Coreference Resolution Using Verbs Knowledge
Journal Title: Journal of Information Systems and Telecommunication - Year 2017, Vol 5, Issue 2
Abstract
Coreference resolution is the problem of determining which mention in a text refer to the same entities, and is a crucial and difficult step in every natural language processing task. Despite the efforts that have been made in the past to solve this problem, its performance still does not meet today’s applications requirements. Given the importance of the verbs in sentences, in this work we tried to incorporate three types of their information on coreference resolution problem, namely, selectional restriction of verbs on their arguments, semantic relation between verb pairs, and the truth that arguments of a verb cannot be coreferent of each other. As a needed resource for supporting our model, we generate a repository of semantic relations between verb pairs automatically using Distributional Memory (DM), a state-of-the-art framework for distributional semantics. This resource consists of pairs of verbs associated with their probable arguments, their role mapping, and significance scores based on our measures. Our proposed model for coreference resolution encodes verbs’ knowledge with Markov logic network rules on top of deterministic Stanford coreference resolution system. Experiment results show that this semantic layer can improve the recall of the Stanford system while preserves its precision and improves it slightly.
Authors and Affiliations
Hasan Zafari, Maryam Hourali, Heshaam Faili
Keywords
Related Articles
- EP ID EP211814
- DOI -
- Views 131
- Downloads 0
Better Performance of New Generation of Digital Video Broadcasting-terrestrial (DVB-T2) Using Alamouti scheme with Cyclic Delay Diversity
The goal of the future terrestrial digital video broadcasting (DVB-T) standard is to employ diversity and spatial multiplexing in order to achieve the fully multiple-input multiple-output (MIMO) channel capacity. The DVB...
Optimization of Random Phase Updating Technique for Effective Reduction in PAPR, Using Discrete Cosine Transform
One of problems of OFDM systems, is the big value of peak to average power ratio. To reduce it, any attempt have been done amongst which, random phase updating is an important technique. In contrast to paper, since power...
Load Balanced Spanning Tree in Metro Ethernet Networks
Spanning Tree Protocol (STP) is a link management standard that provides loop free paths in Ethernet networks. Deploying STP in metro area networks is inadequate because it does not meet the requirements of these network...
Hybrid Task Scheduling Method for Cloud Computing by Genetic and PSO Algorithms
Cloud computing makes it possible for users to use different applications through the internet without having to install them. Cloud computing is considered to be a novel technology which is aimed at handling and providi...
Design and Implementation of an Ultra-Wide Band, High Precision, and Low Noise Frequency Synthesizer
This paper presents system-level design and implementation of an ultra-wide tunable, high precision, fast locking, low phase noise, and low power portable fractional-N frequency synthesizer. The output frequency of the p...