Coreference Resolution Using Neural MCDM and Fuzzy Weighting Technique
نویسندگان
چکیده
منابع مشابه
Neural Coreference Resolution
Much work on coreference resolution has gone towards hand crafting complicated features that are predictive of coreference. However, systems relying on these can become unwieldy and may generalize poorly to new data. In this work, I present a new coreference system based on neural networks that automatically learns dense vector representations for mention pairs. These representations are built ...
متن کاملFuzzy Coreference Resolution for Summarization
We present a fuzzy-theory based approach to coreference resolution and its application to text summarization. Automatic determination of coreference between noun phrases is fraught with uncertainty. We show how fuzzy sets can be used to design a new coreference algorithm which captures this uncertainty in an explicit way and allows us to define varying degrees of coreference. The algorithm is e...
متن کاملPrediction of the main caving span in longwall mining using fuzzy MCDM technique and statistical method
Immediate roof caving in longwall mining is a complex dynamic process, and it is the core of numerous issues and challenges in this method. Hence, a reliable prediction of the strata behavior and its caving potential is imperative in the planning stage of a longwall project. The span of the main caving is the quantitative criterion that represents cavability. In this paper, two approaches are p...
متن کاملCorpus based coreference resolution for Farsi text
"Coreference resolution" or "finding all expressions that refer to the same entity" in a text, is one of the important requirements in natural language processing. Two words are coreference when both refer to a single entity in the text or the real world. So the main task of coreference resolution systems is to identify terms that refer to a unique entity. A coreference resolution tool could be...
متن کاملEnd-to-end Neural Coreference Resolution
We introduce the first end-to-end coreference resolution model and show that it significantly outperforms all previous work without using a syntactic parser or handengineered mention detector. The key idea is to directly consider all spans in a document as potential mentions and learn distributions over possible antecedents for each. The model computes span embeddings that combine context-depen...
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: International Journal of Computational Intelligence Systems
سال: 2020
ISSN: 1875-6883
DOI: 10.2991/ijcis.d.200121.001