The effect of morphology in named entity recognition with sequence tagging
This work proposes a sequential tagger for named entity recognition in morphologically rich languages. Several schemes for representing the morphological analysis of a word in the context of named entity recognition are examined. Word representations are formed by concatenating word and character em...
Gespeichert in:
| Veröffentlicht in: | Natural language engineering 2019-01, Vol.25 (1), p.147-169 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 169 |
|---|---|
| container_issue | 1 |
| container_start_page | 147 |
| container_title | Natural language engineering |
| container_volume | 25 |
| creator | GÜNGÖR, ONUR GÜNGÖR, TUNGA ÜSKÜDARLI, SUZAN |
| description | This work proposes a sequential tagger for named entity recognition in morphologically rich languages. Several schemes for representing the morphological analysis of a word in the context of named entity recognition are examined. Word representations are formed by concatenating word and character embeddings with the morphological embeddings based on these schemes. The impact of these representations is measured by training and evaluating a sequential tagger composed of a conditional random field layer on top of a bidirectional long short-term memory layer. Experiments with Turkish, Czech, Hungarian, Finnish and Spanish produce the state-of-the-art results for all these languages, indicating that the representation of morphological information improves performance. |
| doi_str_mv | 10.1017/S1351324918000281 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2158191972</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><cupid>10_1017_S1351324918000281</cupid><sourcerecordid>2158191972</sourcerecordid><originalsourceid>FETCH-LOGICAL-c317t-9dce66f6abe33c43afd7313de4221539aa4c7b9dde3ad01f9f2c4e72db80a4393</originalsourceid><addsrcrecordid>eNp1kE9LAzEQxYMoWKsfwFvA82pmk-5ujlL8S8GD9bxkk8k2pZvUbIr02xtpwYN4moH3e2-GR8g1sFtgUN-9A58BL4WEhjFWNnBCJiAqWTQA7DTvWS5-9HNyMY7rzAioxYS8LldI0VrUiQZLhxC3q7AJ_Z46T70a0FD0yaU9jahD711ywdMvl1Z0xM8deo00qb53vr8kZ1ZtRrw6zin5eHxYzp-LxdvTy_x-UWgOdSqk0VhVtlIdcq4FV9bUHLhBUZYw41IpoetOGoNcGQZW2lILrEvTNUwJLvmU3BxytzHkD8bUrsMu-nyyzQENSJB1mSk4UDqGcYxo2210g4r7Flj7U1n7p7Ls4UePGrroTI-_0f-7vgG6RW4K</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2158191972</pqid></control><display><type>article</type><title>The effect of morphology in named entity recognition with sequence tagging</title><source>Cambridge University Press Journals Complete</source><creator>GÜNGÖR, ONUR ; GÜNGÖR, TUNGA ; ÜSKÜDARLI, SUZAN</creator><creatorcontrib>GÜNGÖR, ONUR ; GÜNGÖR, TUNGA ; ÜSKÜDARLI, SUZAN</creatorcontrib><description>This work proposes a sequential tagger for named entity recognition in morphologically rich languages. Several schemes for representing the morphological analysis of a word in the context of named entity recognition are examined. Word representations are formed by concatenating word and character embeddings with the morphological embeddings based on these schemes. The impact of these representations is measured by training and evaluating a sequential tagger composed of a conditional random field layer on top of a bidirectional long short-term memory layer. Experiments with Turkish, Czech, Hungarian, Finnish and Spanish produce the state-of-the-art results for all these languages, indicating that the representation of morphological information improves performance.</description><identifier>ISSN: 1351-3249</identifier><identifier>EISSN: 1469-8110</identifier><identifier>DOI: 10.1017/S1351324918000281</identifier><language>eng</language><publisher>Cambridge, UK: Cambridge University Press</publisher><subject>Czech language ; Experiments ; Finnish language ; Hungarian language ; Hypotheses ; Kennedy, John Fitzgerald (1917-1963) ; Languages ; Morphological analysis ; Morphology ; Natural language ; Performance enhancement ; Recognition ; Representations ; Semantics ; Short term memory ; Spanish language ; State of the art ; Tagging (Computational linguistics) ; Turkish language</subject><ispartof>Natural language engineering, 2019-01, Vol.25 (1), p.147-169</ispartof><rights>Copyright © Cambridge University Press 2018</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c317t-9dce66f6abe33c43afd7313de4221539aa4c7b9dde3ad01f9f2c4e72db80a4393</citedby><cites>FETCH-LOGICAL-c317t-9dce66f6abe33c43afd7313de4221539aa4c7b9dde3ad01f9f2c4e72db80a4393</cites><orcidid>0000-0002-7843-1439</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.cambridge.org/core/product/identifier/S1351324918000281/type/journal_article$$EHTML$$P50$$Gcambridge$$H</linktohtml><link.rule.ids>164,314,780,784,27924,27925,55628</link.rule.ids></links><search><creatorcontrib>GÜNGÖR, ONUR</creatorcontrib><creatorcontrib>GÜNGÖR, TUNGA</creatorcontrib><creatorcontrib>ÜSKÜDARLI, SUZAN</creatorcontrib><title>The effect of morphology in named entity recognition with sequence tagging</title><title>Natural language engineering</title><addtitle>Nat. Lang. Eng</addtitle><description>This work proposes a sequential tagger for named entity recognition in morphologically rich languages. Several schemes for representing the morphological analysis of a word in the context of named entity recognition are examined. Word representations are formed by concatenating word and character embeddings with the morphological embeddings based on these schemes. The impact of these representations is measured by training and evaluating a sequential tagger composed of a conditional random field layer on top of a bidirectional long short-term memory layer. Experiments with Turkish, Czech, Hungarian, Finnish and Spanish produce the state-of-the-art results for all these languages, indicating that the representation of morphological information improves performance.</description><subject>Czech language</subject><subject>Experiments</subject><subject>Finnish language</subject><subject>Hungarian language</subject><subject>Hypotheses</subject><subject>Kennedy, John Fitzgerald (1917-1963)</subject><subject>Languages</subject><subject>Morphological analysis</subject><subject>Morphology</subject><subject>Natural language</subject><subject>Performance enhancement</subject><subject>Recognition</subject><subject>Representations</subject><subject>Semantics</subject><subject>Short term memory</subject><subject>Spanish language</subject><subject>State of the art</subject><subject>Tagging (Computational linguistics)</subject><subject>Turkish language</subject><issn>1351-3249</issn><issn>1469-8110</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GNUQQ</sourceid><recordid>eNp1kE9LAzEQxYMoWKsfwFvA82pmk-5ujlL8S8GD9bxkk8k2pZvUbIr02xtpwYN4moH3e2-GR8g1sFtgUN-9A58BL4WEhjFWNnBCJiAqWTQA7DTvWS5-9HNyMY7rzAioxYS8LldI0VrUiQZLhxC3q7AJ_Z46T70a0FD0yaU9jahD711ywdMvl1Z0xM8deo00qb53vr8kZ1ZtRrw6zin5eHxYzp-LxdvTy_x-UWgOdSqk0VhVtlIdcq4FV9bUHLhBUZYw41IpoetOGoNcGQZW2lILrEvTNUwJLvmU3BxytzHkD8bUrsMu-nyyzQENSJB1mSk4UDqGcYxo2210g4r7Flj7U1n7p7Ls4UePGrroTI-_0f-7vgG6RW4K</recordid><startdate>201901</startdate><enddate>201901</enddate><creator>GÜNGÖR, ONUR</creator><creator>GÜNGÖR, TUNGA</creator><creator>ÜSKÜDARLI, SUZAN</creator><general>Cambridge University Press</general><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7T9</scope><scope>7XB</scope><scope>88G</scope><scope>8AL</scope><scope>8FE</scope><scope>8FG</scope><scope>8FI</scope><scope>8FJ</scope><scope>8FK</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>ALSLI</scope><scope>ARAPS</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>CPGLG</scope><scope>CRLPW</scope><scope>DWQXO</scope><scope>FYUFA</scope><scope>GHDGH</scope><scope>GNUQQ</scope><scope>HCIFZ</scope><scope>JQ2</scope><scope>K7-</scope><scope>L6V</scope><scope>M0N</scope><scope>M2M</scope><scope>M7S</scope><scope>P5Z</scope><scope>P62</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PSYQQ</scope><scope>PTHSS</scope><scope>Q9U</scope><orcidid>https://orcid.org/0000-0002-7843-1439</orcidid></search><sort><creationdate>201901</creationdate><title>The effect of morphology in named entity recognition with sequence tagging</title><author>GÜNGÖR, ONUR ; GÜNGÖR, TUNGA ; ÜSKÜDARLI, SUZAN</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c317t-9dce66f6abe33c43afd7313de4221539aa4c7b9dde3ad01f9f2c4e72db80a4393</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Czech language</topic><topic>Experiments</topic><topic>Finnish language</topic><topic>Hungarian language</topic><topic>Hypotheses</topic><topic>Kennedy, John Fitzgerald (1917-1963)</topic><topic>Languages</topic><topic>Morphological analysis</topic><topic>Morphology</topic><topic>Natural language</topic><topic>Performance enhancement</topic><topic>Recognition</topic><topic>Representations</topic><topic>Semantics</topic><topic>Short term memory</topic><topic>Spanish language</topic><topic>State of the art</topic><topic>Tagging (Computational linguistics)</topic><topic>Turkish language</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>GÜNGÖR, ONUR</creatorcontrib><creatorcontrib>GÜNGÖR, TUNGA</creatorcontrib><creatorcontrib>ÜSKÜDARLI, SUZAN</creatorcontrib><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>Linguistics and Language Behavior Abstracts (LLBA)</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Psychology Database (Alumni)</collection><collection>Computing Database (Alumni Edition)</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Hospital Premium Collection</collection><collection>Hospital Premium Collection (Alumni Edition)</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>Social Science Premium Collection</collection><collection>Advanced Technologies & Aerospace Collection</collection><collection>ProQuest Central Essentials</collection><collection>Proquest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>Linguistics Collection</collection><collection>Linguistics Database</collection><collection>ProQuest Central Korea</collection><collection>Health Research Premium Collection</collection><collection>Health Research Premium Collection (Alumni)</collection><collection>ProQuest Central Student</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Computer Science Collection</collection><collection>Computer Science Database</collection><collection>ProQuest Engineering Collection</collection><collection>Computing Database</collection><collection>Psychology Database</collection><collection>Engineering Database</collection><collection>Advanced Technologies & Aerospace Database</collection><collection>ProQuest Advanced Technologies & Aerospace Collection</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest One Psychology</collection><collection>Engineering Collection</collection><collection>ProQuest Central Basic</collection><jtitle>Natural language engineering</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>GÜNGÖR, ONUR</au><au>GÜNGÖR, TUNGA</au><au>ÜSKÜDARLI, SUZAN</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>The effect of morphology in named entity recognition with sequence tagging</atitle><jtitle>Natural language engineering</jtitle><addtitle>Nat. Lang. Eng</addtitle><date>2019-01</date><risdate>2019</risdate><volume>25</volume><issue>1</issue><spage>147</spage><epage>169</epage><pages>147-169</pages><issn>1351-3249</issn><eissn>1469-8110</eissn><abstract>This work proposes a sequential tagger for named entity recognition in morphologically rich languages. Several schemes for representing the morphological analysis of a word in the context of named entity recognition are examined. Word representations are formed by concatenating word and character embeddings with the morphological embeddings based on these schemes. The impact of these representations is measured by training and evaluating a sequential tagger composed of a conditional random field layer on top of a bidirectional long short-term memory layer. Experiments with Turkish, Czech, Hungarian, Finnish and Spanish produce the state-of-the-art results for all these languages, indicating that the representation of morphological information improves performance.</abstract><cop>Cambridge, UK</cop><pub>Cambridge University Press</pub><doi>10.1017/S1351324918000281</doi><tpages>23</tpages><orcidid>https://orcid.org/0000-0002-7843-1439</orcidid></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1351-3249 |
| ispartof | Natural language engineering, 2019-01, Vol.25 (1), p.147-169 |
| issn | 1351-3249 1469-8110 |
| language | eng |
| recordid | cdi_proquest_journals_2158191972 |
| source | Cambridge University Press Journals Complete |
| subjects | Czech language Experiments Finnish language Hungarian language Hypotheses Kennedy, John Fitzgerald (1917-1963) Languages Morphological analysis Morphology Natural language Performance enhancement Recognition Representations Semantics Short term memory Spanish language State of the art Tagging (Computational linguistics) Turkish language |
| title | The effect of morphology in named entity recognition with sequence tagging |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-22T11%3A05%3A54IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=The%20effect%20of%20morphology%20in%20named%20entity%20recognition%20with%20sequence%20tagging&rft.jtitle=Natural%20language%20engineering&rft.au=G%C3%9CNG%C3%96R,%20ONUR&rft.date=2019-01&rft.volume=25&rft.issue=1&rft.spage=147&rft.epage=169&rft.pages=147-169&rft.issn=1351-3249&rft.eissn=1469-8110&rft_id=info:doi/10.1017/S1351324918000281&rft_dat=%3Cproquest_cross%3E2158191972%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2158191972&rft_id=info:pmid/&rft_cupid=10_1017_S1351324918000281&rfr_iscdi=true |