Corpus ID: 59971043

Working notes of the fourth NTCIR workshop meeting

@inproceedings{2004WorkingNO,
  title={Working notes of the fourth NTCIR workshop meeting},
  author={和明 岸田 and 典子 神門 and 和子 栗山 and Haruko Ishikawa and Atsushi Fujii and Makoto Iwayama and Jun-ichi Fukumoto and Tsuneaki Kato and Fumito Masui and T. Fukusima and T. Hirao and 英嗣 難波 and 学 奥村},
  year={2004}
}

Topics from this paper

Analysis of Topics and Relevant Documents for Navigational Retrieval on the Web
An investigation into relationships among search methods, topic types, and styles of relevant Web pages was conducted using the "NTCIR-4 Web test collection for navigational retrieval", which wasExpand
A User-Friendly Tool for Medical-Related Patent Retrieval
TLDR
The development and evaluation of a user-friendly interactive Web application aiming at facilitating health-related patent search, called TWINC, relies on a search engine tuned during several patent retrieval competitions, enhanced with intelligent interaction modules, such as chemical query, normalization and expansion. Expand
Retrieval parameter optimization using genetic algorithms
TLDR
This paper describes the experiments on automatic parameter optimization for the Japanese monolingual retrieval task, and optimized parameters completely independently of retrieval models enabling the optimized parameter set to illustrate the characteristics of the target test collections. Expand
Cluster-based patent retrieval
TLDR
This study investigates cluster-based retrieval in the context of invalidity search task of patent retrieval, and experiments using the NTCIR-4 patent collection showed that the cluster- based language model could be helpful to improving the clusters-less baseline language model. Expand
Multimodal follow-up questions to multimodal answers in a QA system
TLDR
It is argued that the QA system developing a dialogue manager for a multimodal interactive Question Answering (QA) system will need to annotate its pictures with information about the visual elements that the picture is made up of, which enables appropriate anaphor resolution and answering identity questions about these elements. Expand
Questions, pictures, answers : Introducing pictures in question-answering systems
TLDR
The Dutch IMIX research programme on multimodal interaction, speech and language technology is presented, with special attention to the role that images could play in iterative question answering. Expand
Are open-domain question answering technologies useful for information access dialogues?---an empirical study and a proposal of a novel challenge
TLDR
It is found that questions that have values and names as answers account for a majority in realistic information-gathering situations and that those sequences of questions contain a wide range of reference expressions and are sometimes complicated by the inclusion of subdialogues and focus shifts. Expand
Book Review
With goals as intuitive and desirable as they are challenging, the field of automated question answering has generated growing interest in the past few years. The increased momentum is apparent inExpand
Proposal of two-stage patent retrieval method considering the claim structure
TLDR
Evaluation results using test sets of the NTCIR4 Patent Retrieval Task show that the methods are effective, though the degree of the effectiveness varies depending on the test sets. Expand
Static and Dynamic Scoring by Web Page Grouping
  • H. Nakakubo, Takashi Sato
  • Computer Science
  • 21st International Conference on Data Engineering Workshops (ICDEW'05)
  • 2005
TLDR
The technique for using Web Page Grouping together with the link structure analysis, and aim at the improvement in accuracy is proposed, composed of four techniques. Expand
...
1
2
...