1 Turkish and its Challenges for Language and Speech Processing . 1 1.1 Introduction . 1 1.2 Turkish Morphology . 3 1.3 Constituent Order and Morphology-Syntax Interface . 7 1.

4 Applications . 10 1.5 State-of-the-art Tools and Resources for Turkish . 15 References . 17 2 Morphological Processing for Turkish . 21 2.1 Introduction . 21 2.

2 Overview of Turkish Morphology . 22 2.3 Morphophonology and Morphographemics . 23 2.4 Root Lexicons and Morphotactics . 27 2.4.1 Representational Convention .

28 2.4.2 Nominal Morphotactics . 29 2.4.3 Verbal Morphotactics . 29 2.4.

4 Derivations . 30 2.4.5 Examples of Morphological Analyses . 32 2.5 The Architecture of the Turkish Morphological Processor . 34 2.6 Processing Real Texts .

35 2.6.1 Acronyms . 35 2.6.2 Numbers . 36 2.6.

3 Foreign Words . 36 2.6.4 Unknown Words . 36 2.7 Multiword Processing . 37 2.7.

1 Lexicalized Collocations . 38 2.7.2 Semi-lexicalized Collocations . 38 2.7.3 Non-lexicalized Collocations . 40 2.

8 Conclusions . 44 References . 50 3 Morphological Disambiguation for Turkish . 53 3.1 Introduction . 53 3.2 Challenges . 55 3.

3 Previous Work . 55 3.3.1 Rule-based Methods . 56 3.3.2 Learning the Rules . 57 3.

3.3 Models Based on Inflectional Group n-grams . 59 3.3.4 Discriminative Methods for Disambiguation . 60 3.4 Discussion . 63 3.

4.1 Data Sets . 63 3.4.2 Experimental Results . 64 3.5 Conclusions . 65 References .

65 4 Language Modeling for Turkish Text and Speech Processing . 69 Ebru Arisoy and Murat Saraçlar 4.1 Introduction . 69 4.2 Language Modeling . 70 4.3 Challenges in Statistical Language Modeling for Turkish . 73 4.

4 Sub-lexical Units for Statistical Language Modeling . 75 4.4.1 Linguistic Sub-lexical Units . 76 4.4.2 Statistical Sub-lexical Units . 77 4.

5 Statistical Language Modeling for Turkish . 78 4.5.1 Language Modeling with Linguistic Sub-lexical Units . 78 4.5.2 Statistical Sub-lexical Units - Morphs . 81 4.

6 Discriminative Language Modeling for Turkish . 81 4.6.1 Discriminative Language Model . 82 4.6.2 Feature Sets for Turkish DLM . 83 4.

7 Conclusions . 89 References . 89 5 Turkish Speech Recognition. 95 Ebru Arisoy and Murat Saraçlar 5.1 Introduction . 95 5.2 Foundations of Automatic Speech Recognition . 96 5.

3 Turkish Language Resources for ASR . 100 5.3.1 Turkish Acoustic and Text Data . 100 5.3.2 Linguistic Tools Used in Turkish ASR . 105 5.

4 Turkish ASR Systems . 106 5.4.1 Newspaper Content Transcription System . 106 5.4.2 Turkish Broadcast News Transcription System . 109 5.

4.3 LVCSR System for Call Center Conversations . 112 5.5 Conclusions . 114 References . 114 6 Turkish Named Entity Recognition . 119 Reyyan Yeniterzi, Gökhan Tür and Kemal Oflazer 6.1 Introduction .

119 6.2 NER on Turkish . 120 6.3 Task Description . 121 6.3.1 Representation . 121 6.

3.2 Evaluating NER Performance . 122 6.4 Domain and Datasets . 124 6.4.1 Formal Texts . 124 6.

4.2 Informal Texts . 125 6.4.3 Challenges of Informal Texts for NER . 126 6.5 Preprocessing for NER. 126 6.

5.1 Tokenization . 127 6.5.2 Morphological Analysis . 127 6.5.3 Normalization .

127 6.6 Approaches used in Turkish NER . 128 6.6.1 Rule-based Approaches . 129 6.6.2 Hybrid Approaches .

130 6.6.3 Machine Learning Approaches . 131 6.7 Conclusions . 134 References . 134 7 Dependency Parsing of Turkish . 137 7.

1 Introduction . 137 7.2 Dependency Parsing . 139 7.3 Morphology and Dependency Relations in Turkish . 140 7.3.1 Dependency Relations in Turkis.