Semantic Role Labeling for Open Information Extraction

Open Information Extraction is a recent paradigm for machine reading from arbitrary text. In contrast to existing techniques, which have used only shallow syntactic features, we investigate the use of semantic features (semantic roles) for the task of Open IE. We compare TextRunner (Banko et al., 2007), a state of the art open extractor, with our novel extractor SRL-IE, which is based on UIUC's SRL system (Punyakanok et al., 2008). We find that SRL-IE is robust to noisy heterogeneous Web data and outperforms TextRunner on extraction quality. On the other hand, TextRunner performs over 2 orders of magnitude faster and achieves good precision in high locality and high redundancy extractions. These observations enable the construction of hybrid extractors that output higher quality results than TextRunner and similar quality as SRL-IE in much less time.

[1]  John B. Lowe,et al.  The Berkeley FrameNet Project , 1998, ACL.

[2]  Luis Gravano,et al.  Snowball: extracting relations from large plain-text collections , 2000, DL '00.

[3]  Martha Palmer,et al.  From TreeBank to PropBank , 2002, LREC.

[4]  Stephen Soderland,et al.  Learning Information Extraction Rules for Semi-Structured and Free Text , 1999, Machine Learning.

[5]  Doug Downey,et al.  A Probabilistic Model of Redundancy in Information Extraction , 2005, IJCAI.

[6]  Satoshi Sekine,et al.  Preemptive Information Extraction using Unrestricted Relation Discovery , 2006, NAACL.

[7]  Oren Etzioni,et al.  Machine Reading , 2006, AAAI.

[8]  Lenhart K. Schubert,et al.  Open Knowledge Extraction through Compositional Language Processing , 2008, STEP.

[9]  Oren Etzioni,et al.  Open Information Extraction from the Web , 2007, CACM.

[10]  Richard Johansson,et al.  The Effect of Syntactic Representation on Semantic Role Labeling , 2008, COLING.

[11]  Oren Etzioni,et al.  The Tradeoffs Between Open and Traditional Relation Extraction , 2008, ACL.

[12]  Christopher D. Manning,et al.  A Global Joint Model for Semantic Role Labeling , 2008, CL.

[13]  Dan Roth,et al.  The Importance of Syntactic Parsing and Inference in Semantic Role Labeling , 2008, CL.

[14]  Roberto Basili,et al.  Tree Kernels for Semantic Role Labeling , 2008, CL.

[15]  Daniel S. Weld,et al.  Using Wikipedia to bootstrap open information extraction , 2009, SGMD.

[16]  A. Akbik,et al.  Wanderlust : Extracting Semantic Relations from Natural Language Text Using Dependency Grammar Patterns , 2009 .

[17]  Tom M. Mitchell,et al.  Coupling Semi-Supervised Learning of Categories and Relations , 2009, HLT-NAACL 2009.

[18]  Alessandro Moschitti,et al.  Shallow Semantic Parsing for Spoken Language Understanding , 2009, NAACL.

[19]  Hoifung Poon,et al.  Unsupervised Semantic Parsing , 2009, EMNLP.