Semantic Text Matching for Long-Form Documents
Семантическое сопоставление текстов для документов большого объёма
2019-05-13
SCID: 54.1/4nmy6bnd
Discuss with AI
information retrievallong-document-to-long-document matchinglong-form documentsquestion answeringsemantic text matching
Figures from the paper
Abstract (AI)
Semantic text matching is one of the most important research problems in many domains, including, but not limited to, information retrieval, question answering, and recommendation. Among the different types of semantic text matching, long-document-to-long-document text matching has many applications, but has rarely been studied. Most existing approaches for semantic text matching have limited success in this setting, due to their inability to capture and distill the main ideas and topics from long-form text.
Key Findings
1
Existing semantic text matching methods have limited success on long-form documents because they cannot effectively capture and distill their main ideas and topics.
2
Long-document-to-long-document semantic text matching is an important but relatively understudied problem with applications in information retrieval, question answering, and recommendation.
3
The abstract identifies modeling the central ideas and topics of long documents as the key challenge for improving semantic matching in this setting.
Research Object
long-form documents in long-document-to-long-document semantic text matching
Research Subject
capturing and distilling the main ideas and topics from long-form text for semantic matching
Publication Details
Publication Date
2019-05-13
Journal
Publisher
ISSN
Cited by
94
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai5
Adam: A Method for Stochastic Optimization2014
Reducing the Dimensionality of Data with Neural Networks2006
Convolutional Neural Networks for Sentence Classification2014
Hierarchical Attention Networks for Document Classification2016
Siamese Recurrent Architectures for Learning Sentence Similarity2016