Building Morphological Chains for Agglutinative Languages

Download

index.pdf

Date

2017-04-23

Author

Ozen, Serkan
CAN BUĞLALILAR, BURCU

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

78
views

0
downloads

In this paper, we build morphological chains for agglutinative languages by using a log linear model for the morphological segmentation task. The model is based on the unsupervised morphological segmentation system called MorphoChains [1]. We extend MorphoChains log linear model by expanding the candidate space recursively to cover more split points for agglutinative languages such as Turkish, whereas in the original model candidates are generated by considering only binary segmentation of each word. The results show that we improve the state-of-art Turkish scores by 12% having a F-measure of 72% and we improve the English scores by 3% having a F-measure of 74%. Eventually, the system outperforms both MorphoChains and other well-known unsupervised morphological segmentation systems. The results indicate that candidate generation plays an important role in such an unsupervised loglinear model that is learned using contrastive estimation with negative samples.

Subject Keywords

Unsupervised learning, Morphological segmentation, Log-linear models, Morphology, Contrastive estimation

URI

https://hdl.handle.net/11511/65845

DOI

https://doi.org/10.1007/978-3-319-77113-7_8

Collections

Department of Computer Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

A Trie-structured Bayesian Model for Unsupervised Morphological Segmentation Kurfalı, Murathan; Ustun, Ahmet; CAN BUĞLALILAR, BURCU (2017-04-23) In this paper, we introduce a trie-structured Bayesian model for unsupervised morphological segmentation. We adopt prior information from different sources in the model. We use neural word embeddings to discover words that are morphologically derived from each other and thereby that are semantically similar. We use letter successor variety counts obtained from tries that are built by neural word embeddings. Our results show that using different information sources such as neural word embeddings and letter s...
A complete axiomatization for fuzzy functional and multivalued dependencies in fuzzy database relations Sozat, MI; Yazıcı, Adnan (Elsevier BV, 2001-01-15) This paper first introduces the formal definitions of fuzzy functional and multivalued dependencies which are given on the basis of the conformance values presented here. Second, the inference rules are listed after both fuzzy functional and multivalued dependencies are shown to be consistent, that is, they reduce to those of the classic functional and multivalued dependencies when crisp attributes are involved. Finally, the inference rules presented here are shown to be sound and complete for the family of...
A neuro-fuzzy MAR algorithm for temporal rule-based systems Sisman, NA; Alpaslan, Ferda Nur; Akman, V (1999-08-04) This paper introduces a new neuro-fuzzy model for constructing a knowledge base of temporal fuzzy rules obtained by the Multivariate Autoregressive (MAR) algorithm. The model described contains two main parts, one for fuzzy-rule extraction and one for the storage of extracted rules. The fuzzy rules are obtained from time series data using the MAR algorithm. Time-series analysis basically deals with tabular data. It interprets the data obtained for making inferences about future behavior of the variables. Fu...
Improving reinforcement learning by using sequence trees Girgin, Sertan; Polat, Faruk; Alhajj, Reda (Springer Science and Business Media LLC, 2010-12-01) This paper proposes a novel approach to discover options in the form of stochastic conditionally terminating sequences; it shows how such sequences can be integrated into the reinforcement learning framework to improve the learning performance. The method utilizes stored histories of possible optimal policies and constructs a specialized tree structure during the learning process. The constructed tree facilitates the process of identifying frequently used action sequences together with states that are visit...
Analysis and network representation of hotspots in protein interfaces using minimum cut trees Tunçbağ, Nurcan; Keskin, Ozlem; GÜRSOY, Attila (2010-08-01) We propose a novel approach to analyze and visualize residue contact networks of protein interfaces by graph-based algorithms using a minimum cut tree (mincut tree). Edges in the network are weighted according to an energy function derived from knowledge-based potentials. The mincut tree, which is constructed from the weighted residue network, simplifies and summarizes the complex structure of the contact network by an efficient and informative representation. This representation offers a comprehensible vie...

Citation Formats

S. Ozen and B. CAN BUĞLALILAR, “Building Morphological Chains for Agglutinative Languages,” 2017, vol. 10761, p. 99, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/65845.