• Corpus ID: 197634774

DCU at the NTCIR-14 OpenLiveQ-2 Task

@inproceedings{AroraDCUAT,
  title={DCU at the NTCIR-14 OpenLiveQ-2 Task},
  author={Piyush Arora and G. Jones}
}
Main Challenges ● Queries are typically short and ambiguous in nature and might not capture the user’s intention effectively ● For example for Japanese query: “喫煙”, English translation: “smoking” ○ Possible Query Intention-1: “dangers of smoking” ○ Possible Query Intention-2: “mechanism to quit smoking” ● Complex problem to re-rank the questions without understanding the user’s intent and focus of the query ● Aim: How to model the aspects of textual relevance and information gained through user… 
NII Testbeds and Community for Information Access Research: 14th International Conference, NTCIR 2019, Tokyo, Japan, June 10–13, 2019, Revised Selected Papers
TLDR
A method scoring lifelog moments using only the meta information generated by publicly available pretrained detectors with word embeddings is proposed, which shows the higher performance of the proposed method than the automatic retrieval systems presented in the NTCIR-14 Lifelog-3 task.

References

SHOWING 1-10 OF 15 REFERENCES
Overview of NTCIR-13
TLDR
This paper describes an outline of the research project, which includes its organization, schedule, scope and task designs, and introduces brief statistics of participants in the NTCIR-13 Conference.
YJRS at the NTCIR-13 OpenLiveQ Task
TLDR
The baseline method, which is a linear combination of 77 features with different weights, was improved by adding three settings of extended BM25F as additional features, replaced the target function of weight optimization and recalculated feature weights using 5-fold cross validation.
Challenges of Multileaved Comparison in Practice: Lessons from NTCIR-13 OpenLiveQ Task
TLDR
Challenges of an online evaluation technique, multileaved comparison, based on the analysis of evaluation results in a community question-answering (cQA) search service are discussed, and a new experimental design is proposed that evaluates all the rankers online but intensively tests only the top-k rankers.
Okapi at TREC-3
During the course of TREC{1 the low-level search functions were split o into a separate Basic Search System (BSS) [2], but retrieval and ranking of documents was still done using the \classical"
The good, the bad and their kins: Identifying questions with negative scores in StackOverflow
TLDR
This paper proposes a method to address the problem of question classification by retrieving similar questions previously asked in the same forum, and then using the text from these previously asked similar questions to predict the quality of the current question.
Cumulated gain-based evaluation of IR techniques
TLDR
This article proposes several novel measures that compute the cumulative gain the user obtains by examining the retrieval result up to a given ranked position, and test results indicate that the proposed measures credit IR methods for their ability to retrieve highly relevant documents and allow testing of statistical significance of effectiveness differences.
Linear feature-based models for information retrieval
TLDR
This paper details supervised training algorithms that directly maximize the evaluation metric under consideration, such as mean average precision, and shows that linear feature-based models can consistently and significantly outperform current state of the art retrieval models with the correct choice of features.
Sensitive and Scalable Online Evaluation with Theoretical Guarantees
TLDR
A novel multileaved comparison method, Pairwise Preference Multileaving (PPM), is introduced that performs comparisons based on document-pair preferences, and is shown to be more sensitive to user preferences and scalable with the number of rankers being compared.
A Language Modeling Approach to Information Retrieval
TLDR
This work proposes an approach to retrieval based on probabilistic language modeling and integrates document indexing and document retrieval into a single model, which significantly outperforms standard tf.idf weighting on two different collections and query sets.
Overview of the NTCIR-14 OpenLiveQ-2 Task
  • Proceedings of the 14th NTCIR Conference on Evaluation of Information Access Technologies
  • 2019
...
...