Freebase QA: Information Extraction or Semantic Parsing?

By Xuchen Yao, Jonathan Berant, Benjamin Van Durme. 2014

57 citations recorded by the source corpus.

We contrast two seemingly distinct approaches to the task of question answering (QA) using Freebase: one based on information extraction techniques, the other on semantic parsing. Results over the same test-set were collected from two state-ofthe-art, open-source systems, then analyzed in consultation with those systems’ creators. We conclude that the differences between these technologies, both in task performance, and in how they get there, is not significant. This suggests that the semantic parsing community should target answering more compositional open-domain questions that are beyond the reach of more direct information extraction methods.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks (2015, background): “We show our proposed approach does indeed give improved performance on some tasks, but is still unable to solve some of them, which we consider as open problems.”
Machine Comprehension with Syntax, Frames, and Semantics (2015, background): “Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Short Papers), pages 700–706, Beijing, China, July 26-31, 2015. c©2015 Association for Computational Linguistics”
Improved Neural Relation Detection for Knowledge Base Question Answering (2017, background): “Knowledge Base Question Answering (KBQA) systems answer questions by obtaining information from KB tuples (Berant et al., 2013; Yao et al., 2014; Bordes et al., 2015; Bast and Haussmann, 2015; Yih et al., 2015; Xu et al., 2016).”
Simpler Context-Dependent Logical Forms via Model Projections (2016, background): “Pa-supat and Liang (2014) and Wang et al. (2015) proposed generating logical forms without alignments, similar to our Model B. Yao et al. (2014) and Bordes et al. (2014) have explored predicting paths in a knowledge graph directly, which is similar to the ﬂat logical forms of Model C. Relaxation…”
Knowledge Graph and Corpus Driven Segmentation and Answer Inference for Telegraphic Entity-seeking Queries (2014, background): “Very recently, (Yao et al., 2014) have concluded that for current benchmarks, deep parsing and shallow information extraction give comparable interpretation accuracy.”