LAB LOGA page on LabLog, a review site (not the lab's official page)
Text Media Lab
Machine-translated · View original
A lab that builds artificial intelligence that understands and explains text using language models.
AboutAbout the lab
Artificial intelligence for words and text.
The Text Media Lab (Large-Scale Text Archives Group, Academic Center for Computing and Media Studies) conducts research on artificial intelligence for language and text, centered on language models and their applications.
The lab also works on information retrieval, image and language understanding, and applications to history.
Its research results are not only presented at international conferences and in journals, but also used at Kyoto University's libraries and Institute for Information Management and Communication, as well as at other universities and companies.
Key terms
- Language model
- A model that learns how likely a sequence of words in a text is, and is used to understand and generate sentences
- Natural language processing
- Technology that lets computers handle human language, understanding and generating it
- Flow graph
- A diagram that represents the steps of a task or the flow of materials as connected nodes
- Symbol grounding
- Linking words to the actual things and situations they refer to
ResearchResearch themes
The lab works on understanding and generating procedural documents, computers that explain data analysis results in words, text analysis for scholarship, fundamental text analysis, and building and releasing language resources.
*Illustrative imageUnderstanding and Generating Procedural Documents
The lab studies “understanding,” the ultimate goal of natural language processing. For procedural documents, which describe what to do and how, meaning can be represented with a flow graph.
*Illustrative imageComputers That Explain Analysis and Prediction Results
The lab aims to have computers explain the results of data analysis and prediction in words by themselves. What to say is decided through symbol grounding, and how to say it is learned from a large number of example sentences in order to generate text.
*Illustrative imageInformation Extraction from Historical Materials
The lab works on extracting and analyzing advanced information from historical materials, applying language research to history.
MembersFaculty
- ProfessorShinsuke Mori
- Associate ProfessorKazuma Hashimoto
- Assistant ProfessorHirotaka Kameko
- Assistant ProfessorKohei Yamashita
- Assistant ProfessorHiyori Takebe
VoicesStudent voices
Ratings and reviews reflect the experiences of individual current or former students, not the lab's official views. Whether a lab has reviews, or how many, says nothing about the lab itself.
Students who take part in an interview may receive a thank-you gift worth ¥1,000, regardless of what they say.
Student ratings (0 students)
--
--
--
--
--
--
Student voices answer questions like these
- What's great about this lab?
- What did you learn after joining?
- What's the vibe, and what is the professor like?
- Who is this lab for?
- Where do graduates go?
Your experience can help younger students choose their lab. Your name won't be shown.
Write a lab reviewAnonymous · Your draft is saved if you stopRelatedLabs similar to Text Media Lab
Applied Analysis LabGraduate School of Informatics, Department of Informatics, Applied Analysis ChairFundamental analysis, probability theory, geometric analysis…
Computational Neuroscience Lab (Collaborative Unit)Graduate School of Informatics, Department of Informatics, Systems Science Course (Collaborative Unit)Computational neuroscience, brain-inspired information proce…
Cognitive Informatics LabGraduate School of Informatics, Department of Informatics, Brain and Cognitive Science ChairPerceptual information processing, cognitive neuroscience, e…
Large-Scale Data Utilization Infrastructure LabGraduate School of Informatics, Department of Informatics, Social Information Analysis Foundation Chair (Cooperating Chair)Distributed systems, computer systems, databases, large-scal…The information on this page is compiled by the LabLog team from the lab's public information and interviews. For corrections or removal requests, please contact LabLog, not the lab.
Report an errorAbout the images
The top and research theme images are illustrative and were not taken at the lab. They are cropped from Wikimedia Commons images. Cropped CC BY-SA images are provided under the same CC BY-SA license as the original (version shown on each line).
- Top image: “Books and Bookshelves in Mansueto Library” Micheal Kaluba / CC BY-SA 4.0 (cropped)
- Understanding and Generating Procedural Documents: “Curry Japanese Navy Cookbook 1908” MIKI Yoshihito / CC BY 2.0 (cropped)
- Computers That Explain Analysis and Prediction Results: “Weather forecast by JMA 20230511” 気象庁 / CC BY 4.0 (cropped)
- Information Extraction from Historical Materials: “Nanto Nenchu Gyoji Otabisho” 村井古道 / Public domain (cropped)
- Related lab (Applied Analysis Lab): “Julia-Menge -0,5R 0I 30062019” PantheraLeo1359531 / CC BY-SA 4.0 (cropped)
- Related lab (Computational Neuroscience Lab (Collaborative Unit)): “Nyt-Cajal DRAWING m1673-resized-for-web” Santiago Ramón y Cajal / Public domain (cropped)
- Related lab (Cognitive Informatics Lab): “Human eye iris 1” Kamil Saitov / CC BY 4.0 (cropped)
- Related lab (Large-Scale Data Utilization Infrastructure Lab): “Groß und klein” Friedrich Haag / CC BY-SA 4.0 (cropped)
About LabLog
LabLog is a lab review app for students only. Student members at each university interview students in labs and publish what they say. Student voices can only be read by students who sign up with a university email address. Operated by bestiee Inc.
Learn more about LabLog ↗Search engines and AI may reference the basic lab info and rating summaries on this page and the description of LabLog. Student voices are for student members only. Automated collection by programs (scraping, or input to or training of AI) is prohibited under Article 8 of the Terms of Service. If you need data for research or analysis, please contact us.