Lemon and Tea Are Not Similar: Measuring Word-to-Word Similarity by Combining Different Methods

A Survey on Portuguese Lexical Knowledge Bases: Contents, Comparison and Combination

“…By combining distributional vectors with knowledge from Princeton WordNet, a Spearman coefficient of 0.642 was obtained for the English SimLex-999 [31], which is not very far from the results of our best configuration (0.61). In the future, we will study the impact of combining the LKB-based approach with distributional vectors.…”

“…This is partially explained by the fact that LKBs are more theoretical views of the mental lexicon, while the distribution of words in a corpus models the way language is actually used. We are currently working on the combination of both kinds of models in a single, hopefully better, word similarity function, as others have done for English (e.g., [22,31]). Such a function might be useful for higher-level natural language tasks, such as semantic search systems or conversational agents.…”

Evaluating embeddings on dictionary-based similarity

“…State of the art on Simlex-999 was ρ = 0.64 (Banjade et al, 2015), obtained by combining many methods and data sources. More recently, Wieting et al (2015) added paraphrase data to achieve 0.69, and Recski et al (2016) added dictionary data to get to 0.76.…”

“…HGs are very sparse, and SVD doesn't preserve a lot of information from them (the ultimate test of an embedding would be the ability to reconstruct the dictionary relations from the vectors). Even in the best of cases, such as hypernyms derived from WordNet, the relative weight of this information is low (Banjade et al, 2015;Recski et al, 2016). That said, the impact of hypernym/genus on the problem of hubness (Dinu, Lazaridou, and Baroni, 2015) is worth investigating further.…”

NeRoSim: A System for Measuring and Interpreting Semantic Textual Similarity

“…synonymy and antonymy, from WordNet 3.0. As such we computed 1 Models available at http://semanticsimilarity.org 2 Downloaded from http://code.google.com/p/word2vec/ 3 Downloaded from http://nlp.stanford.edu/projects/glove/ similarity scores between two words a and b as: In hybrid approach, we developed a new word-to-word similarity measure (hereafter referred as Combined-Word-Measure) by combining the WordNet-based similarity methods with corpus based methods (using Mikolov's word embeddings and GloVe vectors) by applying Support Vector Regression (Banjade et al, 2015).…”