Abstract | ||
---|---|---|
Most existing information retrieval (IR) systems do not take much advantage of natural language processing (NLP) techniques due to the complexity and limited observed effectiveness of applying NLP to IR. In this paper, we demonstrate that substantial gains can be obtained over a strong baseline using NLP techniques, if properly handled. We propose a framework for deriving semantic text matching features from named entities identified in Web queries; we then utilize these features in a supervised machine-learned ranking approach, applying a set of emerging machine learning techniques. Our approach is especially useful for queries that contain multiple types of concepts. Comparing to a major commercial Web search engine, we observe a substantial 4% DCG5 gain over the affected queries. |
Year | Venue | Keywords |
---|---|---|
2009 | EMNLP | existing information retrieval,limited observed effectiveness,substantial gain,nlp technique,affected query,improving web search relevance,multiple type,semantic feature,web query,dcg5 gain,supervised machine-learned ranking approach,major commercial web search,natural language processing,web search engine,information retrieval |
Field | DocType | Volume |
Web search engine,Search engine,Semantic search,Information retrieval,Semantic Web Stack,Ranking,Computer science,Natural language processing,Artificial intelligence,Machine learning | Conference | D09-1 |
Citations | PageRank | References |
10 | 0.54 | 22 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yumao Lu | 1 | 159 | 8.14 |
Fuchun Peng | 2 | 1378 | 85.75 |
Gilad Mishne | 3 | 1682 | 119.49 |
Xing Wei | 4 | 1141 | 60.87 |
Benoit Dumoulin | 5 | 60 | 3.99 |