Semantic similarity

About: Semantic similarity is a research topic. Over the lifetime, 14605 publications have been published within this topic receiving 364659 citations. The topic is also known as: semantic relatedness.

SensEmbed: Learning Sense Embeddings for Word and Relational Similarity

Abstract: Word embeddings have recently gained considerable popularity for modeling words in different Natural Language Processing (NLP) tasks including semantic similarity measurement. However, notwithstanding their success, word embeddings are by their very nature unable to capture polysemy, as different meanings of a word are conflated into a single representation. In addition, their learning process usually relies on massive corpora only, preventing them from taking advantage of structured knowledge. We address both issues by proposing a multifaceted approach that transforms word embeddings to the sense level and leverages knowledge from a large semantic network for effective semantic similarity measurement. We evaluate our approach on word similarity and relational similarity frameworks, reporting state-of-the-art performance on multiple datasets.

Web-Scale Distributional Similarity and Entity Set Expansion

Abstract: Computing the pairwise semantic similarity between all words on the Web is a computationally challenging task. Parallelization and optimizations are necessary. We propose a highly scalable implementation based on distributional similarity, implemented in the MapReduce framework and deployed over a 200 billion word crawl of the Web. The pairwise similarity between 500 million terms is computed in 50 hours using 200 quad-core nodes. We apply the learned similarity matrix to the task of automatic set expansion and present a large empirical study to quantify the effect on expansion performance of corpus size, corpus quality, seed composition and seed size. We make public an experimental testbed for set expansion analysis that includes a large collection of diverse entity sets extracted from Wikipedia.

Universal Correspondence Network

Abstract: We present a deep learning framework for accurate visual correspondences and demonstrate its effectiveness for both geometric and semantic matching, spanning across rigid motions to intra-class shape or appearance variations. In contrast to previous CNN-based approaches that optimize a surrogate patch similarity objective, we use deep metric learning to directly learn a feature space that preserves either geometric or semantic similarity. Our fully convolutional architecture, along with a novel correspondence contrastive loss allows faster training by effective reuse of computations, accurate gradient computation through the use of thousands of examples per image pair and faster testing with $O(n)$ feed forward passes for $n$ keypoints, instead of $O(n^2)$ for typical patch similarity methods. We propose a convolutional spatial transformer to mimic patch normalization in traditional features like SIFT, which is shown to dramatically boost accuracy for semantic correspondences across intra-class shape variations. Extensive experiments on KITTI, PASCAL, and CUB-2011 datasets demonstrate the significant advantages of our features over prior works that use either hand-constructed or learned features.

Accessing Different Types of Lexical Semantic Information: Evidence From Priming

Abstract: The types of semantic information that are automatically retrieved from the mental lexicon on hearing a word were investigated in 3 semantic priming experiments. The authors probed for activation of information about a word's category membership by using prime-target pairs that were members of a common semantic category (e.g., pig-horse) and 2 types of functional semantic properties: instrument relations (e.g., broom-floor) and script relations (e.g., restaurant-wine). The authors crossed type of semantic relation between prime and target with degree of normative association strength. In a paired and a single-word presentation version of an auditory lexicaldecision priming task, the authors found significant priming for category and functionally related targets, both with and without an additional associative relation. In all cases there was a significant associative boost. However, in a visual version of the single-word lexical-decision paradigm, a different pattern of results was found for each type of semantic relation. Category coordinates primed only when they were normatively associated, instrument relations primed both with and without association, and script relations primed in neither condition.