Cheoneum Park

Coreference Resolution for Korean using Mention Pair with SVM

In this paper, we suggest a Coreference Resolution system for Korean using Mention Pair with SVM. The system introduced in this paper, also be able to extract Mention from document which is including automatically tagged name entity information, dependency trees and POS tags. We also built a corpus, including 214 documents with Coreference tags, referencing online news and Wikipedia for training the system and testing the systems performance. The corpus had 14 documents from online news, along with 200 question-and-answer documents from Wikipedia. When we tested the system by corpus, the performance of the system was extracted by MUC-F1 55.68%, B-cube-F1 57.19%, and CEAFE-F1 61.75%.

Anaphora resolution with pointer networks

Abstract Anaphora resolution is a fundamental problem in natural language processing. In this paper, we cast an anaphora resolution problem to a statistical pointing problem. To address the problem, we use the Pointer Networks model for a neural sequential anaphora pointing architecture. The proposed model automatically captures syntactic and semantic features to resolve anaphora by encoding the input tokens and decoding the chain form of the anaphora with attention mechanism. Our approach does not require any handcrafting features or language-specific rules to implement anaphora resolvers. Furthermore, it shows state-of-the-art performance.