of the user utterance. … 7 a knowledge can potentially improve the task performance of a dialog system. … Cited by 1 Related articles All 2 versions

ISOFT at QALD-4: Semantic similarity-based question answering system over linked data S Park, H Shim, GG Lee – 2014 – … is domain-independent; con- sequently, it can be adapted easily to other KBs such as Yago2 and Freebase. … Research Foundation of Korea (NRF) [NRF-2014R1A2A1A01003041, Development of multi-party antici- patory knowledge-intensive natural language dialog system]. … Cited by 2 Related articles

Swoozy-An Innovative Design of a Distributed and Gesture-based Semantic Television System M Deru, S Bergweiler – … 2014, The Eighth International Conference on …, 2014 – … approach follows the “no presentation without semantic representation” paradigm [40][41][42] in usage in numerous multimodal dialog systems [37]. … the attached Joint Service Engine (JSE), is able to integrate different Web services, like Wikipedia, DBpedia, Freebase, Flickr or … Related articles All 2 versions

Context Awareness and Personalization in Dialogue Planning RWH Fisher – 2014 – … However, such a reinforcement signal is not always easily observable, as such, it may be preferable to use inverse reinforcement learning (also called imitation learning) to train a dialogue system using human demonstration [10]. … Related articles All 2 versions

Interactive service composition and query S Bergweiler – Towards the Internet of Services: The THESEUS …, 2014 – Springer … access to different types of services, such as BBC-Review, DBpedia, Google API (Images, Maps, and Videos), YouTube, Freebase, Yahoo Weather and … The eTFS format is basically the semantic communication standard of the speech and gesture recognizing in dialog systems. … Cited by 4 Related articles All 3 versions

A New Corpus and Imitation Learning Framework for Context-Dependent Semantic Parsing A Vlachos, S Clark – Transactions of the Association for …, 2014 – … As these corpora cover rather narrow application domains, recent work has developed corpora to support natural language in- terfaces to the Freebase database (Cai and Yates, 2013), as well as the development of MT systems (Banarescu et al., 2013). … Related articles All 5 versions

Understanding questions and finding answers: semantic relation annotation to compute the Expected Answer Type V Petukhova – Proceedings 10th Joint ISO-ACL SIGSEM Workshop on …, 2014 – … The system has all components that any traditional dialogue system has: Automatic Speech Recog- nition (ASR) and Speech Generation (eg TTS) modules, and the Dialogue Engine. … nist. gov/pubs/trec8 2http://www. freebase. … Related articles All 3 versions

Dependency Parsing Features for Semantic Parsing W Monroe, Y Wang – … meaning representations is useful for a variety of applica- tions, such as question answering (Clarke et al., 2010), dialogue systems (Artzi and … when a particular type of semantic composition function is used: the bridging functions, which create a relevant Freebase relation “out … Related articles

Entity Ranking for Descriptive Queries K Hong, P Pei, YY Wang, D Hakkani-Tur – … While searching the web or using spoken dialog systems (SDS), of- tentimes people are looking for one or more entities. Structured se- mantic knowledge graphs (eg, Freebase [1]) provide an appropriate resource for responding to such user queries [2, 3] and for bootstrap … Related articles All 3 versions

Learning Phrase Patterns for Text Classification Using a Knowledge Graph and Unlabeled Data A Marin, R Holenstein, R Sarikaya… – … Conference of the …, 2014 – … While sufficient for simpler tasks, such as topic clas- sification, more complex problems like intent classification or slot-filling for dialog systems often require some long-distance context features. … games actor … find … freebase.cvg.cvg_platform 45 230 543 80 … Cited by 1 Related articles All 8 versions

Acquiring Comparative Commonsense Knowledge from the Web N Tandon, G de Melo, G Weikum – Twenty-Eighth AAAI Conference …, 2014 – … in areas like Web Search and Question An- swering, with Freebase forming the core of Google’s Knowl- edge Graph and DBpedia and YAGO being used in IBM’s Jeopardy!-winning Watson system. They also play an im- portant role in intelligent dialog systems like Apple’s Siri … Cited by 1 Related articles All 6 versions

An Introduction to Question Answering over Linked Data C Unger, A Freitas, P Cimiano – Reasoning Web. Reasoning on the Web …, 2014 – Springer … The linked data cloud, consisting of a large amount of interlinked RDF (Resource Description Framework1) datasets, now comprises more than 30 billion RDF triples2. Knowledge bases such as Freebase3 and DBpedia4 are huge and become more and more popular for … Related articles All 4 versions

Summer Internship Report O Kilic – … conversation logs via dialog systems (Artz and Zettlemoyer, 2011), and visual sensors (Matuszek et al … 12 The SEMPRE is available at 13 The FreeBase is available at 14 The CCGBank is available … Related articles

ANA: Automated Nursing Agent K Quinn – 2014 – … A knowledge base is a collection of information describing various entities and their attributes. An example of a knowledge base would be Freebase or Wolfram Alpha. … They provide a dialogue system which displays personal images to a senior. They listen … Related articles All 2 versions

Learning to automatically solve algebra word problems N Kushman, Y Artzi, L Zettlemoyer, R Barzilay – ACL (1), 2014 – … 2013), dialog systems (Artzi and Zettlemoyer, 2011), robot instruction (Chen and Mooney, 2011; Chen, 2012; Kim and Mooney, 2012; Matuszek et al., 2012; Artzi and Zettlemoyer, 2013), and pro- gram executions (Kushman and Barzilay, 2013; Lei et al., 2013). … Cited by 4 Related articles All 11 versions

Bringing machine learning and compositional semantics together P Liang, C Potts – Annual Reviews of Linguistics (submitted), 0, 2014 – Page 1. Bringing machine learning and compositional semantics together Percy Liang and Christopher Potts Abstract Computational semantics has long been seen as a field divided between logical and statistical approaches … Cited by 5 Related articles All 2 versions

Conceptual Dependency Scripts for Business Intelligence V Damjanovic – … Freebase (cf ) and Trueknowledge (cf ) are more recent endeavors to build large-scale … facto-ids), systems enabling reasoning mechanisms, systems that fuse answers from different sources, interactive (dialog) systems, analogical reasoning … Related articles

Domain-sensitive topic management in a modular conversational agent framework D Macias Galindo – 2014 – … Building Modular Knowledge Bases for Conversational Agents. In IJCAI Workshop on Knowledge Representation and Reasoning for Practical Dialogue Systems (KRPDS), pages 16–23, Barcelona, Spain, 2011a (ERA Rank: Unranked) … Related articles All 2 versions

Open Question Answering A Fader – 2014 – … Rewrite 74 million mined operators Execute 1 billion assertions from Freebase, Open IE, Probase, and NELL … simple factoid questions. A common case where this extra functionality is needed includes spoken dialogue systems. For example. modeling a conversation with an … Related articles All 2 versions

Foundations and Trends in Signal Processing L Deng, Y Dong – Signal Processing, 2014 – Page 1. the essence of knowledge FnT SIG 7:3-4 Deep Learning; Methods and Applications Li Deng and Dong Y u Foundations and Trends® in Signal Processing 7:3-4 Deep Learning Methods and Applications Li Deng and Dong Yu now now Page 2. 7.1. … Cited by 1 Related articles All 8 versions

Predictive Spatial Search M Ali, M ABDELTAWAB, M DE COCK, A TEREDESAI – … 1, p. 89, 2005. Page 12. 2014 Specialist Meeting—Spatial Search Conroy Dalton, Krukar—12 [5] H. Cuayáhuitl, N. Dethlefs, K.-F. Richter, T. Tenbrink, and J. Bateman, “A dialogue system for indoor wayfinding using text-based natural language,” Int. J. Comput. Linguist. Appl. … Related articles All 3 versions