Semantic Feature Engineering for Enhancing Disambiguation Performance in Deep Linguistic Processing
نویسندگان
چکیده
The task of parse disambiguation has gained in importance over the last decade as the complexity of grammars used in deep linguistic processing has been increasing. In this paper we propose to employ the fine-grained HPSG formalism in order to investigate the contribution of deeper linguistic knowledge to the task of ranking the different trees the parser outputs. In particular, we focus on the incorporation of semantic features in the disambiguation component and the stability of our model cross domains. Our work is carried out within DELPH-IN (http://www.delph-in.net), using the LinGo Redwoods and the WeScience corpora, parsed with the English Resource Grammar and the PET parser.
منابع مشابه
A Morphology-Aware Network for Morphological Disambiguation
Agglutinative languages such as Turkish, Finnish and Hungarian require morphological disambiguation before further processing due to the complex morphology of words. A morphological disambiguator is used to select the correct morphological analysis of a word. Morphological disambiguation is important because it generally is one of the first steps of natural language processing and its performan...
متن کاملDeep Linguistic Analysis for the Accurate Identification of Predicate-Argument Relations
This paper evaluates the accuracy of HPSG parsing in terms of the identification of predicate-argument relations. We could directly compare the output of HPSG parsing with PropBank annotations, by assuming a unique mapping from HPSG semantic representation into PropBank annotation. Even though PropBank was not used for the training of a disambiguation model, an HPSG parser achieved the accuracy...
متن کاملSemantic Processing Ability in Persian-Speaking Alzheimer’s Patients
Objectives: This paper aims to explore whether the Persian-speaking patients of different stages, ranging from mild to moderate, have a deficit in semantic processing by comparing the performance of Alzheimer’s patients with that of the healthy individuals. Methods: The subjects of both the groups of Alzheimer’s patients and healthy control were matched for age, the state of monoli...
متن کاملFeature Engineering in Persian Dependency Parser
Dependency parser is one of the most important fundamental tools in the natural language processing, which extracts structure of sentences and determines the relations between words based on the dependency grammar. The dependency parser is proper for free order languages, such as Persian. In this paper, data-driven dependency parser has been developed with the help of phrase-structure parser fo...
متن کاملA Common Ontology for Linguistic Concepts
As part of a project called Electronic Metastructure for Endangered Languages Data (EMELD), we have developed an ontology of concepts that encompasses a wide range of linguistic phenomena. The idea was initially conceived to facilitate both the knowledge sharing of annotated linguistic data and the searching of disparate language corpora. Such an ontology, however, is needed outside of the EMEL...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2010