4 accepted papers
Incremental decision making in real-world environments is one of the most challenging tasks in embodied artificial intelligence. One particularly demanding scenario is Vision and Language Navigation (VLN) which requires visual and natural language understanding as well as spatial and temporal reason…
Vision and language navigation (VLN) is a challenging visually-grounded language understanding task. Given a natural language navigation instruction, a visual agent interacts with a graph-based environment equipped with panorama images and tries to follow the described route. Most prior work has bee…
Car-focused navigation services are based on turns and distances of named streets, whereas navigation instructions naturally used by humans are centered around physical objects called landmarks. We present a neural model that takes OpenStreetMap representations as input and learns to generate naviga…
The real-world performance of slot filling and intent detection task generally degrades due to transcription errors generated by speech recognition engine. The insertion, deletion, and mis-recognition errors from speech recognizer's front-end cause the mis-interpretation and mis-alignment of the lan…