# Natural Language Processing > A Turkish-centered NLP course covering Unicode and normalization, tokenization, morphology, syntax, semantics, statistical NLP, Transformers, multilingual models, speech, LLMs, and production engineering in a comparative language perspective. - Author: Muhammet Ali Köker - Language: en - Canonical: https://alikoker.com.tr/en/natural-language-processing - Translation: https://alikoker.com.tr/dogal-dil-isleme - Published: 2018-09-01T12:00:00+03:00 - Modified: 2026-09-18T00:00:00+03:00 - Type: article Natural Language Processing (NLP) studies computational methods for analyzing, transforming, retrieving, classifying, generating, and grounding human language. It is broader than text generation and broader than large language models. Character encoding, normalization, morphology, syntax, semantics, information retrieval, speech recognition, language modeling, evaluation, and production-system behavior all belong to the field. This course is deliberately Turkish-centered. Turkish exposes assumptions that remain hidden in many English-first pipelines: productive agglutinative morphology, vowel harmony, morphophonemic alternation, rich case marking, relatively flexible constituent order, and language-specific casing behavior. The goal is not to treat Turkish as an exception, but to use it to understand why NLP architectures must be evaluated against the linguistic properties of their target languages. The course connects to [Artificial Intelligence: Philosophy, Theory and Practice](/en/artificial-intelligence-philosophy-theory-practice), [Neural Networks and Learning Models](/en/artificial-neural-networks-and-learning-models), [Statistical Learning and Machine Learning](/en/statistical-learning-machine-learning), [Logic Programming and Prolog](/en/logic-programming-and-prolog), and [Large Language Models](/en/large-language-models). Those courses explain broader learning and reasoning mechanisms; this course focuses on how natural language itself is represented and processed. ```text raw language data | v encoding and normalization | v segmentation / tokenization | v morphology | v syntax | v semantics and discourse | v task model | v evaluation and production system ``` Modern end-to-end models can learn several of these stages jointly. The distinctions still matter when diagnosing errors, building datasets, designing interfaces, and operating real systems. ## Unit 1: The NLP Problem Space Natural language is not a formally designed programming notation. Surface strings are ambiguous, multiple forms can express similar meanings, and the same form can serve different grammatical or semantic roles. In Turkish, constituent order may vary while case marking preserves much of the predicate–argument structure. In English, word order often carries a larger share of that information. The same preprocessing assumption therefore has different consequences in different languages. Core NLP task families include normalization, segmentation, morphology, tagging, named-entity recognition, parsing, relation extraction, semantic similarity, retrieval, classification, sentiment analysis, question answering, summarization, machine translation, speech-language processing, dialogue, language modeling, and generation. Rule-based, statistical, and neural methods should be viewed as engineering options rather than mutually exclusive historical camps. ```text explicit rule -> lexicon / grammar / finite-state model statistical model -> n-gram / HMM / Naive Bayes / CRF learned representation -> embedding / RNN / Transformer / LLM ``` A deterministic normalization rule may be preferable for a narrow text transformation, while contextual neural models may be appropriate for NER or semantic classification. ## Unit 2: Language Typology and NLP Design A Unicode-capable program can technically accept many languages without being linguistically language-independent. Important cross-linguistic differences include word-boundary marking, inflectional complexity, derivation, constituent order, casing, orthography-to-pronunciation correspondence, compounding, clitics, and writing systems. Turkish is agglutinative: ```text ev evler evlerimiz evlerimizde evlerimizdekiler evlerimizdekilerden ``` English has much lighter inflection and relies more heavily on word order and separate function words. German combines inflection with productive compounding. Arabic involves root-and-pattern morphology together with attached elements and often omits short-vowel diacritics in ordinary writing. Chinese does not normally mark all word boundaries with spaces, so word segmentation becomes a modeling decision. Japanese combines multiple scripts and also requires explicit segmentation or morphological analysis. Other Turkic languages share structural properties with Turkish but differ in writing systems, phonology, morphology, vocabulary, and resource availability. Relatedness helps transfer in some settings but is not a correctness guarantee. ## Unit 3: Unicode, Orthography, and Normalization The first NLP layer is often character handling. Byte decoding, Unicode normalization, invisible control characters, and language-specific case conversion can alter equality and search behavior. For Turkish: ```text i <-> İ ı <-> I ``` This differs from English-centric casing assumptions. ASCII reduction may be useful as an auxiliary search representation: ```text ç -> c ğ -> g ı -> i ö -> o ş -> s ü -> u ``` but it is lossy and should not replace canonical text. The design issues are explored in [Table-Based ASCII Conversion for Turkish Text](/en/table-based-ascii-conversion-for-turkish-text). The reverse problem, Turkish deasciification, is context-sensitive. `cagri` can be restored as `çağrı`, while other strings remain ambiguous. [Turkish Deasciification in C#](/en/turkish-deasciification-in-csharp) is an example of a small deterministic/contextual NLP model whose scope is explicitly bounded. ## Unit 4: Segmentation, Tokens, and Subwords A token is a computational unit, not a universal linguistic fact. ```text text -> characters -> word candidates -> subwords -> model tokens ``` Whitespace is a strong cue in Turkish and English but not a complete solution. URLs, punctuation, abbreviations, multiword expressions, emojis, proper names, and malformed text all create edge cases. Agglutinative morphology makes word-level vocabularies sparse in Turkish. Subword modeling can share statistical evidence across inflected and derived forms. BPE-style methods merge frequent symbol sequences. Unigram methods score alternative segmentations from a learned subword inventory. SentencePiece can learn directly from raw text without requiring a pre-tokenized word sequence. Model segmentation does not have to align with morphology: ```text linguistic: ev + ler + imiz + den possible model segmentation: evl + erimiz + den ``` The distinction is important in [SentencePiece Tokenization, Normalization and Vocabulary Boundaries](/en/sentencepiece-tokenization-normalization-and-vocabulary-boundaries). Character- and byte-level models reduce vocabulary dependence but lengthen sequences. Tokenizer choice therefore affects memory, latency, effective context length, and multilingual fairness. ## Unit 5: Turkish Morphology Turkish morphology is productive. A root can take multiple inflectional and derivational suffixes. ```text yaz yazıcı yazıcılar yazıcılarımız yazıcılarımızdan ``` Suffixes also have context-dependent surface forms because of vowel harmony and consonant alternations. Finite-state methods provide a natural formalism for much of this regular structure: ```text root lexicon | v morphotactic transitions | v surface alternation rules | v word form ``` Running the relation in the opposite direction yields candidate analyses for a surface form. Syllabification and morphological analysis are different problems. [Finite-State Turkish Syllabification Algorithm](/en/finite-state-turkish-syllabification-algorithm) and the open-source [Turkish Finite-State Syllabifier](/en/turkish-finite-state-syllabifier) demonstrate how a narrow phonotactic/orthographic problem can be solved with a small deterministic state machine without pretending to be a full morphological analyzer. ## Unit 6: Morphological Ambiguity and Tagging A morphological analyzer can produce multiple legal analyses. A disambiguator uses context to select among them. ```text surface form | v morphological analyzer | +-> analysis A +-> analysis B +-> analysis C | v contextual disambiguation | v selected analysis ``` Part-of-speech tagging has been approached with rules, n-gram taggers, HMMs, transformation-based learning, CRFs, perceptrons, and contextual neural models. For Turkish, morphology and syntax interact strongly. Case, agreement, possession, tense, aspect, and person information may be encoded inside the word rather than in separate tokens. ## Unit 7: Syntax and Dependency Parsing Syntax models relationships between linguistic units. Dependency parsing represents head–dependent relationships directly. ```text tested / \ engineer model subject object ``` Relatively flexible constituent order makes explicit dependency structure especially useful for Turkish. Universal Dependencies provides a cross-linguistic annotation framework for parts of speech, morphological features, and dependency relations. It does not claim that languages are structurally identical; it provides shared annotation principles for comparing different grammatical systems. The Turkish BOUN and IMST treebanks are important resources for Turkish dependency parsing. ## Unit 8: Lexical Semantics, Entities, and Discourse Meaning is contextual. A single surface form can have different senses, and a single concept can be expressed by multiple lexical forms. Named-entity recognition identifies people, organizations, locations, dates, products, and other entity types. Turkish suffixes can attach directly to entity names, so normalization and boundary handling affect NER behavior. Relation extraction goes beyond entity detection: ```text PERSON ---- works_at ----> ORGANIZATION PERSON ---- born_in -----> LOCATION EVENT ---- occurred_on -> DATE ``` Coreference resolution and discourse analysis connect expressions across sentence boundaries. ## Unit 9: Logic and Logic Programming Natural language can be mapped into structured representations instead of being left as free-form text. ```text "Deniz sent the report." | v sender = Deniz object = report action = send ``` A symbolic representation can then be expressed as a predicate: ```prolog sent(deniz, report). ``` Prolog and Definite Clause Grammars have a long relationship with natural-language parsing and formal semantics. A modern hybrid system can combine neural extraction with symbolic validation: ```text text | v neural NLP model | v candidate entities / relations | v logic rules and constraints | v validated result ``` This is a direct bridge to [Logic Programming and Prolog](/en/logic-programming-and-prolog). ## Unit 10: Corpora, Annotation, and Data Lifecycle A corpus is not merely a large folder of text. Source, time period, domain, language variety, licensing, deduplication, splits, and annotation rules all affect model behavior. Document-level leakage is particularly important. Near-duplicate documents across train and test sets can create an unrealistically high score. Annotation disagreement should be treated as information about the task rather than hidden. Guidelines, adjudication, and inter-annotator agreement are part of dataset quality. Turkish NLP has developed morphological corpora, dependency treebanks, lexical resources, speech data, and task-specific datasets. Resource size must be considered together with annotation quality, domain, and license. ## Unit 11: Classical Statistical NLP N-gram language models estimate the next unit from a bounded history: ```text P(next word | recent context) ``` They are transparent and efficient but suffer from sparse observations and limited context. Morphologically rich languages can make word-level sparsity more severe. Smoothing reallocates probability mass so unseen events are not automatically impossible. Naive Bayes remains a strong baseline for many text-classification problems. My historical [Spam Detection with Data Mining Techniques](/en/spam-detection-with-data-mining-techniques) work used n-gram features and Naive Bayes implementations to compare practical classification behavior. HMMs and CRFs historically played major roles in tagging and sequence labeling. Understanding them clarifies what modern contextual models changed and what evaluation problems remained unchanged. ## Unit 12: Text Representation and Embeddings Bag-of-words and TF-IDF discard much order information but remain valuable baselines and retrieval representations. Word2Vec and GloVe learn dense distributional representations. FastText-style character n-gram information is particularly relevant to rare and morphologically complex word forms. Contextual models assign different representations to the same surface word depending on its surrounding text. This is one of the key conceptual changes introduced by pre-trained contextual encoders such as BERT. ## Unit 13: Neural Sequence Models RNNs process sequences through recurrent hidden state. LSTM and GRU architectures introduced gates that make long-range dependencies easier to learn. Encoder–decoder systems map one sequence to another, supporting tasks such as machine translation. Attention allows the output process to weight different parts of the source sequence dynamically. This idea later became central to Transformers. ## Unit 14: Transformers and Pre-training Transformers replace recurrent sequence traversal with attention-based interactions between tokens. Their parallel training characteristics enabled much larger pre-training regimes. Encoder-oriented models are commonly used for representation and understanding tasks, decoder-oriented models for autoregressive generation, and encoder–decoder models for sequence transformation. Masked modeling and autoregressive next-token prediction produce different information flows. Pre-training followed by task adaptation is valuable for lower-resource tasks, but multilingual training data is rarely balanced across languages. ## Unit 15: Multilingual NLP and Cross-Lingual Transfer A shared model does not guarantee equal treatment of languages. Tokenization efficiency, training volume, script, typological distance, and domain all affect transfer. A Turkish sentence may consume more subword tokens than an English sentence with similar semantic content. That changes effective context length and inference cost. Transfer between Turkish and related Turkic languages can benefit from shared morphology and vocabulary, but different alphabets, false cognates, and language-specific morphology still matter. Machine translation must reconstruct grammar rather than replace words one by one. Turkish–English translation often requires reorganizing constituent order and expanding morphological information into separate English words. ## Unit 16: Classification, Extraction, and Retrieval Text classification includes spam filtering, topic classification, intent detection, routing, and moderation. Evaluation should separate representation, model, decision threshold, and task metric. Sentiment analysis is not simply positive/negative keyword counting. Negation, target, irony, intensity, domain, and morphology matter. Information retrieval remains fundamental even in LLM systems. A hybrid design may combine lexical and vector search: ```text query | +-> lexical retrieval -----+ | | +-> vector retrieval ------+-> reranker -> results ``` My [Turkish Phonetic Matching with Numeric Soundex](/en/turkish-phonetic-matching-with-numeric-soundex) and open-source [Turkish Numeric Soundex](/en/turkish-numeric-soundex) work treat phonetic coding as candidate generation rather than identity proof. ## Unit 17: Speech and the NLP Boundary Automatic speech recognition converts acoustic input into text. The resulting transcript often still requires NLP normalization. ```text audio | v VAD / segmentation | v ASR | v raw transcript | v punctuation / casing / text normalization | v NLP task ``` Turkish ASR output can contain errors in suffixes, proper names, spacing, numbers, and written-language normalization. [Automatic Speech Recognition](/en/automatic-speech-recognition), [Whisper Architecture in Speech Recognition Systems](/en/whisper-architecture-in-speech-recognition-systems), and [Capacity Engineering for Real-Time Speech Recognition](/en/capacity-engineering-real-time-speech-recognition) cover the acoustic/model and production-system sides of this boundary. WER is useful, but a single suffix error can turn a whole Turkish word into an error. CER can add diagnostic information, although neither metric directly measures semantic harm. ## Unit 18: Large Language Models Within NLP LLMs can perform many NLP tasks but do not eliminate preprocessing, retrieval, data licensing, evaluation, privacy, multilingual imbalance, or production constraints. [Large Language Models](/en/large-language-models) covers Transformer scaling, pre-training, post-training, RAG, tool use, evaluation, and inference engineering. This course focuses on language data and NLP tasks. Structured extraction from an LLM should still be validated: ```text text | v LLM / NLP model | v candidate structure | v schema validation | v domain rules | v persistent result ``` RAG depends on retrieval quality. Turkish chunking, normalization, multilingual embeddings, reranking, and token budget all affect the final answer. ## Unit 19: Evaluation There is no universal NLP score. Classification may use precision, recall, F1, PR curves, and calibration. Sequence labeling requires explicit boundary policy. Dependency parsing evaluates heads and relations. ASR commonly uses WER and CER. Machine translation uses automatic metrics as proxies; semantic adequacy and human judgment remain separate considerations. Macro and micro averaging answer different questions under class imbalance. Robust Turkish evaluation should include clean text together with spelling variation, ASCII Turkish, transcripts, domain shift, code-switching, proper names, dates, and numbers when these are relevant to the target application. ## Unit 20: Production Engineering An NLP service must satisfy accuracy, latency, throughput, memory, fault isolation, reproducibility, privacy, versioning, and observability constraints together. ```text UTF-8 text | v normalization | v tokenization | v model inference | v output validation | v domain model ``` Preprocessing code is part of the model contract. Changing normalization without retraining or re-evaluating can create distribution shift. Batch workloads optimize throughput; interactive systems care about p95/p99 latency. GPU batching can improve throughput while increasing queue delay. Deterministic preprocessing can be cached safely with an explicit version key. Generative output may require a different caching contract. Offline and privacy-sensitive NLP additionally requires explicit model licensing, local compute sizing, update procedures, and sensitive-log handling. ## Unit 21: Robustness and Security Language input is untrusted input. Length limits, Unicode normalization policies, timeouts, quotas, and output schemas belong to service security. LLM applications add prompt injection: natural language can become a control channel rather than passive data. Authorization must remain outside the model. Sensitive information inside text can include names, identifiers, health data, or communication records. Removing filenames does not anonymize such content. ## Unit 22: Turkish-Centered Engineering Patterns A search system should often retain multiple representations rather than destructively normalize its canonical field: ```text canonical text | +-> exact index | +-> case-normalized index | +-> ASCII auxiliary index | +-> phonetic candidate index ``` The original representation remains authoritative. [Choosing Methods for Turkish Text Normalization and Phonetic Matching](/en/choosing-turkish-text-normalization-and-phonetic-matching-methods) develops this design choice in more detail. The open-source [Turkish Finite-State Syllabifier](/en/turkish-finite-state-syllabifier) shows that a deterministic state machine can be the right solution for a narrow linguistic task. The open-source [Turkish Numeric Soundex](/en/turkish-numeric-soundex) shows how a small phonetic key can reduce a candidate set without pretending to establish identity. [Natural Language Processing and Multimedia](/en/natural-language-processing-and-multimedia) connects text with OCR, speech, and other media-derived language. ## Unit 23: Comparing the Same Task Across Languages Tokenization differs by language: ```text Turkish: whitespace is useful + productive suffixes + morphology/subwords matter English: whitespace is a strong baseline + contractions and multiword expressions Chinese: word spaces are not mandatory + segmentation is part of modeling Japanese: mixed scripts + explicit morphological segmentation ``` Morphology differs: ```text Turkish: root + productive suffix chain Arabic: root + pattern + attached elements English: lighter inflection + more separate function words German: inflection + productive compounds ``` Syntax also differs. English relies heavily on word order, while Turkish case marking allows more flexibility. Cross-lingual transfer should therefore be evaluated, not assumed. A shared multilingual model and shared tokenizer do not create linguistic equality by themselves. ## Unit 24: Engineering Principles A robust NLP system should keep the following principles visible: 1. Language data is more than a character string. 2. Document information loss introduced by normalization. 3. Do not equate model tokens with linguistic words. 4. Treat Turkish morphology as a central source of representation sparsity. 5. Keep classical methods as measurable baselines. 6. Do not use model size as a quality metric. 7. Prevent document-level and source-level data leakage. 8. Test domain and language variation explicitly. 9. Analyze error classes, not only average scores. 10. Version tokenizer, normalization, and model together. 11. Define sensitive-data lifecycle before model architecture. 12. Keep hard business constraints outside probabilistic inference when possible. 13. Avoid rigid rules where uncertainty genuinely requires learned models. 14. Do not assume multilingual models represent all languages equally. 15. Validate generated structure before turning it into persistent state. ## Relationship to Artificial Intelligence NLP is one of the longest-running problem areas in artificial intelligence, but NLP and AI are not synonyms. [Artificial Intelligence: Philosophy, Theory and Practice](/en/artificial-intelligence-philosophy-theory-practice) provides the broader framework for discussing understanding, intelligence, agency, and consciousness. Fluent language generation is behavioral evidence of linguistic capability; it does not by itself establish human-like intention or consciousness. [Neural Networks and Learning Models](/en/artificial-neural-networks-and-learning-models) provides the learning machinery behind embeddings, sequence models, attention, Transformers, and modern NLP. NLP adds the linguistic representation and task structure. [Statistical Learning and Machine Learning](/en/statistical-learning-machine-learning) provides probability, classification, generalization, evaluation, HMMs, and distribution-shift concepts that remain relevant across both classical and neural NLP. [Logic Programming and Prolog](/en/logic-programming-and-prolog) connects NLP with symbolic grammar, semantic representation, and rule-based inference. Neural extraction followed by Prolog or formal constraint checking is a practical neuro-symbolic pattern. [Fuzzy Logic](/en/fuzzy-logic) models graded concepts through membership values. Token probabilities from a language model are not fuzzy membership degrees; they answer different modeling questions. [Genetic Algorithms and Applications](/en/genetic-algorithms-and-applications) are not NLP models by themselves but may be used for external search problems such as feature selection or hyperparameter optimization. [Large Language Models](/en/large-language-models) develops the generative-model layer in detail. ```text NLP = language data + representation + task + evaluation + system LLM = a powerful model family that can perform many NLP tasks LLM != all of NLP ``` The engineering objective is not to choose one historical paradigm. It is to decide which parts of a language problem require explicit rules, which require statistical learning, and which require formal validation. ## References ### Turkish NLP and language resources - Kemal Oflazer; Murat Saraçlar (eds.). *Turkish Natural Language Processing*. Springer, 2018. DOI: https://doi.org/10.1007/978-3-319-90165-7 - Kemal Oflazer. “Two-level Description of Turkish Morphology.” *Literary and Linguistic Computing*, 9(2), 1994, 137–148. DOI: https://doi.org/10.1093/llc/9.2.137 - Haşim Sak; Tunga Güngör; Murat Saraçlar. “Resources for Turkish Morphological Processing.” *Language Resources and Evaluation*, 45(2), 2011, 249–261. DOI: https://doi.org/10.1007/s10579-010-9128-6 - Utku Türk et al. “Resources for Turkish Dependency Parsing: Introducing the BOUN Treebank and the BoAT Annotation Tool.” *Language Resources and Evaluation*, 56, 2022, 259–307. DOI: https://doi.org/10.1007/s10579-021-09558-0 - Universal Dependencies. *UD Turkish BOUN*. https://universaldependencies.org/treebanks/tr_boun/ - Universal Dependencies. *UD Turkish IMST*. https://universaldependencies.org/treebanks/tr_imst/ ### Classical NLP, grammar, and statistical methods - Steven Bird; Ewan Klein; Edward Loper. *Natural Language Processing with Python*. O’Reilly Media, 2009. ISBN 978-0-596-51649-9. - Frederick Jelinek. *Statistical Methods for Speech Recognition*. MIT Press, 1997. - Stanley F. Chen; Joshua Goodman. “An Empirical Study of Smoothing Techniques for Language Modeling.” Harvard Computer Science Group Technical Report TR-10-98, 1998. - John Lafferty; Andrew McCallum; Fernando Pereira. “Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data.” *ICML*, 2001. - Fernando C. N. Pereira; David H. D. Warren. “Definite Clause Grammars for Language Analysis.” *Artificial Intelligence*, 13(3), 1980, 231–278. - Marie-Catherine de Marneffe; Christopher D. Manning; Joakim Nivre; Daniel Zeman. “Universal Dependencies.” *Computational Linguistics*, 47(2), 2021, 255–308. DOI: https://doi.org/10.1162/coli_a_00402 ### Subwords and representations - Tomas Mikolov et al. “Efficient Estimation of Word Representations in Vector Space.” 2013. https://arxiv.org/abs/1301.3781 - Jeffrey Pennington; Richard Socher; Christopher D. Manning. “GloVe: Global Vectors for Word Representation.” *EMNLP*, 2014. https://aclanthology.org/D14-1162/ - Piotr Bojanowski et al. “Enriching Word Vectors with Subword Information.” *Transactions of the Association for Computational Linguistics*, 5, 2017, 135–146. https://aclanthology.org/Q17-1010/ - Rico Sennrich; Barry Haddow; Alexandra Birch. “Neural Machine Translation of Rare Words with Subword Units.” *ACL*, 2016. https://aclanthology.org/P16-1162/ - Taku Kudo; John Richardson. “SentencePiece: A Simple and Language Independent Subword Tokenizer and Detokenizer for Neural Text Processing.” *EMNLP System Demonstrations*, 2018. DOI: https://doi.org/10.18653/v1/D18-2012 ### Neural NLP and Transformers - Ilya Sutskever; Oriol Vinyals; Quoc V. Le. “Sequence to Sequence Learning with Neural Networks.” *NeurIPS*, 2014. - Dzmitry Bahdanau; Kyunghyun Cho; Yoshua Bengio. “Neural Machine Translation by Jointly Learning to Align and Translate.” *ICLR*, 2015. https://arxiv.org/abs/1409.0473 - Ashish Vaswani et al. “Attention Is All You Need.” *NeurIPS*, 2017. https://arxiv.org/abs/1706.03762 - Jacob Devlin; Ming-Wei Chang; Kenton Lee; Kristina Toutanova. “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.” 2018. https://arxiv.org/abs/1810.04805 - Alexis Conneau et al. “Unsupervised Cross-lingual Representation Learning at Scale.” 2019. https://arxiv.org/abs/1911.02116 - Marta R. Costa-jussà et al. “No Language Left Behind: Scaling Human-Centered Machine Translation.” 2022. https://arxiv.org/abs/2207.04672 - Alec Radford et al. “Robust Speech Recognition via Large-Scale Weak Supervision.” 2022. https://arxiv.org/abs/2212.04356 ### Current general reference - Daniel Jurafsky; James H. Martin. *Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition with Language Models*. 3rd edition online manuscript, August 19, 2026. https://web.stanford.edu/~jurafsky/slp3/ ## Cite This Work Köker, M. A. (2018). Natural Language Processing. alikoker.com.tr. https://alikoker.com.tr/en/natural-language-processing - BibTeX: https://alikoker.com.tr/en/natural-language-processing.bib - RIS: https://alikoker.com.tr/en/natural-language-processing.ris - CSL-JSON: https://alikoker.com.tr/en/natural-language-processing.csl.json