POMDP-Based Statistical Spoken Dialog Systems: A Review

Young, Steve; Gašić, Milica; Thomson, Blaise; Williams, Jason D.

doi:10.1109/jproc.2012.2225812

Cited by 758 publications

(557 citation statements)

References 73 publications

Supporting

Mentioning

524

Contrasting

Unclassified

Order By: Relevance

“…There has also been considerable work in goaldirected dialog systems in domains such as information provision (Young et al, 2013). These systems model dialog as a POMDP and focus on either the problem of tracking belief state accurately over large state spaces El Asri et al, 2016) or efficiently learning a dialog policy over this state space (Gašić and Young, 2014;Pietquin et al, 2011;Png et al, 2012).…”

Section: Related Workmentioning

confidence: 99%

“…This has led to the development of approximate representations that exploit domain-specific properties of dialog tasks to allow tractable estimation of the belief state and policy optimization (Young et al, 2013).…”

Section: Background -Partially Observable Markov Decision Process (Pomentioning

confidence: 99%

“…We use a POMDP to model dialog and learn a policy (Young et al, 2013), adapting the Hidden Information State model (HIS) to track the belief state as the dialog progresses. The key idea behind this approach is to group states into equivalence classes called partitions, and maintain a probability for each partition instead of each state.…”

Section: Dialog Strategy Learningmentioning

confidence: 99%

See 2 more Smart Citations

Integrated Learning of Dialog Strategies and Semantic Parsing

Padmakumar

Thomason

Mooney

2017

Proceedings of the 15th Conference of the European Chapter of The Association for Computational Linguistics: Volume 1

View full text Add to dashboard Cite

Natural language understanding and dialog management are two integral components of interactive dialog systems. Previous research has used machine learning techniques to individually optimize these components, with different forms of direct and indirect supervision. We present an approach to integrate the learning of both a dialog strategy using reinforcement learning, and a semantic parser for robust natural language understanding, using only natural dialog interaction for supervision. Experimental results on a simulated task of robot instruction demonstrate that joint learning of both components improves dialog performance over learning either of these components alone.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Background -Partially Observable Markov Decision Process (Pomentioning

confidence: 99%

Section: Dialog Strategy Learningmentioning

confidence: 99%

See 1 more Smart Citation

Integrated Learning of Dialog Strategies and Semantic Parsing

Padmakumar

Thomason

Mooney

2017

Proceedings of the 15th Conference of the European Chapter of The Association for Computational Linguistics: Volume 1

View full text Add to dashboard Cite

show abstract

“…It mainly consists of four components: 1) language understanding, 2) conversation state tracking, 3) domain selection and processing and 4) response generation. As can be seen, the architecture of Benben can be corresponded to the classic architecture of spoken dialogue systems (Young et al, 2013). Concretely, the natural language understanding, dialogue management and natural language generation in spoken dialogue systems are corresponding to the 1), 2) and 3), 4) components of the Benben architecture, respectively.…”

Section: Architecturementioning

confidence: 99%

Proceedings of ACL 2017, System Demonstrations

Zhang

2017

View full text Add to dashboard Cite

We present the first open-source tool for annotating morphosyntactic tense, mood and voice for English, French and German verbal complexes. The annotation is based on a set of language-specific rules, which are applied on dependency trees and leverage information about lemmas, morphological properties and POS-tags of the verbs. Our tool has an average accuracy of about 76%. The tense, mood and voice features are useful both as features in computational modeling and for corpuslinguistic research. IntroductionNatural language employs, among other devices such as temporal adverbials, tense and aspect to locate situations in time and to describe their temporal structure (Deo, 2012). The tool presented here addresses the automatic annotation of morphosyntactic tense, i.e., the tense-aspect combinations, expressed in the morphology and syntax of verbal complexes (VC). VCs are sequences of verbal tokens within a verbal phrase. We address German, French and English, in which the morphology and syntax also includes information on mood and voice. Morphosyntactic tenses do not always correspond to semantic tense (Deo, 2012). For example, the morphosyntactic tense of the English sentence "He is leaving at noon." is present progressive, while the semantic tense is future. In the remainder of this paper, we use the term tense to refer to the morphological tense and aspect information encoded in finite verbal complexes.Corpus-linguistic research, as well as automatic modeling of mono-and cross-lingual use of tense, mood and voice will strongly profit from a reliable automatic method for identifying these clausal features. They may, for instance, be used to classify texts with respect to the epoch or region in which they have been produced, or for assigning texts to a specific author. Moreover, in crosslingual research, tense, mood, and voice have been used to model the translation of tense between different language pairs (Santos, 2004; Loáiciga et al., 2014; Ramm and Fraser, 2016)). Identifying the morphosyntactic tense is also a necessary prerequisite for identifying the semantic tense in synthetic languages such as English, French or German (Reichart and Rappoport, 2010). The extracted tense-mood-voice (TMV) features may also be useful for training models in computational linguistics, e.g., for modeling of temporal relations (Costa and Branco, 2012; UzZaman et al., 2013).As illustrated by the examples in Figure 1, relevant information for determining TMV is given by syntactic dependencies and partially by partof-speech (POS) tags output by analyzers such as Mate (Bohnet and Nivre, 2012). However, the parser's output is not sufficient for determining TMV features; morphological features and lexical information needs to be taken into account as well. Learning TMV features from an annotated corpus would be an alternative; however, to the best of our knowledge, no such large-scale corpora exist.A sentence may contain more than one VC, and the tokens belonging to a VC are not always contiguous in the sentence (see VCs A...

show abstract

“…Most recent advances in statistical dialog modeling have been based on the Partially Observable Markov Decision Processes (POMDP) framework which provides a principled way for sequential action planning under uncertainty (Young et al, 2013). In this approach, the task of dialog management is generally decomposed into two subtasks, i.e., dialog state tracking and dialog policy learning.…”

Section: Introductionmentioning

confidence: 99%

Extrinsic Evaluation of Dialog State Tracking and Predictive Metrics for Dialog Policy Optimization

Lee

2014

Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)

View full text Add to dashboard Cite

During the recent Dialog State Tracking Challenge (DSTC), a fundamental question was raised: "Would better performance in dialog state tracking translate to better performance of the optimized policy by reinforcement learning?" Also, during the challenge system evaluation, another nontrivial question arose: "Which evaluation metric and schedule would best predict improvement in overall dialog performance?" This paper aims to answer these questions by applying an off-policy reinforcement learning method to the output of each challenge system. The results give a positive answer to the first question. Thus the effort to separately improve the performance of dialog state tracking as carried out in the DSTC may be justified. The answer to the second question also draws several insightful conclusions on the characteristics of different evaluation metrics and schedules.

show abstract

POMDP-Based Statistical Spoken Dialog Systems: A Review

Cited by 758 publications

References 73 publications

Integrated Learning of Dialog Strategies and Semantic Parsing

Integrated Learning of Dialog Strategies and Semantic Parsing

Proceedings of ACL 2017, System Demonstrations

Extrinsic Evaluation of Dialog State Tracking and Predictive Metrics for Dialog Policy Optimization

Contact Info

Product

Resources

About