Extension of conventional co-training learning strategies to three-view and committee-based learning strategies for effective automatic sentence segmentation
Citation
Dalva, D., Güz, Ü. & Gürkan, H. (2018). Extension of conventional co-training learning strategies to three-view and committee-based learning strategies for effective automatic sentence segmentation. Paper presented at the 2018 IEEE Spoken Language Technology Workshop (SLT), 750-755. doi:10.1109/SLT.2018.8639533Abstract
The objective of this work is to develop effective multi-view semi-supervised machine learning strategies for sentence boundary classification problem when only small sets of sentence boundary labeled data are available. We propose three-view and committee-based learning strategies incorporating with co-training algorithms with agreement, disagreement, and self-combined learning strategies using prosodic, lexical and morphological information. We compare experimental results of proposed three-view and committee-based learning strategies to other semi-supervised learning strategies in the literature namely, self-training and co-training with agreement, disagreement, and self-combined strategies. The experiment results show that sentence segmentation performance can be highly improved using multi-view learning strategies that we propose since data sets can be represented by three redundantly sufficient and disjoint feature sets. We show that the proposed strategies substantially improve the average performance when only a small set of manually labeled data is available for Turkish and English spoken languages, respectively.
Source
2018 IEEE Spoken Language Technology Workshop (SLT)Related items
Showing items related by title, author, creator and subject.
-
Effective semi-supervised learning strategies for automatic sentence segmentation
Dalva, Doğan; Güz, Ümit; Gürkan, Hakan (Elsevier Science BV, 2018-04-01)The primary objective of sentence segmentation process is to determine the sentence boundaries of a stream of words output by the automatic speech recognizers. Statistical methods developed for sentence segmentation requires ... -
Co-training using prosodic, lexical and morphological information for automatic sentence segmentation of Turkish spoken language
Dalva, Doğan (Işık Üniversitesi, 2018-01-15)Sentence segmentation of speech aims detecting sentence boundaries in a stream of words output by the speech recognizer. Sentence segmentation is a preliminary step toward speech understanding. It is of particular importance ... -
Shallow parsing in Turkish
Topsakal, Ozan; Açıkgöz, Onur; Gürkan, Ali Tunca; Kanburoğlu, Ali Buğra; Ertopçu, Burak; Özenç, Berke; Çam, İlker; Avar, Begüm; Ercan, Gökhan; Yıldız, Olcay Taner (IEEE, 2017)In this study, shallow parsing is applied on Turkish sentences. These sentences are used to train and test the per-formances of various learning algorithms with various features specified for shallow parsing in Turkish.