论文信息 - Approaching Textual Entailment with LFG and FrameNet Frames

Approaching Textual Entailment with LFG and FrameNet Frames

We present a baseline system for modeling textual entailment that combines deep syntactic analysis with structured lexical meaning descriptions in the FrameNet paradigm. Textual entailment is approximated by degrees of structural and semantic overlap of text and hypothesis, which we measure in a match graph. The encoded measures of similarity are processed in a machine learning setting.1

Aljoscha Burchardt | Anette Frank | A. Burchardt | A. Frank

[1] K. Markert,et al. Combining Shallow and Deep NLP Methods for Recognizing Textual Entailment , 2005 .

[2] Katrin Erk,et al. Towards an LFG Syntax-Semantics Interface for Frame Semantics Annotation , 2004, CICLing.

[3] Ted Pedersen,et al. Extended Gloss Overlaps as a Measure of Semantic Relatedness , 2003, IJCAI.

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

[5] Katrin Erk,et al. HALMANESER – A Toolchain For Shallow Semantic Parsing , 2006 .

[6] Mark Johnson,et al. Parsing the Wall Street Journal using a Lexical-Functional Grammar and Discriminative Estimation Techniques , 2002, ACL.

[7] Adam Pease,et al. Linking Lixicons and Ontologies: Mapping WordNet to the Suggested Upper Merged Ontology , 2003, IKE.

[8] Ido Dagan,et al. The Third PASCAL Recognizing Textual Entailment Challenge , 2007, ACL-PASCAL@ACL.

[9] Dick Crouch,et al. Packed Rewriting for Mapping Semantics to KR , 2005 .

[10] Katrin Erk,et al. A WordNet Detour to FrameNet , 2005 .