Showing papers by "Omer Levy published in 2015"

Improving Distributional Similarity with Lessons Learned from Word Embeddings

Abstract: Recent trends suggest that neural-network-inspired word embedding models outperform traditional count-based distributional models on word similarity and analogy detection tasks. We reveal that much of the performance gains of word embeddings are due to certain system design choices and hyperparameter optimizations, rather than the embedding algorithms themselves. Furthermore, we show that these modifications can be transferred to traditional distributional models, yielding similar gains. In contrast to prior reports, we observe mostly local or insignificant performance differences between the methods, with no global advantage to any single approach over the others.

Do Supervised Distributional Methods Really Learn Lexical Inference Relations

Abstract: Distributional representations of words have been recently used in supervised settings for recognizing lexical inference relations between word pairs, such as hypernymy and entailment. We investigate a collection of these state-of-the-art methods, and show that they do not actually learn a relation between two words. Instead, they learn an independent property of a single word in the pair: whether that word is a “prototypical hypernym”.

A Simple Word Embedding Model for Lexical Substitution

Abstract: The lexical substitution task requires identifying meaning-preserving substitutes for a target word instance in a given sentential context. Since its introduction in SemEval-2007, various models addressed this challenge, mostly in an unsupervised setting. In this work we propose a simple model for lexical substitution, which is based on the popular skip-gram word embedding model. The novelty of our approach is in leveraging explicitly the context embeddings generated within the skip-gram model, which were so far considered only as an internal component of the learning process. Our model is efficient, very simple to implement, and at the same time achieves state-ofthe-art results on lexical substitution tasks in an unsupervised setting.

Learning to Exploit Structured Resources for Lexical Inference

Abstract: Massive knowledge resources, such as Wikidata, can provide valuable information for lexical inference, especially for proper-names. Prior resource-based approaches typically select the subset of each resource’s relations which are relevant for a particular given task. The selection process is done manually, limiting these approaches to smaller resources such as WordNet, which lacks coverage of propernames and recent terminology. This paper presents a supervised framework for automatically selecting an optimized subset of resource relations for a given target inference task. Our approach enables the use of large-scale knowledge resources, thus providing a rich source of high-precision inferences over proper-names. 1

Undivide and Conquer: On Selling a Divisible and Homogeneous Good

Abstract: With the prevalence of cloud computing emerges the challenges of pricing cloud computing services. There are various characteristics of cloud computing which make the problem unique. We study an abstract model which focuses on one such aspect – the sale of a homogeneous and fully divisible good. We cast onto our model the idea of bundling, studied within the context of monopolist pricing of indivisible goods. We demonstrate how selling a divisible good as an indivisible one may increase seller revenues and characterize when this phenomenon occurs, and the corresponding gain factors.