Date |
Topic |
Readings |
Presenters (Slides) |
8/29 |
The Grounding Problem, Learning from Data vs. Programming with Language, Explanation-Based Learning, Course Overview |
[1-6] |
Katerina
(Intro.pdf) |
9/5 |
Grounding language on programs(I): Executable Semantic Parsing |
[16-19] |
Katerina, Tejas, Sarah
(18.pdf,
16.pdf,
17.pdf) |
9/12 |
Compositionally of Meaning and Recursive networks, Pointer Networks |
[20-24, 53, 69] |
Katerina, Ricson
(RNNsPNs.pdf,
20.pdf) |
9/19 |
Grounding Language on Visual Concepts (I) |
[43-47, 70-72] |
Nikhil, Rishub, Ben, Katerina
(43.pdf,
44.pdf,
70.pdf,
71.pdf) |
9/26 |
Grounding Language on Visual Programs (II) |
[35-37, 74-75] |
Sumedha, Siliang, Sarah, Arjun
(37.pdf,
75.pdf) |
10/3 |
Grounding Language through Multi-Agent Collaboration |
[48-51] |
Manasi, Arjun, Ricson, Varun, Siliang, Deepika
(49.pdf, 44.pdf) |
10/10 |
Language and Memory State Representations: Architectures that Keep Track of State |
[26-29, 73] |
Mohit, Tanmay, Ricson, Varun, Siliang
(27.pdf,
28.pdf,
29.pdf) |
10/17 |
Neural-Symbolic Architecture, Rule-based NN |
[7-8, 76-81] |
Rishub, Varun, Ricson, Sumedha, Ben, Sarah
(7.pdf,
78.pdf,
81.pdf) |
10/24 |
Learning Theorem Proving, Neural-Symbolic Architectures, Rule-based NN |
[11-14] |
Ricson, Varun, Rishub, Nikhil
(13.pdf) |
10/31 |
Grounding Language on Programs: Program Induction |
[30-34] |
Mohit, Ben, Varun, Ricson, Sumedha
(31.pdf,
32.pdf) |
11/7 |
Conversational Agents |
[88-91] |
Ricson, Varun, Sarah, Rhea, Arjun, Deepika, Siliang
(89.pdf,
90.pdf) |
11/14 |
Grounding Language to Robotic Programs (I) |
[57-59, 67-68] |
Siliang, Deepika, Rishub, Ricson
(57.pdf,
58.pdf,
59.pdf) |
11/21 |
Grounding Language to Robotic Programs (II) |
[60-65] |
Ricson, Deepika, Siliang, Rhea, Sarah
(60.pdf,
63.pdf,
64.pdf) |
11/28 |
Weakly Supervised Semantic Parsing |
[82-87] |
Mohit, Sumedha, Arjun, Rhea, Ben, Deepika
(85.pdf,
87.pdf) |
12/5 |
Future of Language Grounding |
|
Katerina |
|
This course assumes familiarity with Computer Vision, basic NLP concepts, machine learning, deep learning.