We present data and methods that enable a supervised learning approach to Open Information Extraction (Open IE). Central to the approach is a novel formulation of Open IE as a sequence tagging problem, addressing challenges such as encoding multiple extractions for a predicate. We also develop a bi-LSTM transducer, extending recent deep Semantic Role Labeling models to extract Open IE tuples and provide confidence scores for tuning their precision-recall tradeoff. Furthermore, we show that the recently released Question-Answer Meaning Representation dataset can be automatically converted into an Open IE corpus which significantly increases the amount of available training data. Our supervised model, made publicly available, 1 outperforms the state-of-The-Art in Open IE on benchmark datasets.
|Title of host publication||Long Papers|
|Publisher||Association for Computational Linguistics (ACL)|
|Number of pages||11|
|State||Published - 2018|
|Event||2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2018 - New Orleans, United States|
Duration: 1 Jun 2018 → 6 Jun 2018
|Name||NAACL HLT 2018 - 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference|
|Conference||2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2018|
|Period||1/06/18 → 6/06/18|
Bibliographical noteFunding Information:
This work was supported in part by grants from the MAGNET program of the Israeli Office of the Chief Scientist (OCS); the German Research Foundation through the German-Israeli Project Cooperation (DIP, grant DA 1600/1-1); the Israel Science Foundation (grant No. 1157/16); the US NSF (IIS1252835,IIS-1562364); and an Allen Distinguished Investigator Award.
© 2018 The Association for Computational Linguistics.