Skip to main navigation Skip to search Skip to main content

An Improved Weighted-Removal Sentence Embedding Based Approach for Service Recommendation

  • School of Computer Science and Technology, Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Currently, there is a large amount of information about user requirements and service in natural language. How to measure the semantic similarity between user requirements and service description is a critical issue in service recommendation and service solution construction. In this paper, we propose a service recommendation method based on the improved Weighted-Removal(WR) sentence embedding to solve the shortcomings of traditional information retrieval methods. After data preprocessing, we use the GloVe method to obtain the word vectors and use the improved WR sentence embedding method to obtain the sentence vectors. The similarity between the vectors can be better measured. The experimental results show that the proposed improved WR method is significantly better than the traditional methods in terms of recommendation accuracy, richness, and ranking.

Original languageEnglish
Title of host publicationProceedings - 2020 International Conference on Service Science, ICSS 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages44-50
Number of pages7
ISBN (Electronic)9781728185316
DOIs
StatePublished - Aug 2020
Externally publishedYes
Event2020 International Conference on Service Science, ICSS 2020 - Xining, China
Duration: 24 Aug 202026 Aug 2020

Publication series

NameProceedings of International Conference on Service Science, ICSS
Volume2020-August
ISSN (Print)2165-3836
ISSN (Electronic)2165-3828

Conference

Conference2020 International Conference on Service Science, ICSS 2020
Country/TerritoryChina
CityXining
Period24/08/2026/08/20

Keywords

  • GloVe Based Word Embedding
  • Semantic Similarity Metrics
  • Sentence Embedding
  • Service Recommendation

Fingerprint

Dive into the research topics of 'An Improved Weighted-Removal Sentence Embedding Based Approach for Service Recommendation'. Together they form a unique fingerprint.

Cite this