Dialogue act tagging with Transformation-Based Learning
Published 1 January 1998Open access
Ken Samuel, Sandra Carberry, K. Vijay‐Shanker
Citations98
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
This work extracts values of well-motivated features of utterances, such as speaker direction, punctuation marks, and a new feature, called dialogue act cues, which it finds to be more effective than cue phrases and word n-grams in practice.
Abstract
For the task of recognizing dialogue acts, we are applying the Transformation-Based Learning (TBL) machine learning algorithm. To circumvent a sparse data problem, we extract values of well-motivated features of utterances, such as speaker direction, punctuation marks, and a new feature, called dialogue act cues, which we find to be more effective than cue phrases and word n-grams in practice. We present strategies for constructing a set of dialogue act cues automatically by minimizing the entropy of the distribution of dialogue acts in a training corpus, filtering out irrelevant dialogue act cues, and clustering semantically-related words. In addition, to address limitations of TBL, we introduce a Monte Carlo strategy for training efficiently and a committee method for computing confidence measures. These ideas are combined in our working implementation, which labels held-out data as accurately as any other reported system for the dialogue act tagging task.
Keywords
Computer Science
Experiments with a new boosting algorithm
7,585 Citations1996Yoav Freund, Robert E. Schapire
Computational LinguisticsAttention, intentions, and the structure of discourse
2,606 Citations1986Barbara J. Grosz, Candace L. Sidner
A new theory of discourse structure that stresses the role of purpose and processing in discourse is explored and various properties of discourse are described, and explanations for the behavior of cue phrases, referring expressions, and interruptions are explored.
Transformation-based error-driven learning and natural language processing: a case study in part-of-speech tagging
1,531 Citations1995Eric Brill
This paper describes a simple rule-based approach to automated learning of linguistic knowledge that has been shown for a number of tasks to capture information in a clearer and more direct fashion without a compromise in performance.
Elsevier eBooksCommittee-Based Sampling For Training Probabilistic Classifiers
497 Citations1995Ido Dagan, Sean P. Engelson
A general method for efficiently training probabilistic classifiers, by selecting for training only the more informative examples in a stream of unlabeled examples, which is particularly attractive because it evaluates the expected information gain from a training example implicitly.
Empirical Studies on the Disambiguation of Cue Phrases
372 Citations1991Julia Hirschberg, Diane Litman
This paper reports results of empirical studies on discourse and sentential uses of cue phrases, in which both text-based and prosodic features were examined for disambiguating power.
Edinburgh Research Archive (University of Edinburgh)A Data-Driven Methodology for Motivating a Set of Coherence Relations
310 Citations1996Alistair Knott
It is argued here that evidence for the constructs modelled by relations can be sought in an analysis of the linguistic resources available for marking them explicitly in text, which rests on a systematic analysis of concrete linguistic data and demands a minimum of theoretical assumptions.
Text, speech and language technologyUnsupervised Learning of Disambiguation Rules for Part-of-Speech Tagging
186 Citations1999Eric Brill, Mihaela Pop
An unsupervised learning algorithm for automatically training a rule-based part of speech tagger without using a manually tagged corpus is described and compared to the Baum-Welch algorithm, used for unsupervised training of stochastic taggers.
Learning features that predict cue usage
48 Citations1997Barbara Di Eugenio, Johanna D. Moore +1 more
The goal is to identify the features that predict the occurrence and placement of discourse cues in tutorial explanations in order to aid in the automatic generation of explanations, and to show that machine learning can be used to induce decision trees useful for text generation.
Topic identification in discourse
44 Citations1995Kuang‐Hua Chen
A corpus-based language model for topic identification, where the nouns that have the strongest connectivities with the other nouns and verbs in the discourse form the preferred topic set.
Journal of Artificial Intelligence ResearchAn Empirical Approach to Temporal Reference Resolution
44 Citations1998Jens Wiebe, Thomas P. O'Hara +2 more
An in-depth empirical investigation of resolving explicit temporal references in scheduling dialogs adopts a pure realization of a recency-based focus model to identify precisely when it is and is not adequate for the task being addressed.
Recognizing complex discourse acts: a tripartite plan-based model of dialogue
28 Citations1993Lynn Lambert
An algorithm is presented that combines world, linguistic, and contextual knowledge to recognize complex discourse acts such as expressing doubt and that enables the system to model the structure of negotiation dialogues, a step towards a complete model of negotiation and thus a more robust model of understanding.
A Statistical Model for Discourse Act Recognition in Dialogue Interactions
23 Citations1998Jennifer Chu‐Carroll
It is shown that taking into account utterance features such as speaker information and syntactic forms of utterances dramatically improves the system’s performance as compared with a simple trigram model of discourse acts.
arXiv (Cornell University)A Machine Learning Approach to the Classification of Dialogue Utterances
21 Citations1996Toine Andernach
arXiv (Cornell University)Computing Dialogue Acts from Features with Transformation-Based Learning
18 Citations1998Ken Samuel, Sandra Carberry +1 more
This 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.
arXiv (Cornell University)Classifying Cue Phrases in Text and Speech Using Machine Learning
17 Citations1994Diane Litman
This paper explores the use of machine learning for classifying cue phrases as discourse or sentential, and two machine learning programs are used to induce classification rules from sets of pre-classified cue phrases and their features.
An Empirical Approach to Temporal Reference Resolution
12 Citations2005Janyce Wiebe, Tom O ‘Hara +2 more
arXiv (Cornell University)An Investigation of Transformation-Based Learning in Discourse
8 Citations1998Ken Samuel, Sandra Carberry +1 more
This paper developed a Monte Carlo version of TransformationBased Learning to make the method tractable for a wider range of problems without degradation in accuracy, and devised a committee method for assigning confidence measures to tags produced by Transformation-Based Learning.
ArXiv.orgAn Empirical Approach to Temporal Reference Resolution
2 Citations1997Janyce Wiebe, Tom O’Hara +2 more