Topic Segmentation Model Focusing on Local Context
Topic segmentation is important in understanding scientific documents since it can not only provide better readability but also facilitate downstream tasks such as information retrieval and question answering by creating appropriate sections or paragraphs. In the topic segmentation task, topic coher...
Saved in:
Published in | arXiv.org |
---|---|
Main Authors | , , , |
Format | Paper |
Language | English |
Published |
Ithaca
Cornell University Library, arXiv.org
05.01.2023
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Topic segmentation is important in understanding scientific documents since it can not only provide better readability but also facilitate downstream tasks such as information retrieval and question answering by creating appropriate sections or paragraphs. In the topic segmentation task, topic coherence is critical in predicting segmentation boundaries. Most of the existing models have tried to exploit as many contexts as possible to extract useful topic-related information. However, additional context does not always bring promising results, because the local context between sentences becomes incoherent despite more sentences being supplemented. To alleviate this issue, we propose siamese sentence embedding layers which process two input sentences independently to get appropriate amount of information without being hampered by excessive information. Also, we adopt multi-task learning techniques including Same Topic Prediction (STP), Topic Classification (TC) and Next Sentence Prediction (NSP). When these three classification layers are combined in a multi-task manner, they can make up for each other's limitations, improving performance in all three tasks. We experiment different combinations of the three layers and report how each layer affects other layers in the same combination as well as the overall segmentation performance. The model we proposed achieves the state-of-the-art result in the WikiSection dataset. |
---|---|
AbstractList | Topic segmentation is important in understanding scientific documents since it can not only provide better readability but also facilitate downstream tasks such as information retrieval and question answering by creating appropriate sections or paragraphs. In the topic segmentation task, topic coherence is critical in predicting segmentation boundaries. Most of the existing models have tried to exploit as many contexts as possible to extract useful topic-related information. However, additional context does not always bring promising results, because the local context between sentences becomes incoherent despite more sentences being supplemented. To alleviate this issue, we propose siamese sentence embedding layers which process two input sentences independently to get appropriate amount of information without being hampered by excessive information. Also, we adopt multi-task learning techniques including Same Topic Prediction (STP), Topic Classification (TC) and Next Sentence Prediction (NSP). When these three classification layers are combined in a multi-task manner, they can make up for each other's limitations, improving performance in all three tasks. We experiment different combinations of the three layers and report how each layer affects other layers in the same combination as well as the overall segmentation performance. The model we proposed achieves the state-of-the-art result in the WikiSection dataset. |
Author | Baek, Sunghoon Song, Min Lee, Jeonghwan Han, Jiyeong |
Author_xml | – sequence: 1 givenname: Jeonghwan surname: Lee fullname: Lee, Jeonghwan – sequence: 2 givenname: Jiyeong surname: Han fullname: Han, Jiyeong – sequence: 3 givenname: Sunghoon surname: Baek fullname: Baek, Sunghoon – sequence: 4 givenname: Min surname: Song fullname: Song, Min |
BookMark | eNqNisEKgkAUAJcoyMp_WOgsrG9d9S5JhzrlXURfomzvmbtCn5-HPqDTwMwcxJaYcCMC0DqO8gRgL0LnRqUUpBkYowMBFU9DKx_Yv5B84wcmeecOrSy5XdxAvVzNjdvGyoLJ48efxO7ZWIfhj0dxLi9VcY2mmd8LOl-PvMy0phqyNE7i3KhE_3d9AfLANUo |
ContentType | Paper |
Copyright | 2023. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
Copyright_xml | – notice: 2023. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
DBID | 8FE 8FG ABJCF ABUWG AFKRA AZQEC BENPR BGLVJ CCPQU DWQXO HCIFZ L6V M7S PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
DatabaseName | ProQuest SciTech Collection ProQuest Technology Collection Materials Science & Engineering Collection ProQuest Central (Alumni) ProQuest Central UK/Ireland ProQuest Central Essentials ProQuest Central Technology Collection ProQuest One Community College ProQuest Central Korea SciTech Premium Collection ProQuest Engineering Collection Engineering Database Publicly Available Content Database ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic ProQuest One Academic UKI Edition ProQuest Central China Engineering Collection |
DatabaseTitle | Publicly Available Content Database Engineering Database Technology Collection ProQuest Central Essentials ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Technology Collection ProQuest SciTech Collection ProQuest Central China ProQuest Central ProQuest Engineering Collection ProQuest One Academic UKI Edition ProQuest Central Korea Materials Science & Engineering Collection ProQuest One Academic Engineering Collection |
DatabaseTitleList | Publicly Available Content Database |
Database_xml | – sequence: 1 dbid: 8FG name: ProQuest Technology Collection url: https://search.proquest.com/technologycollection1 sourceTypes: Aggregation Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Physics |
EISSN | 2331-8422 |
Genre | Working Paper/Pre-Print |
GroupedDBID | 8FE 8FG ABJCF ABUWG AFKRA ALMA_UNASSIGNED_HOLDINGS AZQEC BENPR BGLVJ CCPQU DWQXO FRJ HCIFZ L6V M7S M~E PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
ID | FETCH-proquest_journals_27614185043 |
IEDL.DBID | BENPR |
IngestDate | Thu Oct 10 20:38:21 EDT 2024 |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-proquest_journals_27614185043 |
OpenAccessLink | https://www.proquest.com/docview/2761418504?pq-origsite=%requestingapplication% |
PQID | 2761418504 |
PQPubID | 2050157 |
ParticipantIDs | proquest_journals_2761418504 |
PublicationCentury | 2000 |
PublicationDate | 20230105 |
PublicationDateYYYYMMDD | 2023-01-05 |
PublicationDate_xml | – month: 01 year: 2023 text: 20230105 day: 05 |
PublicationDecade | 2020 |
PublicationPlace | Ithaca |
PublicationPlace_xml | – name: Ithaca |
PublicationTitle | arXiv.org |
PublicationYear | 2023 |
Publisher | Cornell University Library, arXiv.org |
Publisher_xml | – name: Cornell University Library, arXiv.org |
SSID | ssj0002672553 |
Score | 3.4493685 |
SecondaryResourceType | preprint |
Snippet | Topic segmentation is important in understanding scientific documents since it can not only provide better readability but also facilitate downstream tasks... |
SourceID | proquest |
SourceType | Aggregation Database |
SubjectTerms | Classification Context Information retrieval Segmentation |
Title | Topic Segmentation Model Focusing on Local Context |
URI | https://www.proquest.com/docview/2761418504 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwY2BQMU6zSDY2MU7VtUwDNt9M0owsdZNAZxEaA7tiZklJQGwI2ijs62fmEWriFWEaAR1wK4Yuq4SVieCCOiU_GTRGrm8E7G-DDloxMLEvKNQF3RoFml2FXqHBzMBqBJQFpnBWJ1e_gCD4KIuRmTmwzWyMUdCCaw83QQbWgMSC1CIhBqbUPGEGdvCiy-RiEQajkPyCzGSF4NT0XOgOoDwF0N1kOQpu-cmgBenpCkARH1BtowA-RaqiRJRB2c01xNlDF2ZRPDQxFMcjnG4sxsAC7NWnSjAopAKrDwNgYyHZODUN1KlKBEobpKWamZskmRgaGZlLMsjgM0kKv7Q0AxfoXnTwWIGpDANLSVFpqiyw9ixJkmNgtnBzl4MGFJDnW-cKAC37eDc |
link.rule.ids | 786,790,12792,21416,33406,33777,43633,43838 |
linkProvider | ProQuest |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwY2BQMU6zSDY2MU7VtUwDNt9M0owsdZNAZxEaA7tiZklJQGwI2ijs62fmEWriFWEaAR1wK4Yuq4SVieCCOiU_GTRGrm8E7G-DDloxMLEvKNQF3RoFml2FXqHBzMAKOnLTgoWB1cnVLyAIPspiZGYObDMbYxS04NrDTZCBNSCxILVIiIEpNU-YgR286DK5WITBKCS_IDNZITg1PRe6AyhPAXQ3WY6CW34yaEF6ugJQxAdU2yiAT5GqKBFlUHZzDXH20IVZFA9NDMXxCKcbizGwAHv1qRIMCqnA6sMA2FhINk5NA3WqEoHSBmmpZuYmSSaGRkbmkgwy-EySwi8tz8DpEeLrE-_j6ectzcAFuiMdPG5gKsPAUlJUmioLrElLkuSgwQUAVAZ5Fg |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Topic+Segmentation+Model+Focusing+on+Local+Context&rft.jtitle=arXiv.org&rft.au=Lee%2C+Jeonghwan&rft.au=Han%2C+Jiyeong&rft.au=Baek%2C+Sunghoon&rft.au=Song%2C+Min&rft.date=2023-01-05&rft.pub=Cornell+University+Library%2C+arXiv.org&rft.eissn=2331-8422 |