Abstract
Abstract. Discourse may contain both named and nominal entities. Most common nouns or nominal mentions in natural language do not have a single, simple meaning but rather a number of related meanings. This form of ambiguity led to the development of a task in natural language processing known as Word Sense Disambiguation. Recognition and categorisation of named and nominal entities is an essential step for Word Sense Disambiguation methods. Up to now, named entity recognition and categorisation systems mainly focused on the annotation, categorisation and identification of named entities. This paper focuses on the annotation and the identification of spatial nominal entities. We explore the combination of Transfer Learning principle and supervised learning algorithms, in order to build a system to detect spatial nominal entities. For this purpose, different supervised learning algorithms are evaluated with three different context sizes on two manually annotated datasets built from Wikipedia articles and hiking description texts. The studied algorithms have been selected for one or more of their specific properties potentially useful in solving our problem. The results of the first phase of experiments reveal that the selected algorithms have similar performances in terms of ability to detect spatial nominal entities. The study also confirms the importance of the size of the window to describe the context, when word-embedding principle is used to represent the semantics of each word.
Highlights
IntroductionA critical aspect of polysemy (i.e., the ability to have multiple meanings) is that the different meanings of a word can be conceptually closely related but in very distant semantic categories
A critical aspect of polysemy is that the different meanings of a word can be conceptually closely related but in very distant semantic categories
We have evaluated the performance of each machine learning model (GRU, multilayer perceptron (MLP)+ACP, Multilayer perceptron with an auto-encoder (MLP+AE), Support Vector Machine (SVM), Random Forest (RF)) with three different context sizes (1 gram, 5 grams, 7 grams), which results in 15 systems
Summary
A critical aspect of polysemy (i.e., the ability to have multiple meanings) is that the different meanings of a word can be conceptually closely related but in very distant semantic categories. Consider the word ’church’ used to refer an organisation sense as in sentence (1). In this sentence (1), it allows to personify an affirmation, versus a building sense, as in sentence (2) here used as a spatial reference point. Lesk [2] used the context (short phrase containing the ambiguous word) to look for partial matching with the definitions in dictionaries (glossaries) of the ambiguous word and its context words in order to disambiguate the word sense. Lesk’s method aims to disambiguate the sense of any word of the vocabulary, which depends on words’ definitions in dictionaries that are often short and do not provide enough context. We consider the local context of words to disambiguate them, with a focus on a more specific case of spatial entities
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have