Effectiveness of Deep Networks in NLP using BiDAF as an example architecture

Question Answering with NLP has progressed through the evolution of advanced model architectures like BERT and BiDAF and earlier word, character, and context-based embeddings. As BERT has leapfrogged the accuracy of models, an element of the next frontier can be the introduction of deep networks and...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Sarkar, Soumyendu
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Sarkar, Soumyendu
description Question Answering with NLP has progressed through the evolution of advanced model architectures like BERT and BiDAF and earlier word, character, and context-based embeddings. As BERT has leapfrogged the accuracy of models, an element of the next frontier can be the introduction of deep networks and an effective way to train them. In this context, I explored the effectiveness of deep networks focussing on the model encoder layer of BiDAF. BiDAF with its heterogeneous layers provides the opportunity not only to explore the effectiveness of deep networks but also to evaluate whether the refinements made in lower layers are additive to the refinements made in the upper layers of the model architecture. I believe the next greatest model in NLP will in fact fold in a solid language modeling like BERT with a composite architecture which will bring in refinements in addition to generic language modeling and will have a more extensive layered architecture. I experimented with the Bypass network, Residual Highway network, and DenseNet architectures. In addition, I evaluated the effectiveness of ensembling the last few layers of the network. I also studied the difference character embeddings make in adding them to the word embeddings, and whether the effects are additive with deep networks. My studies indicate that deep networks are in fact effective in giving a boost. Also, the refinements in the lower layers like embeddings are passed on additively to the gains made through deep networks.
doi_str_mv 10.48550/arxiv.2109.00074
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2109_00074</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2109_00074</sourcerecordid><originalsourceid>FETCH-LOGICAL-a674-4deb5e343d317d4d63d5dcacf4ff420dec832e7542f7a3ea0d94998fb3fba5783</originalsourceid><addsrcrecordid>eNotz71OwzAUQGEvDKjwAEzcF0hwYrtOxtIfQIoKQ_foxr4XLNo0stNS3h5omc52pE-Iu0LmujJGPmA8hWNeFrLOpZRWX4tmyUxuDEfqKSXYMyyIBljT-LWPnwlCD-vmDQ4p9O_wGBazFWAC7IFOuBu2BBjdRxh_F4dIN-KKcZvo9r8TsVktN_PnrHl9epnPmgynVmfaU2dIaeVVYb32U-WNd-hYM-tSenKVKskaXbJFRSh9reu64k5xh8ZWaiLuL9szpx1i2GH8bv9Y7ZmlfgB_e0gJ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Effectiveness of Deep Networks in NLP using BiDAF as an example architecture</title><source>arXiv.org</source><creator>Sarkar, Soumyendu</creator><creatorcontrib>Sarkar, Soumyendu</creatorcontrib><description>Question Answering with NLP has progressed through the evolution of advanced model architectures like BERT and BiDAF and earlier word, character, and context-based embeddings. As BERT has leapfrogged the accuracy of models, an element of the next frontier can be the introduction of deep networks and an effective way to train them. In this context, I explored the effectiveness of deep networks focussing on the model encoder layer of BiDAF. BiDAF with its heterogeneous layers provides the opportunity not only to explore the effectiveness of deep networks but also to evaluate whether the refinements made in lower layers are additive to the refinements made in the upper layers of the model architecture. I believe the next greatest model in NLP will in fact fold in a solid language modeling like BERT with a composite architecture which will bring in refinements in addition to generic language modeling and will have a more extensive layered architecture. I experimented with the Bypass network, Residual Highway network, and DenseNet architectures. In addition, I evaluated the effectiveness of ensembling the last few layers of the network. I also studied the difference character embeddings make in adding them to the word embeddings, and whether the effects are additive with deep networks. My studies indicate that deep networks are in fact effective in giving a boost. Also, the refinements in the lower layers like embeddings are passed on additively to the gains made through deep networks.</description><identifier>DOI: 10.48550/arxiv.2109.00074</identifier><language>eng</language><subject>Computer Science - Computation and Language ; Computer Science - Learning</subject><creationdate>2021-08</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,778,883</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2109.00074$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2109.00074$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Sarkar, Soumyendu</creatorcontrib><title>Effectiveness of Deep Networks in NLP using BiDAF as an example architecture</title><description>Question Answering with NLP has progressed through the evolution of advanced model architectures like BERT and BiDAF and earlier word, character, and context-based embeddings. As BERT has leapfrogged the accuracy of models, an element of the next frontier can be the introduction of deep networks and an effective way to train them. In this context, I explored the effectiveness of deep networks focussing on the model encoder layer of BiDAF. BiDAF with its heterogeneous layers provides the opportunity not only to explore the effectiveness of deep networks but also to evaluate whether the refinements made in lower layers are additive to the refinements made in the upper layers of the model architecture. I believe the next greatest model in NLP will in fact fold in a solid language modeling like BERT with a composite architecture which will bring in refinements in addition to generic language modeling and will have a more extensive layered architecture. I experimented with the Bypass network, Residual Highway network, and DenseNet architectures. In addition, I evaluated the effectiveness of ensembling the last few layers of the network. I also studied the difference character embeddings make in adding them to the word embeddings, and whether the effects are additive with deep networks. My studies indicate that deep networks are in fact effective in giving a boost. Also, the refinements in the lower layers like embeddings are passed on additively to the gains made through deep networks.</description><subject>Computer Science - Computation and Language</subject><subject>Computer Science - Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz71OwzAUQGEvDKjwAEzcF0hwYrtOxtIfQIoKQ_foxr4XLNo0stNS3h5omc52pE-Iu0LmujJGPmA8hWNeFrLOpZRWX4tmyUxuDEfqKSXYMyyIBljT-LWPnwlCD-vmDQ4p9O_wGBazFWAC7IFOuBu2BBjdRxh_F4dIN-KKcZvo9r8TsVktN_PnrHl9epnPmgynVmfaU2dIaeVVYb32U-WNd-hYM-tSenKVKskaXbJFRSh9reu64k5xh8ZWaiLuL9szpx1i2GH8bv9Y7ZmlfgB_e0gJ</recordid><startdate>20210831</startdate><enddate>20210831</enddate><creator>Sarkar, Soumyendu</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20210831</creationdate><title>Effectiveness of Deep Networks in NLP using BiDAF as an example architecture</title><author>Sarkar, Soumyendu</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a674-4deb5e343d317d4d63d5dcacf4ff420dec832e7542f7a3ea0d94998fb3fba5783</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Computer Science - Computation and Language</topic><topic>Computer Science - Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Sarkar, Soumyendu</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Sarkar, Soumyendu</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Effectiveness of Deep Networks in NLP using BiDAF as an example architecture</atitle><date>2021-08-31</date><risdate>2021</risdate><abstract>Question Answering with NLP has progressed through the evolution of advanced model architectures like BERT and BiDAF and earlier word, character, and context-based embeddings. As BERT has leapfrogged the accuracy of models, an element of the next frontier can be the introduction of deep networks and an effective way to train them. In this context, I explored the effectiveness of deep networks focussing on the model encoder layer of BiDAF. BiDAF with its heterogeneous layers provides the opportunity not only to explore the effectiveness of deep networks but also to evaluate whether the refinements made in lower layers are additive to the refinements made in the upper layers of the model architecture. I believe the next greatest model in NLP will in fact fold in a solid language modeling like BERT with a composite architecture which will bring in refinements in addition to generic language modeling and will have a more extensive layered architecture. I experimented with the Bypass network, Residual Highway network, and DenseNet architectures. In addition, I evaluated the effectiveness of ensembling the last few layers of the network. I also studied the difference character embeddings make in adding them to the word embeddings, and whether the effects are additive with deep networks. My studies indicate that deep networks are in fact effective in giving a boost. Also, the refinements in the lower layers like embeddings are passed on additively to the gains made through deep networks.</abstract><doi>10.48550/arxiv.2109.00074</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2109.00074
ispartof
issn
language eng
recordid cdi_arxiv_primary_2109_00074
source arXiv.org
subjects Computer Science - Computation and Language
Computer Science - Learning
title Effectiveness of Deep Networks in NLP using BiDAF as an example architecture
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-15T21%3A48%3A15IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Effectiveness%20of%20Deep%20Networks%20in%20NLP%20using%20BiDAF%20as%20an%20example%20architecture&rft.au=Sarkar,%20Soumyendu&rft.date=2021-08-31&rft_id=info:doi/10.48550/arxiv.2109.00074&rft_dat=%3Carxiv_GOX%3E2109_00074%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true