Wikipedia-based Kernels for dialogue topic tracking
Published 1 May 2014
Seokhwan Kim, Rafael E. Banchs, Haizhou Li
Citations7
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
The experimental results show that the proposed kernel method for dialogue topic tracking to utilize various types of information obtained from Wikipedia can significantly improve the performances of the task in mixed-initiative human-human dialogues.
Abstract
Dialogue topic tracking aims to segment on-going dialogues into topically coherent sub-dialogues and predict the topic category for each next segment. This paper proposes a kernel method for dialogue topic tracking to utilize various types of information obtained from Wikipedia. The experimental results show that our proposed approach can significantly improve the performances of the task in mixed-initiative human-human dialogues.
Keywords
Computer Science
ACM Transactions on Intelligent Systems and TechnologyLIBSVM
41,340 Citations2011Chih-Chung Chang, Chih‐Jen Lin
Issues such as solving SVM optimization problems theoretical convergence multiclass classification probability estimates and parameter selection are discussed in detail.
Communications of the ACMA vector space model for automatic indexing
7,434 Citations1975Gerard Salton, Anita M.-Y. Wong +1 more
An approach based on space density computations is used to choose an optimum indexing vocabulary for a collection of documents, demonstating the usefulness of the model.
Verbs semantics and lexical selection
3,086 Citations1994Zhibiao Wu, Martha Palmer
This paper will focus on the semantic representation of verbs in computer systems and its impact on lexical selection problems in machine translation (MT), and sees the approach as closely aligned with knowledge-based MT approaches (KBMT), and as a separate component that could be incorporated into existing systems.
Building semantic kernels for text classification using wikipedia
205 Citations2008Pu Wang, Carlotta Domeniconi
This paper overcome the shortages of the BOW approach by embedding background knowledge derived from Wikipedia into a semantic kernel, which is then used to enrich the representation of documents.
Ravenclaw: dialog management using hierarchical task decomposition and an expectation agenda
199 Citations2003Dan Bohus, Alexander I. Rudnicky
RavenClaw is described, a new dialog management framework developed as a successor to the Agenda architecture used in the CMU Communicator, and allows rapid development of dialog management components for spoken dialog systems operating in complex, goal-oriented domains.
The Hidden Information State Approach to Dialog Management
118 Citations2007Steve Young, Jost Schatzmann +2 more
A variation of the classic POMDP called the hidden information state (HIS) model is described in which belief distributions are represented efficiently by grouping states together into partitions and policy optimisation is made tractable by using a master to summary space mapping.
Topic Detection and Extraction in Chat
83 Citations2008Paige Adams, Craig Martell
Preliminary methods of topic detection and topic thread extraction that augment a typical TF-IDF-based vector space model approach with temporal relationship information between posts of the Chat dialog combined with WordNet hypernym augmentation are presented.
Automatic generation of domain models for call centers from noisy transcriptions
48 Citations2006Shourya Roy, L. Venkata Subramaniam
This work uses a state of the art Automatic Speech Recognition system to transcribe the calls between agents and customers and shows that even from these noisy transcriptions of calls, a domain model can be automatically built automatically from call transcriptions.
A DISTRIBUTED ARCHITECTURE FOR COOPERATIVE SPOKEN DIALOGUE AGENTS WITH COHERENT DIALOGUE STATE AND HISTORY
27 Citations2000Bor-Shen Lin, Hsin‐Min Wang +1 more
Under this architecture, different spoken dialogue agents handling different domains can be developed independently, and cooperate with one another to respond to the user’s requests, while a user interface agent can access the correct spoken dialogue agent through a domain switching protocol, and carry over the dialogue state and history so as to keep the knowledge processed persistently and consistently across different domains.
Topic identification in natural language dialogues using neural networks
21 Citations2002Krista Lagus, Jukka Kuusisto
A probabilistic model is defined and different methods for model parameter estimation on a corpus of 189 dialogues are compared and the utilization of information regarding the position of the word in the utterance is found to improve the results.
Approximate inference for domain detection in spoken language understanding
15 Citations2011Aslı Çelikyılmaz, Dilek Hakkani‐Tür +1 more
This paper presents a semi-latent topic model for semantic domain detection in spoken language understanding systems that uses labeled utterance information to capture latent topics, which directly correspond to semantic domains.
Robust Dialog Management with N-Best Hypotheses Using Dialog Examples and Agenda
15 Citations2008Cheongjae Lee, Sangkeun Jung +1 more
This work presents an agenda-based approach to improve the robustness of the dialog manager by using dialog examples and n-best recognition hypotheses, and preliminary evaluation shows this approach would be effective to improvements of example-based dialog modeling.
Extensibility verification of robust domain selection against out-of-grammar utterances in multi-domain spoken dialogue system
9 Citations2008Satoshi Ikeda, Kazunori Komatani +3 more
A robust domain selection method was developed and its extensibility was verified without collecting new data, which means that the classifier should still have high performance without reconstructing it after adding new domains.
Topic detection based on dialogue history
8 Citations2002Takayuki Nakata, Shinichi Ando +1 more
From the evaluation of detection performance using test data comprised of realistic spoken dialogue, the method has shown to perform better with clustering incorporated, and when combined with dialogue history of three sentences, gives detection accuracy of 72.1%.
Harvesting Wikipedia Knowledge to Identify Topics in Ongoing Natural Language Dialogs
7 Citations2011Alexa Breuing, Ulli Waltinger +1 more
A model harvesting the crowd-sourced encyclopedic knowledge provided by Wikipedia to improve the conversational abilities of an artificial agent and aims to improve human-agent conversations by transferring human-like topic awareness to the artificial interlocutor.