Paper Title
Cross Language Opinion Miner: Opinion Target Extraction in an Annoyed-Language Scheme
Abstract
Opinion target extraction is a subtask of opinion mining which is extremely beneficial in numerous applications.
The issue has usually been solved by instruction a sequence labeled on manually labeled data. Even so, the labeled instruction
datasets are imbalanced in various languages, and the lack of labeled corpus in a language limits the investigation progress on
opinion target extraction in this language. In order to handle the above issue, we propose a novel method known as CL Opinion
Miner which investigates leveraging the rich labeled information in a source language for opinion target extraction in a
various target language. In our approach we now have propose across-language opinion target extraction system CL Opinion
Miner with all the monolingual co-training algorithm that may be easily adapted with other cross-language information
extraction tasks.
Keywords - Part of Speech, Conditional Random Field, Feature based summarization, Chinese opinion analysis evaluation.