A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
Filters
Tapping into the Power of Automatic Question Generation
2014
International Journal of Computer Applications
Preserved Fulltext
Question Generation (QG) is an important element of learning environments, information seeking systems, help systems, and other applications. ...
This research tries to have a wide look on existing automatic question generation systems, and some trials of overcoming its difficulties from different points of views. ...
Tregex, a tree query language used in order to implement the rules for transforming source sentences into questions, and Tsurgeon, a tree manipulation language built on top of Tregex. ...
doi:10.5120/18035-7636
fatcat:b7xp4telhfg23g4wizz374rzz4
Universal Semantic Parsing
[article]
2017
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Our code and data can be downloaded at https://github.com/sivareddyg/udeplambda. ...
Results show that UDepLambda outperforms strong baselines across languages and datasets. For English, it achieves a 4.9 F1 point improvement over the state-of-the-art on GraphQuestions. ...
We thank Reviewer 2 for useful feedback. The authors would also like to thank the Universal Dependencies community for the treebanks and documentation. ...
arXiv:1702.03196v4
fatcat:auk3prkzevhfrhfm5qlnjiez6m
Fluent Response Generation for Conversational Question Answering
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:2005.10464v1 fatcat:zcz2tgf4gvdhnlodtw2neb7uo4
From a technical perspective, we use data augmentation to generate training data for an end-to-end system. ...
The code and data are available at https://github.com/abaheti95/QADialogSystem. ...
Acknowledgments We would like to thank the reviewers for providing valuble feedback on an earlier draft of this paper. ...
arXiv:2005.10464v2
fatcat:lamuldyfqfgctizfk6txgzzf7a
Treebank Parsing and Knowledge of Language
[chapter]
2012
Cognitive Aspects of Computational Language Acquisition
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Tregex and tsurgeon: Tools for querying and manipulating tree 1091
data structures. ...
and Tsurgeon toolkit [31]. ...
doi:10.1007/978-3-642-31863-4_6
dblp:series/tanlp/FongMYB13
fatcat:htp3zcp4kbfabapzqfuuck2b7m
Creating Conversational Characters Using Question Generation Tools
2012
Dialogue and Discourse
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
This article describes a new question generation tool for extracting question-answer databases from text articles, and reports three experiments which investigate how suitable this technique is for giving ...
Experiment 1 demonstrates the feasibility of our method by creating characters for 14 distinct topics and evaluating them using hand-authored questions. ...
Acknowledgments We wish to thank Michael Heilman, author of Question Transducer, for giving us access to his code and allowing us to use it in our experiments. ...
doi:10.5087/dad.2012.206
fatcat:skpiu5fhrncupdh3joyj2ufxtq
EFFECTIVE PROCESSING OF QUESTION GENERATION FROM TEXT
2016
International Journal of Pharmacy & Technology
unpublished
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
After that we present a system for question generation that using the existing natural language tools and application for helps in question generation. ...
System uses the manually written rules for transformation and processing some steps. Some experiments done on question generation and that result gives good question that are valuable. ...
Sentence generate question using Tregex, a language that work on query and Tsurgeon for tree manipulation. ...
fatcat:vdxa64ax75fjtg3irvyv2qjbmq
Retrospective Semi-automated Software Feature Extraction from Natural Language User Manuals
2018
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Tsurgeon (Levy and Andrew 2006), which is a tree-transformation utility built on top of Tregex, allows to manipulate the identified parse trees as desired. ...
Tsurgeon (Levy and Andrew 2006) , which is a tree-transformation utility built on top of Tregex, allows to manipulate the identified parse trees as desired. ...
(ROOT (S (NP (JJ other) (NNS options)) (VP (VBP exclude) (NP (NP (NNP DSTreagents)) (, ,) (SBAR (WHNP (WDT which)) (S (VP (VBP are) (VP (VBN used) (PP (IN for) (NP (NP (NNP DSTcontrols)) (CC and) (NP ( ...
doi:10.11588/heidok.00025322
fatcat:axyyuby4kfalbm3i4n7otcmpxi
Fluent Response Generation for Conversational Question Answering
2020
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
unpublished
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
From a technical perspective, we use data augmentation to generate training data for an end-to-end system. ...
Human evaluation on SQuAD 2.0 data (Rajpurkar et al., 2018) demonstrate that the proposed model outperforms baseline CoQA and QuAC models in generating conversational responses. ...
Acknowledgments We would like to thank the reviewers for providing valuble feedback on an earlier draft of this paper. ...
doi:10.18653/v1/2020.acl-main.19
fatcat:uru6jl6rnvf5ddsuxoxsr7d7ya
Reassessing inflectional regularity in Modern Greek conjugation
[chapter]
Proceedings of the Third Italian Conference on Computational Linguistics CLiC-it 2016
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
Acknowledgments We would like to thank the Appetitoso team for making available the system and for providing us with the data for this work. ...
This analysis is useful to identify features for the development of an automatic tool for sentiment-related classification tasks in this domain. The gold standard is available to the community. ...
cannot be easily adapted to general needs, or are devoted to tree manipulation, for example the tool 'Tregex' (Levy and Andrew, 2006) . ...
doi:10.4000/books.aaccademia.1721
fatcat:6mvr6rntdnhrlgxyqoqrvasc6u