Word Embedding-based Text Processing for Comprehensive Summarization and Distinct Information Extraction
This work addresses the problem of processing online reviews for customers or businesses, but it appears incremental as it builds on existing text processing and clustering methods.
The paper tackles automated analysis of online reviews by proposing two frameworks: one for summarizing reviews via sentence clustering and importance scoring, and another for extracting distinct answers using a question-answering neural network and clustering. The frameworks are claimed to be more comprehensive than existing solutions, but no concrete numbers are provided.
In this paper, we propose two automated text processing frameworks specifically designed to analyze online reviews. The objective of the first framework is to summarize the reviews dataset by extracting essential sentence. This is performed by converting sentences into numerical vectors and clustering them using a community detection algorithm based on their similarity levels. Afterwards, a correlation score is measured for each sentence to determine its importance level in each cluster and assign it as a tag for that community. The second framework is based on a question-answering neural network model trained to extract answers to multiple different questions. The collected answers are effectively clustered to find multiple distinct answers to a single question that might be asked by a customer. The proposed frameworks are shown to be more comprehensive than existing reviews processing solutions.