GHH at SemEval-2018 Task 10: Discovering Discriminative Attributes in Distributional Semantics

This paper describes our system submission to the SemEval 2018 Task 10 on Capturing Discriminative Attributes. Given two concepts and an attribute, the task is to determine whether the attribute is semantically related to one concept and not the other. In this work we assume that discriminative attributes can be detected by discovering the association (or lack of association) between a pair of words. The hypothesis we test in this contribution is whether the semantic difference between two pairs of concepts can be treated in terms of measuring the distance between words in a vector space, or can simply be obtained as a by-product of word co-occurrence counts.

[1]  Randy Goebel,et al.  Web-Scale N-gram Models for Lexical Disambiguation , 2009, IJCAI.

[2]  Satoshi Matsuoka,et al.  Analogy-based detection of morphological and semantic relations with word embeddings: what works and what doesn’t. , 2016, NAACL.

[3]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[4]  Diana Inkpen,et al.  Comparison of Semantic Similarity for Different Languages Using the Google n-gram Corpus and Second-Order Co-occurrence Measures , 2011, Canadian Conference on AI.

[5]  Kenneth Ward Church,et al.  Using Web-scale N-grams to Improve Base NP Parsing Performance , 2010, COLING.

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

[7]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[8]  Geoffrey E. Hinton,et al.  Distributed Representations , 1986, The Philosophy of Artificial Intelligence.

[9]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[10]  Jason Weston,et al.  A unified architecture for natural language processing: deep neural networks with multitask learning , 2008, ICML '08.

[11]  Catherine Havasi,et al.  ConceptNet 5.5: An Open Multilingual Graph of General Knowledge , 2016, AAAI.

[12]  Christian Bizer,et al.  DBpedia: A Multilingual Cross-domain Knowledge Base , 2012, LREC.

[13]  Slav Petrov,et al.  Syntactic Annotations for the Google Books NGram Corpus , 2012, ACL.

[14]  Christiane Fellbaum,et al.  Book Reviews: WordNet: An Electronic Lexical Database , 1999, CL.

[15]  Geoffrey Zweig,et al.  Linguistic Regularities in Continuous Space Word Representations , 2013, NAACL.

[16]  Vlado Keselj,et al.  Comparing Word Relatedness Measures Based on Google $n$-grams , 2012, COLING.

[17]  Laura Kallmeyer,et al.  CogALex-V Shared Task: GHHH - Detecting Semantic Relations via Word Embeddings , 2016, CogALex@COLING.

[18]  Michael L. Nelson,et al.  Correlation of Term Count and Document Frequency for Google N-Grams , 2009, ECIR.

[19]  Alessandro Lenci,et al.  SemEval-2018 Task 10: Capturing Discriminative Attributes , 2018, *SEMEVAL.

[20]  Gerard de Melo,et al.  Information Extraction from Web-scale N-gram Data , 2010, SIGIR 2010.

[21]  J. R. Firth,et al.  A Synopsis of Linguistic Theory, 1930-1955 , 1957 .

[22]  Dekang Lin,et al.  Creating Robust Supervised Classifiers via Web-Scale N-Gram Data , 2010, ACL.

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

[24]  Yoshua Bengio,et al.  A Neural Probabilistic Language Model , 2003, J. Mach. Learn. Res..

[25]  Nitish Srivastava,et al.  Improving neural networks by preventing co-adaptation of feature detectors , 2012, ArXiv.

[26]  Björn-Olav Dozo,et al.  Quantitative Analysis of Culture Using Millions of Digitized Books , 2010 .

[27]  Erik T. Mueller,et al.  Open Mind Common Sense: Knowledge Acquisition from the General Public , 2002, OTM.

[28]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.