Corpus ID: 60617953

NTCIR workshop 6 meeting : proceedings of the 6th NTCIR workshop meeting on evaluation of information access technologies: information retrieval, question answering and cross-lingual information access

  title={NTCIR workshop 6 meeting : proceedings of the 6th NTCIR workshop meeting on evaluation of information access technologies: information retrieval, question answering and cross-lingual information access},
  author={Ntcir and 神門 典子 and 国立情報学研究所 and Dave Evans and Hsin-Hsi Chen and Kuang-hua Chen and 岸田 和明 and 栗山 和子 and Sukhoon Lee and Chuan-Jie Lin and Yutaka Sasaki and 藤井 敦 and Makoto Iwayama and Jun-ichi Fukumoto and Tsuneaki Kato and Fumito Masui and Tatsunori Mori and 松下 光範 and Lun-Wei Ku and Chin-Yew Lin and Yohei Seki and 日本学術振興会},
Towards End-to-End Multilingual Question Answering
It is demonstrated that a simple translation of texts can be inadequate in case of Arabic, English and German languages (on InsuranceQA and SemEval datasets), and thus more sophisticated models are required. Expand
An Effectiveness Metric for Ordinal Classification: Formal Properties and Experimental Results
A new metric for Ordinal Classification, Closeness Evaluation Measure, is proposed that is rooted on Measurement Theory and Information Theory and generalizes some popular classification and error minimization metrics, depending on the measurement scale in which it is instantiated. Expand
An authoring tool for decision support systems in context questions of ecological knowledge
This paper proposes an NLI that improves the interaction between the user and the DSS by means of referencing previous questions or their answers, and is based on ontologies that are obtained semi-automatically from a framework that allows the integration of internal and external, structured and unstructured information. Expand
DAEDALUS at SemEval-2014 Task 9: Comparing Approaches for Sentiment Analysis in Twitter
Results prove that the generic model is more robust as it achieves a more balanced evaluation for message polarity along the different test sets, than the machine learning classifier developed for the task using the provided training corpus. Expand
An API-based Search System for One Click Access to Information
A thorough user-based evaluation concludes that such an information retrieval system outperforms the textual preview collected from Google search results, based on a paired sign test. Expand
Evaluation of baseline information retrieval for Polish open-domain Question Answering system
It is shown that using two re-ranking methods based on term proximity allows for significant improvement on simple information retrieval baseline and the improvement is observed as finding more answer-bearing documents among the topn search results. Expand
Query-by-Example Spoken Term Detection ALBAYZIN 2012 evaluation: overview, systems, results, and discussion
The systems submitted to the ALBAYZIN 2012 QbE STD evaluation are presented and the systems aiming at establishing the best technique dealing with that difficult task and looking for defining promising directions for this relatively novel task are compared. Expand
University Entrance Examinations as a Benchmark Resource for NLP-based Problem Solving
A corpus comprised of university entrance examinations is described, providing annotations of question classifications in terms of answer types and knowledge types, and two international shared tasks that employed the resource for developing their evaluation data sets are introduced. Expand
Assessing Sentiment Strength in Words Prior Polarities
This work compares 14 formulae that appear in the literature, and assess which one best approximates the human judgement of prior polarities, with both regression and classification models. Expand