Open IE as an Intermediate Structure for Semantic Tasks

@inproceedings{Stanovsky2015OpenIA,
  title={Open IE as an Intermediate Structure for Semantic Tasks},
  author={Gabriel Stanovsky and Ido Dagan and Mausam},
  booktitle={ACL},
  year={2015}
}
Semantic applications typically extract information from intermediate structures derived from sentences, such as dependency parse or semantic role labeling. In this paper, we study Open Information Extraction’s (Open IE) output as an additional intermediate structure and find that for tasks such as text comprehension, word similarity and word analogy it can be very effective. Specifically, for word analogy, Open IE-based embeddings surpass the state of the art. We suggest that semantic… Expand
50 Citations
Extraction Systems and Downstream Applications
  • Mausam
  • 2016
Open Information Extraction Systems and Downstream Applications
  • Mausam
  • Computer Science
  • IJCAI
  • 2016
Porting an Open Information Extraction System from English to German
A Consolidated Open Knowledge Representation for Multiple Texts
Open information extraction as an intermediate semantic structure for Persian text summarization
Open Information Extraction
Semantic Representation for Age Word Problems with Schemas
Affordance Extraction and Inference based on Semantic Role Labeling
Specifying and Annotating Reduced Argument Span Via QA-SRL
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 28 REFERENCES
Using Semantic Roles to Improve Question Answering
An analysis of open information extraction based on semantic role labeling
Open Language Learning for Information Extraction
Identifying Relations for Open Information Extraction
Learning Dependency-Based Compositional Semantics
Dependency-Based Word Embeddings
MaltParser: A Language-Independent System for Data-Driven Dependency Parsing
...
1
2
3
...