On Collocations and Their Interaction with Parsing and Translation
Journal Title: Informatics - Year 2014, Vol 1, Issue 1
Abstract
We address the problem of automatically processing collocations—a subclass of multi-word expressions characterized by a high degree of morphosyntactic flexibility—in the context of two major applications, namely, syntactic parsing and machine translation. We show that parsing and collocation identification are processes that are interrelated and that benefit from each other, inasmuch as syntactic information is crucial for acquiring collocations from corpora and, vice versa, collocational information can be used to improve parsing performance. Similarly, we focus on the interrelation between collocations and machine translation, highlighting the use of translation information for multilingual collocation identification, as well as the use of collocational knowledge for improving translation. We give a panorama of the existing relevant work, and we parallel the literature surveys with our own experiments involving a symbolic parser and a rule-based translation system. The results show a significant improvement over approaches in which the corresponding tasks are decoupled.
Authors and Affiliations
Violeta Seretan
Keywords
Related Articles
- EP ID EP44036
- DOI https://doi.org/10.3390/informatics1010011
- Views 294
- Downloads 0
Health Literacy for the General Public: Making a Case for Non-Trivial Visualizations
Health literacy is concerned with the degree to which individuals can access and understand information to make health decisions. The multifaceted nature of health data presents challenges for individuals seeking to im...
From Offshore Operation to Onshore Simulator: Using Visualized Ethnographic Outcomes to Work with Systems Developers
This paper focuses on the process of translating insights from a Computer Supported Cooperative Work (CSCW)-based study, conducted on a vessel at sea, into a model that can assist systems developers working with simulato...
The Effect of Evidence Transfer on Latent Feature Relevance for Clustering
Evidence transfer for clustering is a deep learning method that manipulates the latent representations of an autoencoder according to external categorical evidence with the effect of improving a clustering outcome. Evi...
Modifying Dialogical Strategy in Asynchronous Critical Discussions for Cross-Strait Chinese Learners
In this global era, critical thinking has become crucial for educators and learners. The purpose of this research was to explore how modifying a dialogical strategy in asynchronous online discussion forums impacted Chi...
Improving the Classification Efficiency of an ANN Utilizing a New Training Methodology
In this work, a new approach for training artificial neural networks is presented which utilises techniques for solving the constraint optimisation problem. More specifically, this study converts the training of a neur...