Open-Vocabulary Semantic Parsing with both Distributional Statistics and Formal Knowledge

  title={Open-Vocabulary Semantic Parsing with both Distributional Statistics and Formal Knowledge},
  author={Matt Gardner and Jayant Krishnamurthy},
Traditional semantic parsers map language onto compositional, executable queries in a fixed schema. This mapping allows them to effectively leverage the information contained in large, formal knowledge bases (KBs, e.g., Freebase) to answer questions, but it is also fundamentally limiting---these semantic parsers can only assign meaning to language that falls within the KB's manually-produced schema. Recently proposed methods for open vocabulary semantic parsing overcome this limitation by… CONTINUE READING

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • By giving open vocabulary semantic parsers direct access to KB information, we improve mean average precision on this task by over 120%.
  • Our combined model achieved relative gains of over 50% in mean average precision and mean reciprocal rank versus a purely distributional approach.
  • Taken together, the methods introduced in this paper improved mean average precision on our task from .163 to .370, a 127% relative improvement over prior work.


Publications citing this paper.