Expansional Retrofitting for Word Vector Enrichment

Retrofitting techniques, which inject external resources into word representations, have compensated the weakness of distributed representations in semantic and relational knowledge between words. Implicitly retrofitting word vectors by expansional technique outperforms retrofitting in word similarity tasks with word vector generalization. In this paper, we propose unsupervised extrofitting: expansional retrofitting (extrofitting) without external semantic lexicons. We also propose deep extrofitting: in-depth stacking of extrofitting and further combinations of extrofitting with retrofitting. When experimenting with GloVe, we show that our methods outperform the previous methods on most of word similarity tasks while requiring only synonyms as an external resource. Lastly, we show the effect of word vector enrichment on text classification task, as a downstream task.

[1]  Elia Bruni,et al.  Multimodal Distributional Semantics , 2014, J. Artif. Intell. Res..

[2]  T. Landauer,et al.  A Solution to Plato's Problem: The Latent Semantic Analysis Theory of Acquisition, Induction, and Representation of Knowledge. , 1997 .

[3]  Nigel Collier,et al.  SemEval-2017 Task 2: Multilingual and Cross-lingual Semantic Word Similarity , 2017, *SEMEVAL.

[4]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[5]  Steve Young,et al.  Semantic Specialization of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints , 2017 .

[6]  David Vandyke,et al.  Counter-fitting Word Vectors to Linguistic Constraints , 2016, NAACL.

[7]  Ming-Wei Chang,et al.  Importance of Semantic Representation: Dataless Classification , 2008, AAAI.

[8]  W. Pirie Spearman Rank Correlation Coefficient , 2006 .

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

[10]  George A. Miller,et al.  WordNet: A Lexical Database for English , 1995, HLT.

[11]  Alessandro Lenci,et al.  Distributional Models of Word Meaning , 2018 .

[12]  Jens Lehmann,et al.  DBpedia - A large-scale, multilingual knowledge base extracted from Wikipedia , 2015, Semantic Web.

[13]  Stephen Clark,et al.  Specializing Word Embeddings for Similarity or Relatedness , 2015, EMNLP.

[14]  Roberto Navigli,et al.  NASARI: a Novel Approach to a Semantically-Aware Representation of Items , 2015, NAACL.

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

[16]  Felix Hill,et al.  SimLex-999: Evaluating Semantic Models With (Genuine) Similarity Estimation , 2014, CL.

[17]  Goran Glavas,et al.  Explicit Retrofitting of Distributional Word Vectors , 2018, ACL.

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

[19]  Luke S. Zettlemoyer,et al.  Deep Contextualized Word Representations , 2018, NAACL.

[20]  Tomas Mikolov,et al.  Enriching Word Vectors with Subword Information , 2016, TACL.

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

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

[23]  Kevin Gimpel,et al.  From Paraphrase Database to Compositional Paraphrase Model and Back , 2015, Transactions of the Association for Computational Linguistics.

[24]  Yoon Kim,et al.  Convolutional Neural Networks for Sentence Classification , 2014, EMNLP.

[25]  Richard Hans Robert Hahnloser,et al.  Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit , 2000, Nature.

[26]  Chris Callison-Burch,et al.  PPDB: The Paraphrase Database , 2013, NAACL.

[27]  Hwiyeol Jo,et al.  Extrofitting: Enriching Word Representation and its Vector Space with Semantic Lexicons , 2018, Rep4NLP@ACL.

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

[29]  Anna Korhonen,et al.  Cross-Lingual Induction and Transfer of Verb Classes Based on Word Vector Space Specialisation , 2017, EMNLP.

[30]  Ehud Rivlin,et al.  Placing search in context: the concept revisited , 2002, TOIS.

[31]  Felix Hill,et al.  SimVerb-3500: A Large-Scale Evaluation Set of Verb Similarity , 2016, EMNLP.

[32]  Eneko Agirre,et al.  SemEval-2017 Task 1: Semantic Textual Similarity Multilingual and Crosslingual Focused Evaluation , 2017, *SEMEVAL.