Notes:
A probabilistic context-free grammar (PCFG) is a formal grammar that is used to describe the structure and syntax of a language, and that assigns probabilities or weights to the various rules and productions in the grammar. A PCFG is a type of context-free grammar (CFG), which is a formal grammar that is characterized by its ability to describe the syntax of a language using a set of rules that are independent of context.
A stochastic context-free grammar (SCFG) is another term that is sometimes used to refer to a PCFG. A PCFG or SCFG is called “probabilistic” or “stochastic” because it assigns probabilities or weights to the various rules and productions in the grammar, which reflects the likelihood that these rules will be used in the generation of a sentence.
PCFGs or SCFGs are used in a variety of applications, including natural language processing, machine learning, and linguistics. They can be used to analyze the structure and syntax of natural language text, to generate new sentences or phrases that follow the rules of the grammar, and to help systems understand and interpret the meaning of natural language input.
Probabilistic context-free grammars (PCFGs) and stochastic context-free grammars (SCFGs) are formalisms that can be used to represent and generate language in a systematic and structured way. In a dialog system, they can be used to generate natural language responses based on a given context or prompt.
One way that PCFGs and SCFGs can be used in dialog systems is to define a set of rules that describe the structure and content of the responses that the system should generate. These rules can be used to parse input sentences and generate appropriate responses, taking into account the context of the conversation and the goals of the system.
For example, a PCFG or SCFG for a customer service chatbot might include rules for generating responses to common questions, such as inquiries about shipping times or product availability. The grammar could also include rules for handling more complex queries or requests, such as requests for price comparisons or personalized product recommendations.
PCFGs and SCFGs can also be used in combination with other techniques, such as machine learning, to improve the accuracy and flexibility of the dialog system. For example, a dialog system might use a PCFG or SCFG to generate a set of candidate responses, and then use machine learning to select the most appropriate response based on the context of the conversation.
Wikipedia:
See also:
CFG (Context-free Grammar) Parsers | PLSA (Probabilistic Latent Semantic Analysis) & Dialog Systems | Probabilistic Consistency Engine (PCE) | Probabilistic Graphical Models & Dialog Systems
Two-Layer Semantic Entity Detection and Utterance Validation for Spoken Dialogue Systems A Chýlek, J Švec, L Šmídl – Text, Speech and Dialogue, 2014 – Springer … The expert knowledge is represented as in many current commercial dialogue system by probabilistic context free grammars (PCFGs) which are used for both speech recognition and understanding. The developer of PCFG grammar does not need to be a dialogue system … Related articles All 3 versions
Modeling user behavior online for disambiguating user input in a spoken dialogue system F Wang, K Swegles – Speech Communication, 2013 – Elsevier … A spoken dialogue system (SDS) is a computer system that interacts with its human user in … forms of acoustic models, N-gram models, Probabilistic Context Free Grammars (PCFGs), and so … In syntactic analysis, the Probabilistic Context-Free Grammar (PCFG) is one of the most … Cited by 2 Related articles All 3 versions
Optimising incremental dialogue decisions using information density for interactive systems N Dethlefs, H Hastie, V Rieser, O Lemon – Proceedings of the 2012 Joint …, 2012 – dl.acm.org … An important decision for a dialogue system is then when to generate a backchannel? … We simulate ID of user utterances based on proba- bilistic context-free grammars (PCFG) that were au … We use these PCFGs to simulate user utterances to which the sys- tem has to react. … Cited by 14 Related articles All 9 versions
Concept-to-text generation via discriminative reranking I Konstas, M Lapata – Proceedings of the 50th Annual Meeting of the …, 2012 – dl.acm.org … Specifically, we define a probabilistic context-free grammar (PCFG) that captures the structure of the … approach, we could first learn the weights of the PCFG by maximising the … discriminative approaches to text generation were introduced in spoken dialogue systems, and usually … Cited by 21 Related articles All 6 versions
tucSage: Grammar Rule Induction for Spoken Dialogue Systems via Probabilistic Candidate Selection A Chorianopoulou, G Athanasopoulou, E Iosif… – SemEval 2014, 2014 – aclweb.org … 1 Introduction A critical task for Spoken Dialogue Systems (SDS) is the understanding of the transcribed user input, that utilizes an underlying domain grammar. … The estimation of stochastic context-free grammars using the inside- outside algorithm. … Related articles All 7 versions
A combined method based on stochastic and linguistic paradigm for the understanding of arabic spontaneous utterances C Lhioui, A Zouaghi, M Zrigui – Computational Linguistics and Intelligent …, 2013 – Springer … In fact, the automatic SLU is an essential step in Oral Dialogue Systems. It consists of extracting the meaning of utterances that are in the most of time ambiguous and uncertain. … q ? ? . : X Having defined PCFGs, we derive a PCFG from a corpus. … Cited by 1 Related articles All 3 versions
Using syntactic and confusion network structure for out-of-vocabulary word detection. A Marin, T Kwiatkowski, M Ostendorf, LS Zettlemoyer – SLT, 2012 – wiki.inf.ed.ac.uk … tactic non-terminal OOV via a Markov process integrated into the PCFG parser using … We renormalize all the rule probabilities to give a generative probabilistic context- free grammar, GS. … al., “Semantic processing of out-of-vocabulary words in a spoken dialogue system,” in Proc. … Cited by 5 Related articles All 6 versions
Spoken dialogue system design in 3 weeks T Valenta, J Švec, L Šmídl – Text, Speech and Dialogue, 2012 – Springer … such a dialogue system. The final implementation was written in dynamically generated VoiceXML. The large vocabulary continuous speech recognition sys- tem was used and the language understanding module was implemented using non-recursive probabilistic context free … Cited by 4 Related articles All 4 versions
“Can you give me another word for hyperbaric?”: Improving speech translation using targeted clarification questions NF Ayan, A Mandal, M Frandsen… – … , Speech and Signal …, 2013 – ieeexplore.ieee.org … of natural spoken language have a significant negative impact on the overall per- formance of existing dialog systems. … word posteriors; (2) Choose the best path through the WCN allowing OOV spans, using a probabilistic context free grammar (PCFG) parser modified … Cited by 5 Related articles All 9 versions
On the Use of Phoneme Lattices in Spoken Language Understanding J Švec, L Šmídl – Text, Speech, and Dialogue, 2013 – Springer … In this paper, we will focus on the spoken language understanding (SLU) task in the spoken dialogue systems. … The output layer then predicts lexicalized probabilities. The probabilities are used to parameterize the generalized probabilistic context-free grammar (PCFG). … Cited by 1 Related articles All 2 versions
Integration of complex language models in ASR and LU systems R Justo, MI Torres – Pattern Analysis and Applications, 2014 – Springer … Spe- cifically, n-gram models [15] are the most popular approach. Other approaches, such as syntactic LMs including a stochastic component, could also be employed in this kind of applications, ie, stochastic context-free grammars (SCFG) [3, 18]. … Related articles
Stochastic Language Generation in Dialogue Using Factored Language Models F Mairesse, S Young – 2014 – MIT Press … evaluate the generalization performance of synchronous context-free grammars in a dialogue system domain. … content selection and surface realization by training a forest of PCFGs expressing the … to find the optimal derivations at generation time; however, the PCFG weights are … Related articles All 9 versions
Fusion of knowledge-based and data-driven approaches to grammar induction S Georgiladakis, C Unger, E Iosif… – … Conference of the …, 2014 – mazsola.iit.uni-miskolc.hu … [4] A. Flycht-Eriksson, “Design and use of ontologies in information-providing dialogue systems,” Ph.D. disserta- tion, School of Engineering, Linköping University, 2004. … [13] JM Benedi and JA Snchez, “Combination of n-grams and stochastic context-free grammars for language … Related articles All 7 versions
The evaluation of spoken dialog management models for multimodal HCIs. R Maskeliunas – Int. Arab J. Inf. Technol., 2014 – ccis2k.org … 93-103, 1997. [6] Hacioglu K. and Ward W., “Dialog-Context Dependent Language Modeling Combining n- Grams and Stochastic Context-Free Grammars,” in … 163-200, 1987. [10] Marque F., Bennacef S., Neel F., and Trinh S.‚ “PAROLE: A Vocal Dialogue System for Air Traffic … Related articles All 4 versions
Contextual word spotting in historical manuscripts using markov logic networks D Fernández, S Marinai, J Lladós… – Proceedings of the 2nd …, 2013 – dl.acm.org … of expectations of a dialogue system to perform semantic processing in a spoken Dialogue System. … context-free grammar (SCFG, or probabilis- tic context-free grammar, PCFG) is a … to identify the most probable parse of a sentence given a probabilistic context-free grammar (CFG … Cited by 6 Related articles All 5 versions
Using a knowledge graph and query click logs for unsupervised learning of relation detection D Hakkani-Tur, L Heck, G Tur – Acoustics, Speech and Signal …, 2013 – ieeexplore.ieee.org … Furthermore, we enhance our data with web search queries which are inquiring similar information as dialog system users. 3.1. Relation Detection … [15] S. Petrov and D. Klein, “Learning and inference for hierarchi- cally split PCFGs,” in Proceedings of the AAAI, 2007. … Cited by 10 Related articles All 8 versions
Hierarchical discriminative model for spoken language understanding J Svec, L Smídl, P Ircing – Acoustics, Speech and Signal …, 2013 – ieeexplore.ieee.org … the whole dialog could consist of many misunder- standings and the dialog system would be … statistical parser introduced in [1]. It is based on the lexicalized PCFG with rule … HDM output layer uses a semantic grammar similar to lexi- calized probabilistic context-free grammars. … Cited by 6 Related articles
Situated Incremental Natural Language Understanding using a Multimodal, Linguistically-driven Update Model C Kennington, S Kousidis, D Schlangen – Proceedings of the 25th …, 2014 – aclweb.org … The final, bolded NLU frame in Figure 1 shows the addressee (in this case, the dialogue system) as the recip- ient of the request, the … 1 We use the German RMRS parser described in Peldszus et al (2012), Peldszus and Schlangen (2012) which is a top-down PCFG parser that … Related articles All 4 versions
Semantic entity detection from multiple ASR hypotheses within the WFST framework J Svec, P Ircing, L Smídl – Automatic Speech Recognition and …, 2013 – ieeexplore.ieee.org … In current commercial dialog systems, it is common to repre- sent the expert knowledge with probabilistic context free grammars (PCFGs) which are used both for speech recognition and understand- ing. The PCFG framework is also relatively simple to use – the developer of … Cited by 3 Related articles
Hmi Modelling for Multimodal Lithuanian Applications R Maskeliunas, K Ratkevicius – Information Technology And Control, 2012 – eejournal.ktu.lt … [8] K. Hacioglu, W. Ward. Dialog-context dep endent language modeling combining n-grams and stochastic context-free grammars. … Cooperation in Dialogue and Discourse Structure. IJCAI workshop on Collaboration, Cooperation and Conflict in Dialogue Systems, 1997, 33-39. … Related articles All 21 versions
Incremental grammar induction from child-directed dialogue utterances A Eshghi, J Hough, M Purver – CMCL 2013, 2013 – anthology.aclweb.org … incremental, probabilistic gram- mar for parsing and production, suitable for use in state-of-the-art incremental dialogue systems (Purver et … LHS category can be estimated, producing a gram- mar suitable for probabilistic parsing and disam- biguation eg a PCFG (Charniak, 1996 … Cited by 4 Related articles All 11 versions
Context Awareness and Personalization in Dialogue Planning RWH Fisher – 2014 – cs.cmu.edu … 4.1 Semantic Features One critical component in dialogue systems is semantic understanding of unstructured user input. … The Stanford Parser Probabilistic Context-Free Grammar (PCFG) suite is used to extract syn- tactic information from the input sentence[38]. … Related articles All 2 versions
Robust Algorithms for Semantic Class Labeling in Chinese Query Understanding? Y LI, Y YAN – Journal of Computational Information Systems, 2014 – jofcis.com … With the improvement of Automatic Speech Recognition (ASR), the technology of spoken dialog systems (SDS) has developed … include hidden Markov model (HMM), ie AT&T’s CHRONUS [3]; model based on Probabilistic Context-Free Grammar (PCFG), ie BBN’s … Related articles
A global model for concept-to-text generation I Konstas, M Lapata – Journal of Artificial Intelligence Research, 2013 – dl.acm.org … Rather than breaking up the generation process into a sequence of local decisions, we define a probabilistic context-free grammar that globally describes the … Trainable approaches to surface natural language generation and their application to conversational dialog systems. … Cited by 1 Related articles
Exploiting the semantic web for unsupervised spoken language understanding L Heck, D Hakkani-Tur – Spoken Language Technology …, 2012 – ieeexplore.ieee.org … literature is beyond the scope of this paper, it is clear that these kinds semantic ontologies are very close to the semantic ontologies used in goal-oriented natural dialog systems. … [13] S. Petrov and D. Klein, “Learning and inference for hierarchically split PCFGs,” in Proceedings … Cited by 17 Related articles All 7 versions
A Complete Bibliography of ACM Transactions on Speech and Language Processing (TSLP) NHF Beebe – 2014 – tug.ctan.org … Constant:2013:CCR [CLS13a] Matthieu Constant, Joseph Le Roux, and Anthony Sigogne. Combining compound recogni- tion and PCFG–LA parsing with word lattices and condi- tional random fields. … Evaluating dis- course understanding in spoken dialogue systems. … Related articles All 10 versions
Robust kaomoji detection in Twitter S Bedrick, R Beckley, B Roark, R Sproat – Proceedings of the Second …, 2012 – dl.acm.org … (2003) presented a natural language dialogue system that learned a … We perform a separate PCFG induction for ev- ery candidate emoticon sequence, based on a small set of … By inducing small, example-specific PCFGs, we ensure that every example has a valid parse, without … Cited by 5 Related articles All 6 versions
Fuzzy Matching of Semantic Class in Chinese Spoken Language Understanding LI Yanling, Z Qingwei… – IEICE TRANSACTIONS on …, 2013 – search.ieice.org … Thus, the performance of spoken dialog systems not only relies on the accuracy of recognition achieved by ASR … driven approaches include hidden Markov model (HMM), ie AT&T’s CHRONUS[5]; model based on Probabilistic Context-Free Grammar (PCFG), ie BBN’s … Cited by 1 Related articles All 5 versions
Joint satisfaction of syntactic and pragmatic constraints improves incremental spoken language understanding A Peldszus, T Baumann, O Buß… – Proceedings of the 13th …, 2012 – dl.acm.org … and its ac- companying logical form) as a combination of a syntactic probability (as in a typical PCFG) and a … semantic construction and reference resolution modules are implemented within the InproTK toolkit for incremental spoken dialogue systems development (Schlangen et … Cited by 10 Related articles All 12 versions
Object Recognition Using Dialogues And Semantic Anchoring VK Bandaru, B Rajasekaran – 2013 – diva-portal.se … Figure 4.1 Framework 4.1 Dialogue system … Stanford’s Parser[22] package is a Java implementation of probabilistic natural language parsers, both highly optimized PCFG and lexicalized dependency parsers, and a lexicalized PCFG parser. … Related articles All 3 versions
Using a serious game to collect a child learner speech corpus C Baur, E Rayner, N Tsourakis – 2014 – archive-ouverte.unige.ch … The Nuance Toolkit performs two more compila- tion steps, first using the example corpus to add probabilis- tic weights to the CFG form, and then converting the result- ing PCFG grammar into a … Real user evalua- tion of spoken dialogue systems using Amazon Mechan- ical Turk … Cited by 3 Related articles All 2 versions
Deriving local relational surface forms from dependency-based entity embeddings for unsupervised spoken language understanding YN Chen, D Hakkani-Tür, G Tur – Proceedings of SLT, 2014 – researchgate.net … 1. INTRODUCTION Spoken language understanding (SLU) aims to detect the semantic frames that include domain-related information. Traditional spo- ken dialogue systems (SDS) are trained with annotated examples and support limited domains. …
Adapting dependency parsing to spontaneous speech for open domain spoken language understanding F Bechet, A Nasr, B Favre – Fifteenth Annual Conference …, 2014 – mazsola.iit.uni-miskolc.hu … 85–88. [8] Y.-N. Chen, WY Wang, and AI Rudnicky, “Unsuper- vised induction and filling of semantic slots for spoken dialogue systems using frame … 40, no. 1, pp. 9–56, 2014. [10] S. Petrov and D. Klein, “Learning and inference for hierar- chically split pcfgs,” in Proccedings of the … Related articles All 7 versions
Inducing Document Plans for Concept-to-Text Generation. I Konstas, M Lapata – EMNLP, 2013 – anthology.aclweb.org … The input to our model is a set of database records and collocated descriptions, exam- ples of which are shown in Figure 1. Given this input, we define a probabilistic context-free grammar (PCFG) that captures the structure of the database and how it can be verbal- ized. … Cited by 1 Related articles All 3 versions
Incremental derivations in CCG V Demberg – Proceedings of the 11th International Workshop on …, 2012 – alpage.inria.fr … Dialogue systems which interact with the user in real time have been shown to exhibit more natu- ral behaviour when they process the … Full connectedness has been implemented with other grammar formalisms: for fully connected PCFG parsing, a top-down (Roark, 2001) or left … Cited by 2 Related articles
Learning to map sentences to logical form: Structured classification with probabilistic categorial grammars LS Zettlemoyer, M Collins – arXiv preprint arXiv:1207.1420, 2012 – arxiv.org … all logical forms L and the hidden syntax T is marginalized out by summing over all parses that produce L. We use dynamic programming al- gorithms for this step, which are very similar to CKY–style algorithms for parsing probabilistic context-free grammars (PCFGs).2 Dynamic … Cited by 291 Related articles All 28 versions
Probabilistic grammar induction in an incremental semantic framework A Eshghi, M Purver, J Hough, Y Sato – Constraint Solving and Language …, 2013 – Springer … semantic logical forms (LFs), the ability to automatically induce DS grammars could lead to a novel and useful resource for dialogue systems. … coupled with statistical esti- mation of the probabilities for production rules that share the same LHS category (eg PCFGs [7]). However … Related articles All 6 versions
Syntactic surprisal affects spoken word duration in conversational contexts V Demberg, AB Sayeed, PJ Gorinski… – Proceedings of the …, 2012 – dl.acm.org … Using linear mixed-effects modeling, we found that syntactic surprisal as calculated from a top- down incremental PCFG parser accounts for a … Spoken dialogue systems are of increasing eco- nomic and technological importance in recent times, particularly as it is now feasible to … Cited by 5 Related articles All 8 versions
Cross-Language Phrase Boundary Detection VS Martinez, EL Cooper, A Rosenberg… – 2013 – academiccommons.columbia.edu … and for distinguishing between given and new information in speech summarization, identifying turn-taking behavior and dialogue acts in spoken dialogue systems [1, 2, 3, 4 … [1] Zhongqiang Huang and Mary Harper, “Appropriately handled prosodic breaks help pcfg parsing,” in … Related articles
Cross-language phrase boundary detection V Soto, E Cooper, A Rosenberg… – Acoustics, Speech and …, 2013 – ieeexplore.ieee.org … and for distinguishing between given and new information in speech summarization, identifying turn-taking behavior and dialogue acts in spoken dialogue systems [1, 2, 3, 4 … [1] Zhongqiang Huang and Mary Harper, “Appropriately handled prosodic breaks help pcfg parsing,” in … Cited by 3 Related articles All 7 versions
Better Surface Realization through Psycholinguistics R Rajkumar, M White – Language and Linguistics Compass, 2014 – Wiley Online Library … 2013), thereby making them more suitable for integration into real-time incremental dialog systems (Schlangen and Skantze 2011; Dethlefs et al. 2013). … 3.2 INCREMENTAL GRAMMAR FORMALISMS FOR DIALOG SYSTEMS. … Related articles
A computational linguistic approach to natural language processing with applications to garden path sentences analysis J DU, P YU – cognitive science, 2012 – Citeseer … linguistic knowledge [12-17]. There are a lot of helpful NLP models for linguistic research focusing on various application areas, eg Zhou & Hripcsak’medical NLP model and Plant& Murrell’s dialogue system. Figure 1 Zhou & … Cited by 1 Related articles All 6 versions
Joint Parsing and Disfluency Detection in Linear Time. MS Rasooli, JR Tetreault – EMNLP, 2013 – aclweb.org … Lease and Johnson (2006) use a PCFG-based parser to parse sentences along with finding edited phrases. … Such a parser is useful for spoken dialogue systems which typically encounter disfluent speech and require accurate syntactic structures. … Cited by 3 Related articles All 5 versions
A task-performance evaluation of referring expressions in situated collaborative task dialogues P Spanger, R Iida, T Tokunaga, A Terai… – Language resources and …, 2013 – Springer Page 1. ORIGINAL PAPER A task-performance evaluation of referring expressions in situated collaborative task dialogues Philipp Spanger • Ryu Iida • Takenobu Tokunaga • Asuka Terai • Naoko Kuriyama Published online: 21 … Cited by 1 Related articles All 4 versions
A System for Recognizing Natural Spelling of English Words L Czech, A Waibel, S Stüker, DIT Köhler – Links, 2014 – isl.anthropomatik.kit.edu … plenty of use cases for such a system, including out-of-vocabulary learning, error recovery and dialog systems, for example in … This work uses formal languages and grammars like context-free grammars (CFG) and probabilistic context-free grammars (PCFG) for many … Related articles All 2 versions
Toward Semantic Machine Translation J Andreas – 2012 – academiccommons.columbia.edu … by an SCFG. As mentioned in the introduction, we would also like a unified model of … who learn a Markov logic network in order to induce semantic forms [PD09]; Artzi et al.’s semantic parser bootstrapped from transcripts of interactions with a dialog system [AZ11]; … Related articles
Biocomputing: an insight from linguistics G Bel-Enguix, MD Jiménez-López – Natural Computing, 2012 – Springer … 2. Stochastic context-free grammars for modeling RNA (Sakakibara et al. 1994). … A topic where context and interaction among agents is essential is the field of dialogue modeling and its applications to the design of effective and user-friendly computer dialogue systems. … Related articles All 7 versions
A Statistical Model of Error Correction for Computer Assisted Language Learning Systems H Basiron – 2012 – otago.ourarchive.ac.nz … NICT JLE The National Institute of Information and Communications Technology Japanese Learner English, page 73 NLP Natural Language Processing, page 5 PCFG Probabilistic Context Free Grammar, page 50 xiv Page 15. POS Part-Of-Speech, page 50 … Related articles All 2 versions
HFST—a system for creating NLP tools K Lindén, E Axelson, S Drobac, S Hardwick… – … and Frameworks for …, 2013 – Springer … the noun “sviitti”. 2.3 Language Generation for Out-of-Vocabulary Words Natural-language user interfaces, such as dialogue systems, need a language generation component for generating messages for the user. The aim is … Cited by 3 Related articles All 5 versions
Insight into Information Extraction Method using Natural Language Processing Technique K Dhanasekaran, R Rajeswari – Insight, 2013 – ijcsma.com … They show several interesting theoretical properties of probabilistic context-free grammars that are estimated in … has been used to prove some previously unknown properties of PCFGs trained over … tasks: a medium vocabulary medical domain doctor-patient dialog system and a … Related articles All 3 versions
Joint models for concept-to-text generation I Konstas – 2014 – era.lib.ed.ac.uk … We begin by extending an existing content selection model (Liang et al., 2009), and recasting it into a probabilistic context-free grammar. Then we formulate several decoding … This is more common in the NLG part of dialogue systems, which need to keep track of what … Related articles All 4 versions
Rethinking Deep and Surface: towards a comprehensive model of anaphoric processes in dialogue J Ginzburg – Festshcrift for Ivan Sag, ed. by Philip Hofmeister, 2013 – stanford.edu Page 1. Rethinking Deep and Surface: towards a comprehensive model of anaphoric processes in dialogue Jonathan Ginzburg ? CLILLAC-ARP and LLF (UMR 7110) Université Paris-Diderot and LabEx-EFL, Sorbonne Paris-Cité yonatan.ginzburg@univ-paris-diderot.fr … Cited by 1 Related articles
Language Processing with Perl and Prolog P Nugues – Cognitive Technologies, 2014 – Springer Page 1. Cognitive Technologies Pierre M. Nugues Language Processing with Perl and Prolog Theories, Implementation, and Application Second Edition Page 2. Cognitive Technologies Managing Editors: DM Gabbay J. Siekmann … Related articles All 10 versions
Word Activation Forces-Based Language Modeling and Smoothing M Qin, G Liu, B Li, Y Lu – Intelligent Human-Machine Systems …, 2013 – ieeexplore.ieee.org … Castro, and R. De-Mori, “Cache neural network language models based on long-distance dependencies for a spoken dialog system,” IEEE ICASSP … Using a stochastic context-free grammar as a language model for speech recognition,” In IEEE ICASSP-95, 1995, pages 189C192 … Related articles All 2 versions
Learning to automatically solve algebra word problems N Kushman, Y Artzi, L Zettlemoyer, R Barzilay – ACL (1), 2014 – anthology.aclweb.org … 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 3 Related articles All 11 versions
[BOOK] Multilingual natural language processing applications: from theory to practice D Bikel, I Zitouni – 2012 – books.google.com … 14.6 Evaluation and Metrics 14.6.1 Evaluation Metrics in the GALE Program 14.7 Summary Chapter 15 Spoken Dialog Systems 15.1 Introduction 15.2 Spoken Dialog Systems 15.2.1 Speech Recognition and Understanding 15.2.2 Speech Generation 15.2.3 Dialog Manager … Cited by 4 Related articles All 2 versions
[BOOK] The handbook of computational linguistics and natural language processing A Clark, C Fox, S Lappin – 2013 – books.google.com … Basic componentsofaspoken dialogue system. Finite state machine for a simple ticket booking application. … Relative clause attachment ambiguity. An example for the parse-trees generated by a probabilistic-context free grammar (PCFG) (adapted from Crocker & Keller 2006). … Cited by 48 Related articles All 5 versions
Exploiting the Semantic Web for Unsupervised Natural Language Semantic Parsing. G Tür, M Jeong, YY Wang, D Hakkani-Tür… – INTERSPEECH, 2012 – 202.114.89.42 … Natural language understanding (NLU) in goal-oriented dialog systems aims to automatically identify the domain and intent of the user … generative models such as hidden Markov models [3], discrim- inative classification methods [4, 5, 6] and probabilistic context free grammars [7 … Cited by 14 Related articles All 10 versions
Learning a semantic parser from spoken utterances J Gaspers, P Cimiano – Acoustics, Speech and Signal …, 2014 – ieeexplore.ieee.org … While a word-based automatic speech recognizer (ASR) may be applied in order to handle spoken utterances as typically done in spoken dialogue systems, in this paper we explore how a … [4], who tackled the task by inducing a Probabilistic Context Free Grammar, achieving an … Cited by 1 Related articles All 3 versions
SemEval-2014 Task 6: Supervised Semantic Parsing of Robotic Spatial Commands K Dukes – SemEval 2014, 2014 – aclweb.org … ing methods have used for a variety of applica- tions, including question answering (Kwiat- kowski et al., 2013; Krishnamurthy and Mitchell, 2012), dialog systems (Artzi and … Unsuper- vised PCFG Induction for Grounded Language Learning with Highly Ambiguous Supervision. … Related articles All 7 versions
Communication Aspects: How Landmarks Enrich the Communication Between Human and Machine KF Richter, S Winter – Landmarks, 2014 – Springer … Except for being a dialog system, ie, enabling some synchronous, co-presence user interaction, the system’s approach to producing … is a full-fledged NLG system based on the pCRU framework [ 5 ] . This framework—probabilistic context-free representational underspecification … Related articles
Reporting on existing USP-techniques KIT Achim Rettinger, L Zhang, CD Date – 2012 – xlike.org … Context-free grammar generates a formal language. Probabilistic context-free grammar (PCFG) is a context-free grammar in which each production is augmented with a probability. Page 10. XLike Deliverable D3.4.1 Page 10 of (28) © XLike consortium 2012 – 2014 … Related articles
Semantic parsing using word confusion networks with conditional random fields. G Tür, A Deoras, D Hakkani-Tür – INTERSPEECH, 2013 – msr-waypoint.net … Spoken language understanding (SLU) in goal-oriented dialog systems aims to automatically identify the domain and intent of the user, as … These approaches use generative models such as hidden Markov mod- els [3] and probabilistic context free grammars [4, 5] or dis … Cited by 9 Related articles All 8 versions
Learner Corpora and Natural Language Processing D Meurers – Submitted to The Cambridge Handbook of Learner …, 2013 – purl.org … included. Finally, probabilistic grammar formalisms such as PCFGs and optimality theoretic mark-up of LFG grammars can be used to tune the licensing of grammatical and ungrammatical structures to learner language (cf. Wagner … Cited by 1 Related articles All 2 versions
A Complete Bibliography of ACM Transactions on Asian Language Information Processing NHF Beebe – 2014 – tug.ctan.org … Patterns [119, 167, 4, 81]. PCFG [104]. N-gram-based [46]. … [37] Harksoo Kim and Jungyun Seo. Resolution of referring expressions in a Korean multimodal dialogue system. … A hy- brid language model based on a combination of N-grams and stochastic context-free grammars. … Related articles All 9 versions
Text to speech in new languages without a standardized orthography S Sitaram, GK Anumanchipalli, J Chiu… – Proceedings of 8th …, 2013 – parlikar.com … the speech to be generated, and produce a string of phones from the natural language generation model in the bus information dialog system. … A stochastic context free grammar is trained on such parses of accent groups, so as to allow prediction of accent groups for unseen … Cited by 3 Related articles All 5 versions
Reconstruction of Multifunction Radar Search Plan Based on Multiple Sequence Alignment S MA, Z LIU, W JIANG – Chinese Journal of Electronics, 2014 – ejournal.org.cn … Krishnamurthy, A. Wang, et al., “Syntac- tic modeling and signal processing of multifunction radars: A stochastic context-free grammar approach … et al., “The time-synchronous dynamic programming approach to the shortest path search in spoken dialog system”, Chinese Journal … Related articles All 2 versions
Unsupervised Learning of Lexical Information for Language Processing Systems G Neubig – 2012 – phontron.com Page 1. Unsupervised Learning of Lexical Information for Language Processing Systems Graham Neubig Page 2. Abstract Natural language processing systems such as speech recognition and ma- chine translation conventionally … Related articles All 2 versions
Easy contextual intent prediction and slot detection A Bhargava, A Celikyilmaz… – … , Speech and Signal …, 2013 – ieeexplore.ieee.org … Intents signify the goal of the user and vary across domains, but ultimately, a dialog system must at some point make a … among others, generative mod els such as hidden Markov models [5], discriminative classification methods [6, 7, 8], and probabilistic context-free grammars [9 … Cited by 2 Related articles All 4 versions
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 … 2003; Moschitti et al. 2007), and has recently been argued to be useful in machine translation and its evaluation (Wu and Fung 2009; Liu and Gildea 2010; Lo and Wu 2011; Wu et al. 2011), dialogue systems (Basili et al. 2009 … Cited by 2 Related articles All 6 versions
Latent semantic modeling for slot filling in conversational understanding G Tur, A Celikyilmaz… – Acoustics, Speech and …, 2013 – ieeexplore.ieee.org … More specifically, targeted SLU models in hu- man/machine spoken dialog systems aim to automatically identify several components: (i) the … include generative models such as hidden Markov models [2], discriminative methods [3, 4, 5], or probabilistic context free grammars [6, … Cited by 3 Related articles All 2 versions
Style-Specific Phrasing in Speech Synthesis A Parlikar – 2013 – errico.srv.cs.cmu.edu Page 1. Style-Specific Phrasing in Speech Synthesis Alok Parlikar CMU-LTI-13-012 Language Technologies Institute School of Computer Science Carnegie Mellon University 5000 Forbes Avenue Pittsburgh, PA 15213 Thesis Committee Alan W Black Carnegie Mellon … Cited by 3 Related articles All 13 versions
Joint Phrase Alignment and Extraction for Statistical Machine Translation G Neubig, T Watanabe, E Sumita, S Mori… – Information and Media …, 2012 – jlc.jst.go.jp … 4. Bayesian Modeling for Inversion Transduc- tion Grammars The probabilities of ITG models can be calculated in the same manner as traditional unsupervised PCFGs using the expectation- maximization algorithm and maximum likelihood estimation. … Cited by 1 Related articles All 7 versions
Elaborate descriptive information in indoor route instructions V Mast, C Jian, D Zhekova – Proceedings of the 34th …, 2012 – palm.mindmodeling.org … It was developed based on a general computational dialogue system architecture and framework named DAISIE (Ross & Bateman … 3) Natural lan- guage generation with the probabilistic context-free represen- tational underspecification framework (Belz, 2008) and the KPML … Cited by 7 Related articles All 4 versions
Bypassing Words in Automatic Speech Recognition P De Palma, G Luger, C Smith, C Wooters – Midwest Artificial Intelligence …, 2012 – Citeseer … This improved accuracy has the potential to be used in fully functional dialog systems. … Hacioglu, K., Ward, W. 2001. Dialog-Context Dependent Language Modeling Combining N-Grams and Stochastic Context-Free Grammars. … All 9 versions
Probabilistic grammar induction from sentences and structured meanings TM Kwiatkowski – 2012 – era.lib.ed.ac.uk Page 1. This thesis has been submitted in fulfilment of the requirements for a postgraduate degree (eg PhD, MPhil, DClinPsychol) at the University of Edinburgh. Please note the following terms and conditions of use: • This work … Cited by 1 Related articles All 3 versions
Affective-cognitive dialogue act detection in an error-aware spoken dialogue system WB Liang, CH Wu, MH Sheng – Signal and Information …, 2013 – ieeexplore.ieee.org … 2. Page 3. Fig. 1. Block diagram of the DA detection with error-awareness in a spoken dialogue system Fig. … The first category is the syntactic rules obtained from a probabilistic context free grammar parser (Stanford Parser [25]) trained on the annotated parts-of-speech (POSs). … Related articles All 2 versions
The Graph Symbol Model: Context-Free Parsing With Context JCP Bastings – 2012 – dare.uva.nl … These two formalisms differ mainly in their building blocks: PCFGs have context- free rules as … Dialog systems – eg a chat robot that lets you reserve a movie ticket interactively … This gives rise to probabilistic grammar, and probabilistic context-free grammar (PCFG) in particular. … Related articles All 2 versions
[BOOK] Plan, Activity, and Intent Recognition: Theory and Practice G Sukthankar, C Geib, HH Bui, D Pynadath… – 2014 – books.google.com Page 1. s PLAN, ACTIVITY, AND INTENT RECOGNITION THEORY AND PRACTICE EDITED BY GITA SUKTHAN KAR ROBERT P. GULDMAN CHRISTOPHER GEIB DAVID V. PYNADATH HUNG HAI BUI Page 2. Plan, Activity, and Intent Recognition Page 3. … Cited by 3 Related articles All 2 versions
Cluster-based Prediction of User Ratings for Stylistic Surface Realisation N Dethlefs, H Cuayáhuitl, H Hastie, V Rieser… – EACL …, 2014 – anthology.aclweb.org … Fu- ture work involves integrating the surface realiser into the PARLANCE1 (Hastie et al., 2013) spo- ken dialogue system with a method for triggering the different styles. … pCRU is based on probabilistic context- free grammars and generation is done using Viterbi search … Cited by 1 Related articles All 8 versions
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
Improving statistical machine translation using bayesian word alignment and gibbs sampling C Mermer, M Saraçlar, R Sarikaya – IEEE Transactions on Audio, …, 2013 – msr-waypoint.com Page 1. 1090 IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 21, NO. 5, MAY 2013 Improving Statistical Machine Translation Using Bayesian Word Alignment and Gibbs Sampling Co?kun … Cited by 1 Related articles All 6 versions
Blog Mining and Emotion Argumentation Argumentation SBSBS Bandyopadhyay – 2012 – dspace.jdvu.ac.in Page 1. Blog Mining and Emotion Argumentation Argumentation Thesis submitted to the Faculty of Engineering & Technology, Jadavpur University In partial fulfillment of the requirements for the Degree Of Master of Computer … Related articles All 2 versions
Expectation-Based Command Recognition Off the Shelf: Publicly Reproducible Experiments with Speech Input D Ertl, J Falb, H Kaindl, R Popp… – … (HICSS), 2013 46th …, 2013 – ieeexplore.ieee.org … [4] M. Gabsdil and O. Lemon. Combining acoustic and prag- matic features to predict recognition performance in spoken dialogue systems. … [6] K. Hacioglu and W. Ward. Dialog-context dependent lan- guage modeling combining n-grams and stochastic context- free grammars. … Related articles All 4 versions
Detecting Grammatical Errors with Treebank-Induced, Probabilistic Parsers J Wagner – 2012 – core.kmi.open.ac.uk … 128 4.7.3 Adding Negative Training Data . . . . . 128 4.7.4 Basic PCFG Parsing . . . . . 129 … 293 C.3.2 PCFG Pruning Parameters . . . . . 293 C.3.3 Markovisation Rules . . . . . … Cited by 5 Related articles All 8 versions
Data-Driven Methods for Spoken Language Understanding J Henderson, F Jur?í?ek – … Methods for Adaptive Spoken Dialogue Systems, 2012 – Springer … Spoken dialogue systems need to be able to interpret the spoken input from the user. … O. Lemon and O. Pietquin (eds.), Data-Driven Methods for Adaptive Spoken Dialogue Systems, DOI 10.1007/978-1-4614-4803-7 3, © Springer Science+Business Media New York 2012 19 … Related articles All 4 versions
Using Recurrent Neural Networks for Slot Filling in Spoken Language Understanding G Mesnil, Y Dauphin, K Yao, Y Bengio, L Deng… – 2013 – ieeexplore.ieee.org … These approaches include generative models such as hidden Markov models, discriminative classification methods such as CRFs, knowledge-based methods, and probabilistic context free grammars. A detailed survey of these earlier approaches can be found in [7]. … Related articles All 3 versions
Diagnostic and accessibility based user modelling SP Carmien, AM Cantera – User Modeling and Adaptation for Daily …, 2013 – Springer Logo Springer. Search Options: … Cited by 3 Related articles All 3 versions
Integrated supertagging and parsing M Auli – 2012 – era.lib.ed.ac.uk … 77 4.3.1 Hardware-Independent Results: PCFG . . . . . 78 … chine translation (Auli, 2009). CCG is also suitable for incremental processing of language from left to right and has been used in this way for dialogue systems (Kruijff et al., 2007). … Cited by 1 Related articles All 6 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 10 Related articles All 4 versions
Review of research on speech technology: main contributions from Spanish research groups R San-Segundo… – Journal of Speech …, 2012 – journalofspeechsciences.org … 6 Spoken Language Applications This section includes spoken language understanding and translation, spoken dialogue systems, voice-activated question answering (QA), and applications for people with special needs. 6.1 … Cited by 2 Related articles All 4 versions
Normalization Strategy of Logical Knowledge Representation for Text Document. RA Kadir, TMT Sembok, F Ahmad, A Azman – International Journal of …, 2013 – ijetch.org … technique, which plays a highly visible role in representing knowledge, to acting as computing or helping the further research such as query system, dialogue system or search … [13] S. Zhu, M. Zhou, X. Liu, and C. Huang, “An efficient stochastic context-free parsing algorithm … Related articles All 2 versions
A German Treebank and Lexicon for Tree-Adjoining Grammars M Kaeshammer – 2012 – user.phil-fak.uni-duesseldorf.de … in the future. Incremental analysis of input text is desirable, for example, in human-machine dialogue systems, where the processing should start before the input is complete (Schlangen and Skantze, 2009). A PLTAG parser … Cited by 1 Related articles
Syntactic language modeling with formal grammars T Kaufmann, B Pfister – Speech Communication, 2012 – Elsevier It has repeatedly been demonstrated that automatic speech recognition can benefit from syntactic information. However, virtually all syntactic language models f. Cited by 1 Related articles All 7 versions
Gerald Penn DG Hays – Philosophy of Linguistics, 2012 – books.google.com … overall structure of a text’s logical argument. Dialogue systems research attempts to recognize plans and intentions in speech transcripts and to respond to them constructively and naturally. 3 SEMANTICS IN CL Much of the … Related articles All 3 versions
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
[BOOK] Interactive Approaches to Video Lecture Assessment K Riedhammer – 2012 – books.google.com Page 1. Studien zur Mustererkennung \ * Band 36 \ Korbinian Riedhammer Interactive Approaches to Video Lecture Assessment Page 2. Interactive Approaches to Video Lecture Assessment Der Technischen Fakultat der Universitat … Cited by 3 Related articles All 4 versions