CSI: A Coarse Sense Inventory for 85% Word Sense Disambiguation
نویسندگان
چکیده
منابع مشابه
Coarse Word-Sense Disambiguation Using Common Sense
Coarse word sense disambiguation (WSD) is an NLP task that is both important and practical: it aims to distinguish senses of a word that have very different meanings, while avoiding the complexity that comes from trying to finely distinguish every possible word sense. Reasoning techniques that make use of common sense information can help to solve theWSD problem by taking word meaning and conte...
متن کاملI2R: Three Systems for Word Sense Discrimination, Chinese Word Sense Disambiguation, and English Word Sense Disambiguation
This paper describes the implementation of our three systems at SemEval-2007, for task 2 (word sense discrimination), task 5 (Chinese word sense disambiguation), and the first subtask in task 17 (English word sense disambiguation). For task 2, we applied a cluster validation method to estimate the number of senses of a target word in untagged data, and then grouped the instances of this target ...
متن کاملSense Discriminative Patterns for Word Sense Disambiguation
Given a target word wi to be disambiguated, we define a class of local contexts for wi such that the sense of wi is univocally determined. We call such local contexts sense discriminative and represent them with sense discriminative (SD) patterns of lexico-syntactic features. We describe an algorithm for the automatic acquisition of minimal SD patterns based on training data in SemCor. We have ...
متن کاملWord Domain Disambiguation via Word Sense Disambiguation
Word subject domains have been widely used to improve the performance of word sense disambiguation algorithms. However, comparatively little effort has been devoted so far to the disambiguation of word subject domains. The few existing approaches have focused on the development of algorithms specific to word domain disambiguation. In this paper we explore an alternative approach where word doma...
متن کاملProbabilistic word sense disambiguation
We present a theoretically motivated method for creating probabilistic word sense disambiguation (WSD) systems. The method works by composing multiple probabilistic components: such modularity is made possible by an application of Bayesian statistics and Lidstone’s smoothing method. We show that a probabilistic WSD system created along these lines is a strong competitor to state-of-the-art WSD ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Proceedings of the AAAI Conference on Artificial Intelligence
سال: 2020
ISSN: 2374-3468,2159-5399
DOI: 10.1609/aaai.v34i05.6324