Shijing Si
Papers
1
Total Citations
10
H-Index
1
About
Dr. Shijing Si is a researcher whose work lies at the intersection of natural language processing and conversational AI, with a particular focus on semantic understanding for question-answering systems. Their most-cited paper, "Sentence Similarity Computation in Question Answering Robot" (2019, 10 citations), addresses a fundamental challenge in NLP: accurately measuring semantic similarity between sentences. This work is critical for improving the performance of QA robots, search engines, and query suggestion tools. Dr. Si’s contributions explore how lexical matching and distributional semantics can be combined to better capture meaning, advancing the reliability of automated responses in dialogue systems. While their citation count is modest, the practical relevance of their research—enhancing how machines understand and compare human language—positions them as a thoughtful contributor to applied NLP. Their work serves as a valuable reference for students and engineers building more intuitive, context-aware conversational agents.
Research Focus
Key Achievements
Top Papers
- 1Sentence Similarity Computation in Question Answering Robot10 citations · 2019