Filters








4 Hits in 3.9 sec

CMU OAQA at TREC 2016 LiveQA: An Attentional Neural Encoder-Decoder Approach for Answer Ranking

Di Wang, Eric Nyberg
2016 Text Retrieval Conference  
The main improvement this year is the introduction of a novel answer passage ranking method based on attentional encoder-decoder recurrent neural networks (RNN).  ...  In the TREC 2016 LiveQA evaluations, human assessors gave our system an average score of 1.1547 on a three-point scale and the average score was .5766 for all the 26 systems evaluated.  ...  Here we describe the attention-based neural encoder-decoder model we used for ranking in greater detail.  ... 
dblp:conf/trec/WangN16 fatcat:ifbytcfxx5gy7ai64p7ggedsou

CMU OAQA at TREC 2017 LiveQA: A Neural Dual Entailment Approach for Question Paraphrase Identification

Di Wang, Eric Nyberg
2017 Text Retrieval Conference  
In this paper, we present CMU's question answering system that was evaluated in the TREC 2017 LiveQA Challenge. Our overall approach this year is similar to the one used in 2015 and 2016.  ...  In the TREC 2017 LiveQA evaluations, human assessors gave our system an average score of 1.139 on a three-point scale and the median score was 0.777 for all the systems evaluated.  ...  During the official run, our QA server received one question per minute for 24 hours and Figure 1 : Architecture of the CMU-OAQA LiveQA system provided answers within one minute for 98% of the input questions  ... 
dblp:conf/trec/WangN17 fatcat:yfpimgedavfnzme26dmjeirpnq

A question-entailment approach to question answering

Asma Ben Abacha, Dina Demner-Fushman
2019 BMC Bioinformatics  
Following the evaluation process used in TREC 2017 LiveQA, we find that our approach exceeds the best results of the medical task with a 29.8% increase over the best official score.  ...  Second, we combine IR models with the best RQE method to select entailed questions and rank the retrieved answers.  ...  Shooshan (NLM/NIH) for her help with the judgment of the retrieved answers, and Ellen Voorhees (NIST) for her help with the TREC LiveQA evaluation.  ... 
doi:10.1186/s12859-019-3119-4 fatcat:ztrn5jaiwjdizmicuscn466ghq

A Question-Entailment Approach to Question Answering [article]

Asma Ben Abacha, Dina Demner-Fushman
2019 arXiv   pre-print
Following the evaluation process used in TREC 2017 LiveQA, we find that our approach exceeds the best results of the medical task with a 29.8% increase over the best official score.  ...  Second, we combine IR models with the best RQE method to select entailed questions and rank the retrieved answers.  ...  The CMU-OAQA system [48] achieved the best performance of 0.637 average score on the medical task by using an attentional encoder-decoder model for paraphrase identification and answer ranking.  ... 
arXiv:1901.08079v1 fatcat:kwtxhoxuvnbovgxve33vb4d6b4