Spatial Language Understanding
Malihe Alikhani, Jason Baldridge, Mohit Bansal, Archna Bhatia, Parisa Kordjamshidi and Marie-Francine Moens
Time (PDT) | Event | Hosts |
---|---|---|
Nov 19, (13:00-14:00 UTC) | QA/Poster |
SpLU Organizers |
Nov 19, (14:00-14:10 UTC) | Opening Talk |
Parisa Kordjamshidi |
Nov 19, (14:10-15:00 UTC) | Invited talk 1: James Pustejovsky |
Parisa Kordjamshidi |
Nov 19, (15:00-15:56 UTC) | Paper Presentations |
Parisa Kordjamshidi |
Nov 19, (15:00-15:14 UTC) | An Element-wise Visual-enhanced BiLSTM-CRF Model for Location Name Recognition |
Parisa Kordjamshidi |
Nov 19, (15:14-15:28 UTC) | BERT-based Spatial Information Extraction |
Parisa Kordjamshidi |
Nov 19, (15:28-15:42 UTC) | A Cognitively Motivated Approach to Spatial Information Extraction |
Parisa Kordjamshidi |
Nov 19, (15:42-15:56 UTC) | Language-Conditioned Feature Pyramids for Visual Selection Tasks |
Parisa Kordjamshidi |
Nov 19, (15:56-16:05 UTC) | Break |
Parisa Kordjamshidi |
Nov 19, (16:05-16:55 UTC) | Invited talk 2: Julia Hockenmeir |
Archna Bhatia |
Nov 19, (16:55-17:51 UTC) | Paper Presentations |
Archna Bhatia |
Nov 19, (16:55-17:09 UTC) | They are not all alike: answering different spatial questions requires different grounding strategies |
Archna Bhatia |
Nov 19, (17:09-17:23 UTC) | Categorisation, Typicality and Object-Specific Features in Spatial Referring Expressions |
Archna Bhatia |
Nov 19, (17:23-17:37 UTC) | A Linguistic Analysis of Visually Grounded Dialogues Based on Spatial Expressions |
Archna Bhatia |
Nov 19, (17:37-17:51 UTC) | Visually-Grounded Planning without Vision: Language Models Infer Detailed Plans from High-level Instructions |
Archna Bhatia |
Nov 19, (17:51-18:00 UTC) | Break |
TBD |
Nov 19, (18:00-18:50 UTC) | Invited talk 3: Yoav Artzi |
Parisa Kordjamshidi |
Nov 19, (18:50-19:46 UTC) | Paper Presentations |
Parisa Kordjamshidi |
Nov 19, (18:50-19:04 UTC) | A Hybrid Deep Learning Approach for Spatial Trigger Extraction from Radiology Reports |
Parisa Kordjamshidi |
Nov 19, (19:04-19:18 UTC) | Retouchdown: Releasing Touchdown on StreetLearn as a Public Resource for Language Grounding Tasks in Street View |
Parisa Kordjamshidi |
Nov 19, (19:18-19:32 UTC) | SpaRTQA: A Textual Question Answering Benchmark for Spatial Reasoning |
Parisa Kordjamshidi |
Nov 19, (19:32-19:46 UTC) | Decoding Language Spatial Relations to 2D Spatial Arrangements |
Parisa Kordjamshidi |
Nov 19, (19:46-20:45 UTC) | QA/Poster |
SpLU Organizers |
Nov 19, (20:45-21:35 UTC) | Invited talk 4: Bonnie Dorr |
Parisa Kordjamshidi |
Nov 19, (21:35-22:31 UTC) | Paper Presentations |
Parisa Kordjamshidi |
Nov 19, (21:35-21:49 UTC) | Geocoding with multi-level loss for spatial language representation |
Parisa Kordjamshidi |
Nov 19, (21:49-22:03 UTC) | Vision-and-Language Navigation by Reasoning over Spatial Configurations |
Parisa Kordjamshidi |
Nov 19, (22:03-22:17 UTC) | LiMiT: The Literal Motion in Text Dataset |
Parisa Kordjamshidi |
Nov 19, (22:17-22:31 UTC) | ARRAMON: A Joint Navigation-Assembly Instruction Interpretation Task in Dynamic Environments |
Parisa Kordjamshidi |
Nov 19, (22:31-22:45 UTC) | Break |
TBD |
Nov 19, (22:45-23:35 UTC) | Invited Talk 5: Douwe Kiela |
Malihe Alikhani |
Nov 19, (23:35-00:03 UTC) | Paper Presentations |
Malihe Alikhani |
Nov 19, (23:35-23:49 UTC) | Robust and Interpretable Grounding of Spatial References with Relation Networks |
Malihe Alikhani |
Nov 19, (23:49-00:03 UTC) | RMM: A Recursive Mental Model for Dialogue Navigation |
Malihe Alikhani |
Nov 20, (00:03-01:00 UTC) | Panel Discussion |
Parisa Kordjamshidi |
Nov 20, (01:00-02:00 UTC) | QA/Poster |
SpLU Organizers |
Pre-recorded Plenary Talks
Visualizing Meaning: Semantic Simulation of Actions and Events
James Pustejovsky, Brandeis University
Collaborative Construction and Communication with Minecraft
Julia Hockenmaier, University of Illinois at Urbana-Champaign
Lexical Conceptual Structure: Spatial Representations for AI Applications
Bonnie Dorr, Florida Institute for Human and Machine Cognition
Few-shot Grounding, Mapping and Plan Generation for Instruction Following
Yoav Artzi, Cornell University