Term-weighting approaches in automatic text retrieval
Information Processing and Management: an International Journal
A statistical approach to machine translation
Computational Linguistics
Proceedings of the 22nd annual international ACM SIGIR conference on Research and development in information retrieval
Automatic title generation for EM
DL '00 Proceedings of the fifth ACM conference on Digital libraries
Information Retrieval
Advances in Automatic Text Summarization
Advances in Automatic Text Summarization
Learning to Select Good Title Words: An New Approach based on Reverse Information Retrieval
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Web-assisted annotation, semantic indexing and search of television and radio news
WWW '05 Proceedings of the 14th international conference on World Wide Web
Automatic labeling of multinomial topic models
Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining
The effect of title term suggestion on e-commerce sites
Proceedings of the 10th ACM workshop on Web information and data management
How many words is a picture worth? Automatic caption generation for news images
ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
Automatic headline generation using character cross-correlation
HLT-SS '11 Proceedings of the ACL 2011 Student Session
Comparing topiary-style approaches to headline generation
ECIR'05 Proceedings of the 27th European conference on Advances in Information Retrieval Research
| Hi-index | 0.00 |
Title generation is a complex task involving both natural language understanding and natural language synthesis. In this paper, we propose a new probabilistic model for title generation. Different from the previous statistical models for title generation, which treat title generation as a generation process that converts the 'document representation' of information directly into a 'title representation' of the same information, this model introduces a hidden state called 'information source' and divides title generation into two steps, namely the step of distilling the 'information source' from the observation of a document and the step of generating a title from the estimated 'information source'. In our experiment, the new probabilistic model outperforms the previous model for title generation in terms of both automatic evaluations and human judgments.