8 Hits in 5.1 sec

Arabic Question Answering Systems: Gap Analysis

Mariam M. Biltawi, Sara Tedmori, Arafat Awajan
2021 IEEE Access  
The same authors [83] experimented with their RST-based method by using 110 "why" questions on the same dataset.  ...  VOLUME XX, 2017 1 Another attempt to answer Arabic "why" questions based on rhetorical structure theory (RST) relations was proposed by Azmi and AlShenaifi [42] .  ... 
doi:10.1109/access.2021.3074950 fatcat:zsjkex2ylfa5hgg3qjedhqsce4

Machine Comprehension with Discourse Relations

Karthik Narasimhan, Regina Barzilay
2015 Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)  
The model jointly identifies relevant sentences, establishes relations between them and predicts an answer.  ...  This design provides limited opportunities for guiding the discourse parser based on the requirements of the target task.  ...  This research is developed in a collaboration of MIT with the Arabic Language Technologies (ALT) group at Qatar Computing Research Institute (QCRI) within the Interactive sYstems for Answer Search (IYAS  ... 
doi:10.3115/v1/p15-1121 dblp:conf/acl/NarasimhanB15 fatcat:fptqm54vsjc2fn3icq2by6vlea

Message from the general chair

Benjamin C. Lee
2015 2015 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)  
To maximize the utility of the injected knowledge, we deploy a learning-based multi-sieve approach and develop novel entity-based features.  ...  Our end system outperforms the state-of-the-art baseline by 2 B 3 F1 points on non-transcript portion of the ACE 2004 dataset.  ...  We combine this simple idea with semantic word classes for ranking answers to why-questions and show that on a set of 850 why-questions our method gains 15.2% improvement in precision at the top-1 answer  ... 
doi:10.1109/ispass.2015.7095776 dblp:conf/ispass/Lee15 fatcat:ehbed6nl6barfgs6pzwcvwxria

Discourse analysis of asynchronous conversations

Shafiq Rayhan Joty
Our graph-based approach extends state-of-the-art methods by integrating a fine-grained conversational structure with other conversational features.  ...  Our approaches rely on two related computational methodologies: graph theory and probabilistic graphical models.  ...  Rhetorical structure has also been used for extracting answers of why questions [215] . The dialog act structure has been used to detect action items in meetings [147, 166] .  ... 
doi:10.14288/1.0165726 fatcat:jixdchdwqzecployo5xgznb534

Representation Learning and Learning from Limited Labeled Data for Community Question Answering

Andreas Rücklé
A limitation of previous approaches is that they leverage question information when learning answer representations.  ...  We show that our model achieves on-par or better performance for answer selection tasks compared to other approaches while allowing us to encode questions and answers independently.  ...  For instance, it has been shown that answers to "Why" questions typically consist of multiple sentences (Verberne et al., 2007) .  ... 
doi:10.26083/tuprints-00018508 fatcat:lrqvfpbsvbb2lfo4bqrwu3jaym

Addressing the data bottleneck in implicit discourse relation classification [article]

Wei Shi, Universität Des Saarlandes
The recent neural network based approaches in particular suffer from insufficient training (and test) data.  ...  The identification of discourse relations is beneficial for various NLP applications such as question-answering, summarization, machine translation, information extraction etc.  ...  ., 2007; Chai and Jin, 2004) , especially with respect to why-questions and causality in discourse relations.  ... 
doi:10.22028/d291-32711 fatcat:vxjavm5xrbfdfkgrgprrzch6t4

Computing Negotiation Update Semantics in Multi-issue Bargaining Dialogues

Volha Petukhova, Harry Bunt, Andrei Malchanau
2017 SEMDIAL 2017 (SaarDial) Workshop on the Semantics and Pragmatics of Dialogue   unpublished
A proof-ofconcept experiment on a visual reference resolution task shows the promise of the approach.  ...  Conclusion We presented a simple approach to make neural dialogue models "incremental" -that is, able to operate on incremental units instead of on complete utterances.  ...  Such moves can also be made by why-questions (Schlöder et al., 2016) , polar questions and rising declaratives.  ... 
doi:10.21437/semdial.2017-10 fatcat:7zzmv3z7jrevzokb5dtlf6jr3m

Urban Regeneration Strategies in Amman's Core: Urban Development and Real Estate Market

Kamila Ashour, Christoph Zöpel, Tu Dortmund, T Reicher, Mehdi Dortmund, T Vazifedoost, Dortmund
2016 unpublished
The analysis and review are conducted based on data from onsite, interviews, observations, photographs, official reports and articles.  ...  The time-series analysis aims to examine the "how" and "why" questions about the relationship of events overtime.  ...  Arab or Muslim cities.  ...