University of Cambridge > Talks.cam > NLIP Seminar Series > Exploring Feedback Comment Generation for Language Learners

Exploring Feedback Comment Generation for Language Learners

Add to your list(s) Download to your calendar using vCal

  • UserRyo Nagata (Konan University)
  • ClockFriday 15 October 2021, 12:00-13:00
  • HouseVirtual (Zoom).

If you have a question about this talk, please contact Huiyuan Xie.

Join Zoom Meeting https://cl-cam-ac-uk.zoom.us/j/95503034642?pwd=NTF0RS8xZXdtN2ErQkt4N2ozaVBrZz09

Meeting ID: 955 0303 4642 Passcode: 654610

In this talk, I explore a task called feedback comment generation for language learners. It is a task of generating explanatory notes or hints facilitating writing learning. To begin with, through my personal and research experiences, I discuss how difficult English can be for non-native speakers of English, especially, for those whose mother tongue is a genetically unrelated language (e.g, Japanese) (for instance, I had a hard time to determine which is better, “based on/through my experience/experiences”, and am still not quite sure). Feedback comments help learners understand why their writings are not good together with underlying rules. Following this, I talk about several generation methods together with the datasets for research in feedback comment generation. I compare these generation methods to discuss their advantages and disadvantages. Finally, I summarize the talk with promising future directions.

This talk is part of the NLIP Seminar Series series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2021 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity