- Project Title
- Names of team members
- Research question.
- e.g., “What semantic structures can enable a robot to understand and use spatial language in realistic scenarios?”
- e.g., “How well can a model trained using GIZA++ follow natural language route instructions?”
- Significance. Why is it an important problem?
- Methodology.
- How are you going to solve it?
- How will you know if you've solved it?
- Related Work. Who else has addressed (aspects of) this problem? What did they do? How is their approach different from your approach?
- Schedule. The schedule should consist of dates and milestones. “Work on corpus collection” is not a milestone. “Collected a dataset of at least 1000 sentences” is a milestone.
- Who is responsible for what parts of the project?
Project proposal presentations will take place in class on Tuesday, October 8th and Thursday, October 10th. Each team will have approximately five minutes to present, and ten minutes for comments and discussions. You should be prepared to present on either day. I will make a schedule of presentations after I have all of the proposal documents on Sunday night.
Tuesday:
- Lauren Bilsky. Machine Translation using Grounded Language and Topic Modeling.
- Stephen Brawner. Task-based User Modeling in Shared Autonomy.
- Do Kook Choe. Navigation via Machine Translation.
- Izaak Baker and Nakul Gopalan. Athena.
- Andrew Kovacs and Sam Birch. Webtalk.
Thursday:
- Jun Ki Lee, Zhiqiang Sui. Learning Natural Language Commands for Robots in Home Environment Situations.
- Xiaolu Li , Zhe Zhao. Automatic Turtle Graphics.
- Tom Sgouros. SHRDLU updated: parsing with ambiguity and without rules.
- Miles Eldon and Kurt Spindler. Comparing Inference Algorithms for Grounding Trajectories.
- Yujie Wan, Lixing Lian. Learning Semantic Parser from Question-Answer Pairs.
- Charles Yeh and Bowei Wang. Application of SHRDLU in Minecraft.
No comments:
Post a Comment