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.

Automatic semantic role labeling for Chinese verbs

Abstract: Recent years have seen a revived interest in semantic parsing by applying statistical and machine-learning methods to semantically annotated corpora such as the FrameNet and the Proposition Bank. So far much of the research has been focused on English due to the lack of semantically annotated resources in other languages. In this paper, we report first results on semantic role labeling using a pre-release version of the Chinese Proposition Bank. Since the Chinese Proposition Bank is superimposed on top of the Chinese Tree-bank, i.e., the semantic role labels are assigned to constituents in a treebank parse tree, we start by reporting results on experiments using the handcrafted parses in the treebank. This will give us a measure of the extent to which the semantic role labels can be bootstrapped from the syntactic annotation in the treebank. We will then report experiments using a fully automatic Chinese parser that integrates word segmentation, POS-tagging and parsing. This will gauge how successful semantic role labeling can be done for Chinese in realistic situations. We show that our results using hand-crafted parses are slightly higher than the results reported for the state-of-the-art semantic role labeling systems for English using the Penn English Proposition Bank data, even though the Chinese Proposition Bank is smaller in size. When an automatic parser is used, however, the accuracy of our system is much lower than the English state-of-the-art. This reveals an interesting cross-linguistic difference between the two languages, which we attempt to explain. We also describe a method to induce verb classes from the Proposition Bank "frame files" that can be used to improve semantic role labeling.

Learning Deep Multi-Level Similarity for Thermal Infrared Object Tracking

Abstract: Existing deep Thermal InfraRed (TIR) trackers only use semantic features to represent the TIR object, which lack the sufficient discriminative capacity for handling distractors. This becomes worse when the feature extraction network is only trained on RGB images. To address this issue, we propose a multi-level similarity model under a Siamese framework for robust TIR object tracking. Specifically, we compute different pattern similarities using the proposed multi-level similarity network. One of them focuses on the global semantic similarity and the other computes the local structural similarity of the TIR object. These two similarities complement each other and hence enhance the discriminative capacity of the network for handling distractors. In addition, we design a simple while effective relative entropy based ensemble subnetwork to integrate the semantic and structural similarities. This subnetwork can adaptive learn the weights of the semantic and structural similarities at the training stage. To further enhance the discriminative capacity of the tracker, we propose a large-scale TIR video sequence dataset for training the proposed model. To the best of our knowledge, this is the first and the largest TIR object tracking training dataset to date. The proposed TIR dataset not only benefits the training for TIR object tracking but also can be applied to numerous TIR visual tasks. Extensive experimental results on three benchmarks demonstrate that the proposed algorithm performs favorably against the state-of-the-art methods.

Ad Hoc Table Retrieval using Semantic Similarity

Abstract: We introduce and address the problem of ad hoc table retrieval: answering a keyword query with a ranked list of tables. This task is not only interesting on its own account, but is also being used as a core component in many other table-based information access scenarios, such as table completion or table mining. The main novel contribution of this work is a method for performing semantic matching between queries and tables. Specifically, we (i) represent queries and tables in multiple semantic spaces (both discrete sparse and continuous dense vector representations) and (ii) introduce various similarity measures for matching those semantic representations. We consider all possible combinations of semantic representations and similarity measures and use these as features in a supervised learning model. Using a purpose-built test collection based on Wikipedia tables, we demonstrate significant and substantial improvements over a state-of-the-art baseline.

Effects of bilingualism, aging, and semantic relatedness on memory under divided attention.

Abstract: We examined how encoding and retrieval processes were affected by manipulations of attention, and whether the degree of semantic relatedness between words in the memory and distracting task modulated these effects. We also considered age and bilingual status as mediating factors. Monolingual and bilingual younger and older adults studied a list of words from a single semantic category pre- sented auditorily, and later free recalled them aloud. During either study or retrieval, participants concurrently per- formed a distracting task requiring size decisions to words from either the same or a different semantic category as the words in the memory task. The greatest disruptions of memory from divided attention (DA) were for encoding rather than retrieval. The effect of semantic relatedness was significant only for DA at encoding. Older age and bilin- gualism were associated with lower recall scores in all con- ditions, but these factors did not influence the magnitude of memory interference. The results suggest that encoding is more sensitive to semantic similarity in a distracting task than is retrieval. The role of attention at encoding and retrieval is discussed.