Tools

LEADER 03131cam 2200481Ii 4500

001 on1164146340;

003 OCoLC;

005 20210312015605.0;

006 m o d ;

007 cr unu||||||||;

008 200709s2020 ncua obm 000 0 eng d;

035 a| (Sirsi) o1164146340;

035 a| (OCoLC)1164146340;

049 a| EREE;

090 a| QA76.9.Q4;

100 1 a| Busireddy, Swetha,e| author.?| UNAUTHORIZED;

245 12 a| A framework for question answering system using dynamic co-attention networks /c| by Swetha Busireddy.;

264 1 a| [Greenville, N.C.] :b| [East Carolina University],c| 2020.;

300 a| 42 pages :b| illustrations (some color);

336 a| textb| txt2| rdacontent;

337 a| computerb| c2| rdamedia;

338 a| online resourceb| cr2| rdacarrier;

347 a| text fileb| PDFc| 1.147 MB2| rda;

538 a| System requirements: Adobe Reader.;

538 a| Mode of access: World Wide Web.;

502 b| Computer Sciencec| East Carolina Universityd| 2020.;

500 a| Presented to the faculty of the Department of Computer Science.;

500 a| Advisor: Venkat Gudivada;

500 a| Title from PDF t.p. (viewed March 8, 2021).;

520 3 a| Question answering (QA) systems have evolved exponentially over the past few years and have reached a reliable human standard. Attention mechanisms, as well as other methods of deep learning, paved the way for this development. But, because of their single-pass nature, they are incapable of recovering from local maxima matching to incorrect answers. Dynamic coattention network (DCN) is used to answer this issue. But as it has only one layer, the ability of the DCN to write diverse input representations is limited. We proposed a few modifications to DCN to overcome these findings. First, we used a bidirectional long short-term memory network (biLSTM) to encode the question and document. Next, we applied the concept of self-attention to DCN by using multiple coattention layers. This helps the encoder to generate more profuse input representations. Lastly, we combine outputs from these layers; this improves the long-range dependencies. We built a question answering system based on this multiattention DCN and tested on one of our course documents. On Stanford question answering dataset (SQuAD), this system improves the F1 mean on validation to 79.9% from its previous state of art at 75.6%.;

504 a| Includes bibliographical references.;

650 0 a| Question-answering systems.=| ^A84757;

650 0 a| Human-computer interaction.=| ^A225132;

700 1 a| Gudivada, Venkat N.e| degree supervisor.=| ^A1308613;

710 2 a| East Carolina University.b| Department of Computer Science.?| UNAUTHORIZED;

856 40 z| Access via ScholarShipu| http://hdl.handle.net/10342/8646;

949 o| wjh;

994 a| C0b| ERE;

596 a| 1 4;

998 a| 5336221;

999 a| CLICK ON WEB ADDRESSw| ASISc| 1i| 5336221-1001l| JNETm| JOYNERr| Ys| Yt| JNE3ETDu| 7/9/2020x| ETDz| JERESOURCE;

999 a| CLICK ON WEB ADDRESSw| ASISc| 1i| 5336221-2001l| HSLELECm| HSLr| Ys| Yt| HEETDu| 7/9/2020x| ETDz| HERESOURCE;

A framework for question answering system using dynamic co-attention networks / by Swetha Busireddy.

Author/creator	Busireddy, Swetha author.
Other author	Gudivada, Venkat N. degree supervisor.
Other author	East Carolina University. Department of Computer Science.
Format	Theses and dissertations
Publication	[Greenville, N.C.] : [East Carolina University], 2020.
Description	42 pages : illustrations (some color)
Supplemental Content	Access via ScholarShip
Subjects	Question-answering systems. Human-computer interaction.

Summary	Question answering (QA) systems have evolved exponentially over the past few years and have reached a reliable human standard. Attention mechanisms, as well as other methods of deep learning, paved the way for this development. But, because of their single-pass nature, they are incapable of recovering from local maxima matching to incorrect answers. Dynamic coattention network (DCN) is used to answer this issue. But as it has only one layer, the ability of the DCN to write diverse input representations is limited. We proposed a few modifications to DCN to overcome these findings. First, we used a bidirectional long short-term memory network (biLSTM) to encode the question and document. Next, we applied the concept of self-attention to DCN by using multiple coattention layers. This helps the encoder to generate more profuse input representations. Lastly, we combine outputs from these layers; this improves the long-range dependencies. We built a question answering system based on this multiattention DCN and tested on one of our course documents. On Stanford question answering dataset (SQuAD), this system improves the F1 mean on validation to 79.9% from its previous state of art at 75.6%.
General note	Presented to the faculty of the Department of Computer Science.
General note	Advisor: Venkat Gudivada
General note	Title from PDF t.p. (viewed March 8, 2021).
Dissertation note	Computer Science East Carolina University 2020.
Bibliography note	Includes bibliographical references.
Technical details	System requirements: Adobe Reader.
Technical details	Mode of access: World Wide Web.

A framework for question answering system using dynamic co-attention networks / by Swetha Busireddy.

Click here for more information about this title