Results 1 -
4 of
4
Getting More Mileage from Web Text Sources for Conversational Speech Language Modeling using Class-Dependent Mixtures
- Proc. HLT-NAACL 2003
, 2003
"... Sources of training data suitable for language modeling of conversational speech are limited. In this paper, we show how training data can be supplemented with text from the web filtered to match the style and/or topic of the target recognition task, but also that it is possible to get bigger perfor ..."
Abstract
-
Cited by 36 (8 self)
- Add to MetaCart
Sources of training data suitable for language modeling of conversational speech are limited. In this paper, we show how training data can be supplemented with text from the web filtered to match the style and/or topic of the target recognition task, but also that it is possible to get bigger performance gains from the data by using class-dependent interpolation of N-grams.
Detection Of Agreement Vs. Disagreement In Meetings: Training With Unlabeled Data
- In Proc. HLT-NAACL Conference
, 2003
"... To support summarization of automatically transcribed meetings, we introduce a classifier to recognize agreement or disagreement utterances, utilizing both word-based and prosodic cues. We show that hand-labeling efforts can be minimized by using unsupervised training on a large unlabeled data set c ..."
Abstract
-
Cited by 31 (4 self)
- Add to MetaCart
To support summarization of automatically transcribed meetings, we introduce a classifier to recognize agreement or disagreement utterances, utilizing both word-based and prosodic cues. We show that hand-labeling efforts can be minimized by using unsupervised training on a large unlabeled data set combined with supervised training on a small amount of data.
Directions for Multi-Party Human-Computer Interaction Research
- In Proceedings of the HLT-NAACL 2003 Workshop on Research Directions in Dialogue Processing
, 2003
"... Research on dialog systems has so far concentrated on interactions between a single user and a machine. In this paper we identify novel research directions arising from multi-party human computer interaction, i.e. scenarios where several human participants interact with a dialog system. ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
Research on dialog systems has so far concentrated on interactions between a single user and a machine. In this paper we identify novel research directions arising from multi-party human computer interaction, i.e. scenarios where several human participants interact with a dialog system.
DETECTION OF AGREEMENT vs. DISAGREEMENT IN MEETINGS:
- In Proc. HLT-NAACL Conference
, 2003
"... To support summarization of automatically transcribed meetings, we introduce a classifier to recognize agreement or disagreement utterances, utilizing both word-based and prosodic cues. We show that hand-labeling efforts can be minimized by using unsupervised training on a large unlabeled data ..."
Abstract
- Add to MetaCart
To support summarization of automatically transcribed meetings, we introduce a classifier to recognize agreement or disagreement utterances, utilizing both word-based and prosodic cues. We show that hand-labeling efforts can be minimized by using unsupervised training on a large unlabeled data set combined with supervised training on a small amount of data.

