Identifying Domain Adjacent Instances for Semantic Parsers

When the semantics of an input are not representable in a sematic 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.

• Natural Language Processing