Computing Dialogue Acts from Features with Transformation-Based Learning

To interpret natural language at the discourse level, it is very useful to accurately recognize dialogue acts, such as SUGGEST, in identifying speaker intentions. Our research explores the utility of a machine learning method called Transformation-Based Learning (TBL) in computing dialogue acts, because TBL has a number of advantages over alternative approaches for this application. We have identified some extensions to TBL that are necessary in order to address the limitations of the original algorithm and the particular demands of discourse processing. We use a Monte Carlo strategy to increase the applicability of the TBL method, and we select features of utterances that can be used as input to improve the performance of TBL. Our system is currently being tested on the VERBMOBIL corpora of spoken dialogues, producing promising preliminary results.

• Publication year

  1998

• Venue

  arXiv.org

• Publication date

  1998-06-02

• Fields of study

  Computer Science

• Identifiers
  arXiv cmp-lg/9806002
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Lazy Transformation-Based Learning

  1998cited by this paper
• Dialogue act classification using language models

  1997cited by this paper
• A Machine Learning Approach to the Classification of Dialogue Utterances

  1996cited by this paper
• Predicting dialogue acts for a speech-to-speech translation system

  1996cited by this paper
• A Robust and Efficient Three-Layered Dialogue Component for a Speech-to-Speech Translation System

  1995cited by this paper
• Utilizing Statistical Dialogue Act Processing in Verbrnobil

  1995cited by this paper
• Unsupervised Learning of Disambiguation Rules for Part of Speech Tagging

  1995cited by this paper
• Automatic classification of dialog acts with semantic classification trees and polygrams

  1995cited by this paper
• Transformation-Based Error-Driven Learning and Natural Language Processing: A Case Study in Part-of-Speech Tagging

  1995influential reference
• Committee-Based Sampling For Training Probabilistic Classi(cid:12)ers

  1995cited by this paper
• Topic Identification in Discourse

  1995cited by this paper
• Exploring the Statistical Derivation of Transformational Rule Sequences for Part-of-Speech Tagging

  1994influential reference
• First steps towards statistical modeling of dialogue to predict the speech act type of the next utterance

  1994cited by this paper
• Empirical Studies on the Disambiguation of Cue Phrases

  1993cited by this paper
• Recognizing complex discourse acts: a tripartite plan-based model of dialogue

  1993cited by this paper
• Linguistic and pragmatic constraints on utterance interpretation

  1990cited by this paper

• An Integrated Neural Network Model for Domain Action Determination in Goal-Oriented Dialogues

  2013cites this paper
• Text Categorization for Assessing Multiple Documents Integration, or John Henry Visits a Data Mine

  2011cites this paper
• Learning the Structure of Task-Driven Human–Human Dialogs

  2008cites this paper
• Domain action classification using a maximum entropy model in a schedule management domain

  2008cites this paper
• Towards Learning to Converse: Structuring Task-Oriented Human-Human Dialogs

  2006cites this paper
• Learning the Structure of Task-Driven Human-Human Dialogs

  2006cites this paper
• Efficient Domain Action Classification Using Neural Networks

  2006cites this paper
• An Integrated Dialogue Analysis Model for Determining Speech Acts and Discourse Structures

  2005cites this paper
• WORD CLASSES AND PART-OF-SPEECH TAGGING Conjunction Junction , what ’ s your function ?

  2005cites this paper
• A neural network model with feature selection for korean speech act classification

  2004cites this paper
• Machine Learning for Shallow Inter pretation of UserUtterancesin Spoken DialogueSystems PiroskaLendvai ILK ResearchGroup Tilburg University

  2003cites this paper
• Machine Learning for Shallow Interpretation of User Utterances in Spoken Dialogue Systems

  2003cites this paper
• 0 System Overview The Language Processing Modules in Verbmobil Recognition Prosody Synsem Transfer Generation Synthesis Context Dialogue ́

  2002cites this paper
• Robust Content Extraction for Translation and Dialog Processing

  2000cites this paper
• Leave One Out Experiments for Statistical Dialogue Act Recognition

  2000cites this paper
• Analysis System of Speech Acts and Discourse Structures Using Maximum Entropy Model

  1999cites this paper
• Fuzzy trigram model for speech act analysis of utterances in dialogues

  1999cites this paper
• Using Phrase Accent Information for Dialogue Act Recognition in Spontaneous German Speech

  1999cites this paper
• USING PHRASE ACCENT INFORMATION FOR DIALOGUE ACTRECOGNITION IN SPONTANEOUS GERMAN

  1999cites this paper
• Automatically Selecting Useful Phrases for Dialogue Act Tagging

  1999cites this paper
• Prosody prediction for speech synthesis using transformational rule-based learning

  1998influential citation
• Dialogue Act Tagging with Transformation-Based Learning

  1998influential citation
• Dialogue Act DISCOURSE LEARNING: Tagging with Transformation-Based

  1998cites this paper
• Can Prosody Aid the Automatic Classification of Dialog Acts in Conversational Speech?

  1998cites this paper
• The Neural Path to Dialogue Acts

  1998cites this paper
• An Investigation of Transformation-Based Learning in Discourse

  1998cites this paper
• Lazy Transformation-Based Learning

  1998cites this paper
• Discourse Learning: Dialogue Act Tagging with Transformation-Based Learning

  1998cites this paper
• A Statistical Model for Discourse Act Recognition in Dialogue Interactions

  1998influential citation
• Dialogue Act Tagging with Transformation-Based Learning

  1998cites this paper
• Speech and Language Processing : An introduction to natural language processing , computational linguistics , and speech recognition

  year unknowncites this paper