Toggle navigation
gokhanercan.com
reading
recording
teaching
publications
resources
about
contact
Publications
Külçe, A., Esen, A., Fikir, Ç., Kurt, B., Arar, K., Ercan, G. and Tek, F.B., 2026.
ECHO: A Locally-Deployable Agentic Health Assistant with Temporal Memory, Safety Guardrails, and Speech Assessment
arXiv preprint arXiv:2608.06110
[Paper]
[DOI]
Ercan, G. and Yıldız, O.T., 2025.
Grammar or Crammer? The Role of Morphology in Distinguishing Orthographically Similar but Semantically Unrelated Words
IEEE Access
[Data]
[Code]
[Paper]
[Details]
Top Journal
Ercan, G., 2024.
PhD Thesis: Semantic Relation Extraction by Enriching Word Embeddings Exploiting Turkish Morphology
Arıcan, B.N., Kuzgun, A., Marsan, B., Aslan, D.B., Sanıyar, E., Cesur, N., Kara, N., Kuyrukçu, O., Ozçelik, M., Yenice, A.B., Dogan, M., Oksal, C., Ercan, G. and Yıldız, O.T., 2022, June.
Morpholex Turkish: A Morphological Lexicon for Turkish.
In
LREC 2022 Workshop
Language Resources and Evaluation Conference 20-25 June 2022 (p. 68).
[Paper]
Yıldız, O.T., Avar, B. and Ercan, G., 2019, September.
An Open, Extendible, and Fast Turkish Morphological Analyzer
Recent Advances in Natural Language Processing (
RANLP 2019
).
[Paper]
[Code]
Ercan, G. and Yıldız, O.T., 2018, August.
AnlamVer: Semantic Model Evaluation Dataset for Turkish - Word Similarity and Relatedness
The 27th International Conference on Computational Linguistics (
COLING 2018
).
[Paper]
[Code]
[Data]
[Slides]
Top Conference
Best resource paper
Uludogan, G., Özçelik, R., Parlar, S., Ercan, G. and Yıldız, O.T.,
Türkçe Doğal Dil İşleme İçin Arayüzler.
Signal Processing and Communication Applications Conference, 2019, April
[Paper]
[Code]
Ercan, G., Erkek, O., Açıkgöz, O., Özçelik, R., Parlar, S. and Yıldız, O.T., 2018.
Türkçe Anlamsal Söylem ve Cümle Benzerliği Analizleri için Veri Kümesi Oluşturma Yöntemi.
In Computer Science and Engineering (UBMK), 2018 International Conference.
[Paper]
Yıldız, O.T., Ak, K., Ercan, G., Topsakal, O. and Asmazoglu, C., 2018, April.
A Multilayer Annotated Corpus for Turkish.
International Conference on Natural Language and Speech Processing (ICNLSP).
[Paper]
Ertopçu, B., Kanburoğlu, A.B., Topsakal, O., Açıkgöz, O., Gürkan, A.T., Özenç, B., Çam, İ., Avar, B., Ercan, G. and Yıldız, O.T., 2017, October.
A new approach for named entity recognition.
In Computer Science and Engineering (UBMK), 2017 International Conference on (pp. 474-479). IEEE.
[Paper]
[Slides]
Açıkgöz, O., Gürkan, A.T., Ertopçu, B., Topsakal, O., Özenç, B., Kanburoğlu, A.B., Çam, İ., Avar, B., Ercan, G. and Yıldız, O.T., 2017, October.
All-words word sense disambiguation for Turkish.
In Computer Science and Engineering (UBMK), 2017 International Conference on (pp. 490-495). IEEE.
[Paper]
Topsakal, O., Açıkgöz, O., Gürkan, A.T., Kanburoğlu, A.B., Ertopçu, B., Özenç, B., Çam, İ., Avar, B., Ercan, G. and Yıldız, O.T., 2017, October.
Shallow parsing in Turkish.
In Computer Science and Engineering (UBMK), 2017 International Conference on (pp. 480-485). IEEE.
[Paper]
Profile pages:
Google Scholar
,
ResearchGate
,
IEEE Xplore
.
Publons WoS
.
Reviewer
Signal Processing and Communications Applications Conference (SIU):
2026
,
2025
,
2024
,
2020
,
2019
International Conference on Computer Science and Engineering (UBMK): 2026
Artificial Intelligence Review - An International Science and Engineering Journal
(2019)
Gökhan Ercan
See it on X
The best programmers today will be the next generation of product managers.
Companies should stop this non-technical “Product Owner + Scrum Master” nonsense and start empowering their strongest engineers to own, prioritize, and deliver the backlog.
t.co/qGDM3zBUaQ
Read more
Oct 3, 2026
Gökhan Ercan
See it on X
A pleasure to teach Agentic AI this term at Istanbul Technical University.
We covered 17 agentic patterns: Agentic RAG, ReAct, Memory, Guardrails, multi-agent, Graph-of-Thoughts. Best part: seeing 40 student projects move from "use an LLM" to "design an agent."
Read more
Jun 25, 2026
Gökhan Ercan
See it on X
RT
@dhh
: Microservices is the software industry’s most successful confidence scam. It convinces small teams that they are “thinking big” while systematically destroying their ability to move at all. It flatters ambition by weaponizing insecurity: if you’re not running a constellation of services, are you even a real company? Never mind that this architecture was invented to cope with organizational dysfunction at planetary scale. Now it’s being prescribed to teams that still share a Slack channel and a lunch table.
Small teams run on shared context. That is their superpower. Everyone can reason end-to-end. Everyone can change anything. Microservices vaporize that advantage on contact. They replace shared understanding with distributed ignorance. No one owns the whole anymore. Everyone owns a shard. The system becomes something that merely happens to the team, rather than something the team actively understands. This isn’t sophistication. It’s abdication.
Then comes the operational farce. Each service demands its own pipeline, secrets, alerts, metrics, dashboards, permissions, backups, and rituals of appeasement. You don’t “deploy” anymore—you synchronize a fleet. One bug now requires a multi-service autopsy. A feature release becomes a coordination exercise across artificial borders you invented for no reason. You didn’t simplify your system. You shattered it and called the debris “architecture.”
Microservices also lock incompetence in amber. You are forced to define APIs before you understand your own business. Guesses become contracts. Bad ideas become permanent dependencies. Every early mistake metastasizes through the network. In a monolith, wrong thinking is corrected with a refactor. In microservices, wrong thinking becomes infrastructure. You don’t just regret it—you host it, version it, and monitor it.
The claim that monoliths don’t scale is one of the dumbest lies in modern engineering folklore. What doesn’t scale is chaos. What doesn’t scale is process cosplay. What doesn’t scale is pretending you’re Netflix while shipping a glorified CRUD app. Monoliths scale just fine when teams have discipline, tests, and restraint. But restraint isn’t fashionable, and boring doesn’t make conference talks.
Microservices for small teams is not a technical mistake—it is a philosophical failure. It announces, loudly, that the team does not trust itself to understand its own system. It replaces accountability with protocol and momentum with middleware. You don’t get “future proofing.” You get permanent drag. And by the time you finally earn the scale that might justify this circus, your speed, your clarity, and your product instincts will already be gone.
Read more
Dec 12, 2025
Gökhan Ercan
See it on X
RT
@ealpaydin
: "Scientists undertake basic research to generate new knowledge with no specific end goal in mind. Applied research is different in that it aims to find solutions to real-world problems."
t.co/3zQAg87EUy
Read more
Oct 5, 2025
Gökhan Ercan
See it on X
RT
@rohanpaul_ai
: "Hallucinations need not be mysterious—they originate simply as errors in binary classification.
If incorrect statements cannot be distinguished from facts, then hallucinations in pretrained language models will arise through natural statistical pressures."
- OpenAI Paper
Read more
Sep 6, 2025
Gökhan Ercan
See it on X
I really liked this OS analogy for LLMs. Strongly encourage watching the full speech by Karpathy.
t.co/df0wB6JqnU
Read more
Aug 23, 2025
Gokhan Ercan, 2026