Semantic Parsing on Freebase from Question-Answer Pairs

TLDR

The main challenge is narrowing the vast number of possible logical predicates for a given question. The paper trains a semantic parser that scales to Freebase. They learn from question‑answer pairs, building a coarse phrase‑to‑predicate mapping with a knowledge base and corpus, and use a bridging operation to generate additional predicates, also collecting a realistic dataset. On the Cai and Yates dataset the system outperforms the state‑of‑the‑art parser, and on the new dataset it improves over a natural baseline.

Abstract

In this paper, we train a semantic parser that scales up to Freebase. Instead of relying on annotated logical forms, which is especially expensive to obtain at large scale, we learn from question-answer pairs. The main challenge in this setting is narrowing down the huge number of possible logical predicates for a given question. We tackle this problem in two ways: First, we build a coarse mapping from phrases to predicates using a knowledge base and a large text corpus. Second, we use a bridging operation to generate additional predicates based on neighboring predicates. On the dataset of Cai and Yates (2013), despite not having annotated logical forms, our system outperforms their state-of-the-art parser. Additionally, we collected a more realistic and challenging dataset of question-answer pairs and improves over a natural baseline.