Background | Once a semantic parser is trained, it can be used at test time to transform novel instructions into formal navigation plans which are then carried out by a virtual robot (MacMahon et al., 2006). |
Experiments | The second task is evaluating the performance of the semantic parsers trained on the disambiguated data. |
Experiments | For the second and third tasks, we train a semantic parser on the automatically disambiguated data, and test on sentences from the third, unseen map. |
Experiments | Other than the modifications discussed, we use the same components as their system including using KRISP to train the semantic parsers and using the execution module from MacMahon et al. |
Online Lexicon Learning Algorithm | To train a semantic parser using KRISP (Kate and Mooney, 2006), they had to supply a MRG, a context-free grammar, for their formal navigation plan language. |