Olive Oil is Made of Olives, Baby Oil is Made for Babies: Interpreting Noun Compounds using Paraphrases in a Neural Model

Automatic interpretation of the relation between the constituents of a noun compound, e.g. olive oil (source) and baby oil (purpose) is an important task for many NLP applications. Recent approaches are typically based on either noun-compound representations or paraphrases. While the former has initially shown promising results, recent work suggests that the success stems from memorizing single prototypical words for each relation. We explore a neural paraphrasing approach that demonstrates superior performance when such memorization is not possible.

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

[2]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[3]  Preslav Nakov,et al.  SemEval-2013 Task 4: Free Paraphrases of Noun Compounds , 2013, SemEval@NAACL-HLT.

[4]  Mirella Lapata,et al.  Composition in Distributional Models of Semantics , 2010, Cogn. Sci..

[5]  Marco Baroni,et al.  Nouns are Vectors, Adjectives are Matrices: Representing Adjective-Noun Constructions in Semantic Space , 2010, EMNLP.

[6]  Ioannis Korkontzelos,et al.  Estimating Linear Models for Compositional Distributional Semantics , 2010, COLING.

[7]  Preslav Nakov,et al.  Using Verbs to Characterize Noun-Noun Relations , 2006, AIMSA.

[8]  D I A R M U I D ´ O S ´ E A G H D H A And A N N C O.  Interpreting compound nouns with kernel methods , 2012 .

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

[10]  Stephen Tratz.  Semantically-enriched parsing for natural language understanding , 2011 .

[11]  Fintan J. Costello,et al.  General and specific paraphrases of semantic relations between nouns , 2013, Natural Language Engineering.

[12]  Erhard W. Hinrichs,et al.  Automatic Noun Compound Interpretation using Deep Neural Networks and Word Embeddings , 2015, IWCS.

[13]  Soma Paul,et al.  A VSM-based Statistical Model for the Semantic Relation Interpretation of Noun-Modifier Pairs , 2015, RANLP.

[14]  Suresh Manandhar,et al.  An Empirical Study on Compositionality in Compound Nouns , 2011, IJCNLP.

[15]  Corina Dima.  On the Compositionality and Semantic Interpretation of English Noun Compounds , 2016, Rep4NLP@ACL.

[16]  Karen Sparck Jones.  Compound noun interpretation problems , 1986 .

[17]  Eduard H. Hovy,et al.  A Taxonomy, Dataset, and Classifier for Automatic Noun Compound Interpretation , 2010, ACL.

[18]  Andrew Y. Ng,et al.  Semantic Compositionality through Recursive Matrix-Vector Spaces , 2012, EMNLP.

[19]  Preslav Nakov,et al.  Large-Scale Noun Compound Interpretation Using Bootstrapping and the Web as a Corpus , 2011, EMNLP.

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

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

[22]  Tim Van de Cruys,et al.  MELODI: A Supervised Distributional Approach for Free Paraphrasing of Noun Compounds , 2013, *SEMEVAL.

[23]  Georgiana Dinu,et al.  General estimation and evaluation of compositional distributional semantic models , 2013, CVSM@ACL.

[24]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.