Look-up and Adapt: A One-shot Semantic Parser
This addresses the limitation of computing devices in handling natural language interactions beyond supported domains, though it appears incremental as it builds on existing parsing strategies.
The paper tackles the problem of semantic parsers failing on out-of-domain utterances by proposing a parser that adapts logical forms from seen examples, achieving up to 68.8% improvement in one-shot parsing compared to baselines.
Computing devices have recently become capable of interacting with their end users via natural language. However, they can only operate within a limited "supported" domain of discourse and fail drastically when faced with an out-of-domain utterance, mainly due to the limitations of their semantic parser. In this paper, we propose a semantic parser that generalizes to out-of-domain examples by learning a general strategy for parsing an unseen utterance through adapting the logical forms of seen utterances, instead of learning to generate a logical form from scratch. Our parser maintains a memory consisting of a representative subset of the seen utterances paired with their logical forms. Given an unseen utterance, our parser works by looking up a similar utterance from the memory and adapting its logical form until it fits the unseen utterance. Moreover, we present a data generation strategy for constructing utterance-logical form pairs from different domains. Our results show an improvement of up to 68.8% on one-shot parsing under two different evaluation settings compared to the baselines.