%0 Generic %1 vylomova2015gaggle %A Vylomova, Ekaterina %A Rimell, Laura %A Cohn, Trevor %A Baldwin, Timothy %D 2015 %K word2vec %T Take and Took, Gaggle and Goose, Book and Read: Evaluating the Utility of Vector Differences for Lexical Relation Learning %U http://arxiv.org/abs/1509.01692 %X Recent work on word embeddings has shown that simple vector subtraction over pre-trained embeddings is surprisingly effective at capturing different lexical relations, despite lacking explicit supervision. Prior work has evaluated this intriguing result using a word analogy prediction formulation and hand-selected relations, but the generality of the finding over a broader range of lexical relation types and different learning settings has not been evaluated. In this paper, we carry out such an evaluation in two learning settings: (1) spectral clustering to induce word relations, and (2) supervised learning to classify vector differences into relation types. We find that word embeddings capture a surprising amount of information, and that, under suitable supervised training, vector subtraction generalises well to a broad range of relations, including over unseen lexical items.

@misc{vylomova2015gaggle, abstract = {Recent work on word embeddings has shown that simple vector subtraction over pre-trained embeddings is surprisingly effective at capturing different lexical relations, despite lacking explicit supervision. Prior work has evaluated this intriguing result using a word analogy prediction formulation and hand-selected relations, but the generality of the finding over a broader range of lexical relation types and different learning settings has not been evaluated. In this paper, we carry out such an evaluation in two learning settings: (1) spectral clustering to induce word relations, and (2) supervised learning to classify vector differences into relation types. We find that word embeddings capture a surprising amount of information, and that, under suitable supervised training, vector subtraction generalises well to a broad range of relations, including over unseen lexical items.}, added-at = {2015-12-01T14:15:26.000+0100}, author = {Vylomova, Ekaterina and Rimell, Laura and Cohn, Trevor and Baldwin, Timothy}, biburl = {https://www.bibsonomy.org/bibtex/27ac064a9c919882efb7d25ff9127f527/obaskov}, description = {Take and Took, Gaggle and Goose, Book and Read: Evaluating the Utility of Vector Differences for Lexical Relation Learning}, interhash = {5e7f01ad3c166dcab0c2947298943554}, intrahash = {7ac064a9c919882efb7d25ff9127f527}, keywords = {word2vec}, note = {cite arxiv:1509.01692}, timestamp = {2015-12-01T14:15:26.000+0100}, title = {Take and Took, Gaggle and Goose, Book and Read: Evaluating the Utility of Vector Differences for Lexical Relation Learning}, url = {http://arxiv.org/abs/1509.01692}, year = 2015 }