Path-based vs. Distributional Information in Recognizing Lexical Semantic Relations

Recognizing various semantic relations between terms is beneficial for many NLP tasks. While path-based and distributional information sources are considered complementary for this task, the superior results the latter showed recently suggested that the former's contribution might have become obsolete. We follow the recent success of an integrated neural method for hypernymy detection (Shwartz et al., 2016) and extend it to recognize multiple relations. The empirical results show that this method is effective in the multiclass setting as well. We further show that the path-based information source always contributes to the classification, and analyze the cases in which it mostly complements the distributional information.

[1]  Ido Dagan,et al.  Integrating Pattern-Based and Distributional Similarity Methods for Lexical Entailment Acquisition , 2006, ACL.

[2]  Ido Dagan,et al.  Improving Hypernymy Detection with an Integrated Path-based and Distributional Method , 2016, ACL.

[3]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[4]  Chu-Ren Huang,et al.  Nine Features in a Random Forest to Learn Taxonomical Semantic Relations , 2016, LREC.

[5]  Graeme Hirst,et al.  Computing Lexical Contrast , 2013, CL.

[6]  Alessandro Lenci,et al.  How we BLESSed distributional semantic evaluation , 2011, GEMS.

[7]  Daniel Jurafsky,et al.  Learning Syntactic Patterns for Automatic Hypernym Discovery , 2004, NIPS.

[8]  Núria Bel,et al.  Reading Between the Lines: Overcoming Data Sparsity for Accurate Classification of Lexical Relationships , 2015, *SEM@NAACL-HLT.

[9]  Yves Peirsman,et al.  Proceedings of the GEMS 2011 Workshop on GEometrical Models of Natural Language Semantics , 2011 .

[10]  Gemma Boleda,et al.  Inclusive yet Selective: Supervised Distributional Hypernymy Detection , 2014, COLING.

[11]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[12]  Omer Levy,et al.  Do Supervised Distributional Methods Really Learn Lexical Inference Relations? , 2015, NAACL.

[13]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[14]  Daniel Jurafsky,et al.  Semantic Taxonomy Induction from Heterogenous Evidence , 2006, ACL.

[15]  Catherine Havasi,et al.  ConceptNet 5: A Large Semantic Network for Relational Knowledge , 2013, The People's Web Meets NLP.

[16]  Chu-Ren Huang,et al.  EVALution 1.0: an Evolving Semantic Dataset for Training and Evaluation of Distributional Semantic Models , 2015, LDL@IJCNLP.

[17]  Katrin Erk,et al.  Relations such as Hypernymy: Identifying and Exploiting Hearst Patterns in Distributional Vectors for Lexical Entailment , 2016, EMNLP.

[18]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[19]  Ido Dagan,et al.  CogALex-V Shared Task: LexNET - Integrated Path-based and Distributional Method for the Identification of Semantic Relations , 2016, CogALex@COLING.

[20]  Zornitsa Kozareva,et al.  A Semi-Supervised Method to Learn and Construct Taxonomies Using the Web , 2010, EMNLP.

[21]  Raffaella Bernardi,et al.  Entailment above the word level in distributional semantics , 2012, EACL.

[22]  Andrew McCallum,et al.  Relation Extraction with Matrix Factorization and Universal Schemas , 2013, NAACL.

[23]  Malvina Nissim,et al.  Adding Semantics to Data-Driven Paraphrasing , 2015, ACL.

[24]  Chu-Ren Huang,et al.  Unsupervised Antonym-Synonym Discrimination in Vector Space , 2014 .

[25]  David J. Weir,et al.  Learning to Distinguish Hypernyms and Co-Hyponyms , 2014, COLING.

[26]  Christopher Potts,et al.  Learning Distributed Word Representations for Natural Logic Reasoning , 2014, AAAI Spring Symposia.

[27]  Marti A. Hearst.  Automatic Acquisition of Hyponyms from Large Text Corpora , 1992, COLING.

[28]  Gerhard Weikum,et al.  PATTY: A Taxonomy of Relational Patterns with Semantic Types , 2012, EMNLP.