Institute of Formal and Applied Linguistics
Charles University, Czech Republic
Faculty of Mathematics and Physics
Master or Bachelor Thesis at ÚFAL
If you think about a thesis concerning language technologies, then the best way to proceed is to contact us at thesis@ufal.mff.cuni.cz (feel free to write either in Czech, Slovak or English). Alternatively, if you prefer contacting individual prospective supervisors, you are welcome to do so.
- If you have a topic or area of interest of your own, we will be very glad to hear about it!
- We also list the overview of areas we at ÚFAL are actively working on, so please share with us what kind of language technologies do you find interesting.
Machine Translation NLPProgress
- Best Systems for Czech and Other Languages Translation
- Offline Machine Translation Bergamot
- Live Translation ELITR
- Multimodal Translation Multi30k
Dialogue Systems NLPProgress
Interactive text-based or speech-based systems that help fulfill tasks (e.g. booking tickets, searching for bus connections, restaurant recommendation). Works on this can include:
- End-to-end neural systems (see e.g. this shared task challenge or this dataset)
- Dialogue system components: Language understanding, dialogue management
- Chatbots Details
Chatbots are interactive systems that can converse about any topic and keep the user entertained. Works on this topic include:
- Neural generative chatbot models
- [Information-retrieval-based models
- Automatic Speech Recognition UWebASR NLPProgress
- Text to Speech
- Language Generation Details
This can include response generation for dialogue systems as well as data-to-text generation (weather reports, sports reports etc.) or surface realization (generating text from semantic/syntactic trees).
Morphosyntactic Analysis
- Part of Speech Tagging, Lemmatization UDPipe MorphoDiTa UD PDT NLPProgress Details
Current Czech best results on arXiv.org.
- Dependency Parsing UDPipe UD PDT NLPProgress Details
Current Czech best results on arXiv.org.
- Derivational Morphology DeriNet
Natural Language Understanding
- Semantic Parsing PDT NLPProgress
- Discourse Analysis, Coreference Resolution PDT Details
Discourse analysis includes among others:
- Discourse Connectives NLPProgress
- Implicit Discourse Relations
- Question Answering SQuAD NLPProgress
- Summarization SumeCzech NLPProgress
Named Entities
- Named Entity Recognition NameTag CNEC NLPProgress Details
Current Czech best results on arXiv.org.
- Named Entity Linking NLPProgress
- Relationship Extraction NLPProgress
Applications
- Grammar Error Correction Korektor AKCES-GEC NLPProgress
- Optical Character Recognition NLPServices Details
Detailed description of the thesis in SIS