%0 Conference Proceedings %T Identifying Domain Adjacent Instances for Semantic Parsers %A Ferguson, James %A Christensen, Janara %A Li, Edward %A Gonzàlez, Edgar %Y Riloff, Ellen %Y Chiang, David %Y Hockenmaier, Julia %Y Tsujii, Jun’ichi %S Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing %D 2018 %8 oct nov %I Association for Computational Linguistics %C Brussels, Belgium %F ferguson-etal-2018-identifying %X When the semantics of a sentence are not representable in a semantic parser’s output schema, parsing will inevitably fail. Detection of these instances is commonly treated as an out-of-domain classification problem. However, there is also a more subtle scenario in which the test data is drawn from the same domain. In addition to formalizing this problem of domain-adjacency, we present a comparison of various baselines that could be used to solve it. We also propose a new simple sentence representation that emphasizes words which are unexpected. This approach improves the performance of a downstream semantic parser run on in-domain and domain-adjacent instances. %R 10.18653/v1/D18-1539 %U https://aclanthology.org/D18-1539 %U https://doi.org/10.18653/v1/D18-1539 %P 4964-4969