Is ChatGPT A Good Keyphrase Generator? A Preliminary Study
The emergence of ChatGPT has recently garnered significant attention from the computational linguistics community. To demonstrate its capabilities as a keyphrase generator, we conduct a preliminary evaluation of ChatGPT for the keyphrase generation task. We evaluate its performance in various aspect...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2023-12 |
---|---|
Hauptverfasser: | , , , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | arXiv.org |
container_volume | |
creator | Song, Mingyang Jiang, Haiyun Shi, Shuming Yao, Songfang Lu, Shilong Feng, Yi Liu, Huafeng Jing, Liping |
description | The emergence of ChatGPT has recently garnered significant attention from the computational linguistics community. To demonstrate its capabilities as a keyphrase generator, we conduct a preliminary evaluation of ChatGPT for the keyphrase generation task. We evaluate its performance in various aspects, including keyphrase generation prompts, keyphrase generation diversity, and long document understanding. Our evaluation is based on six benchmark datasets, and we adopt the prompt suggested by OpenAI while extending it to six candidate prompts. We find that ChatGPT performs exceptionally well on all six candidate prompts, with minor performance differences observed across the datasets. Based on our findings, we conclude that ChatGPT has great potential for keyphrase generation. Moreover, we discover that ChatGPT still faces challenges when it comes to generating absent keyphrases. Meanwhile, in the final section, we also present some limitations and future expansions of this report. |
format | Article |
fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2790189013</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2790189013</sourcerecordid><originalsourceid>FETCH-proquest_journals_27901890133</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mSw8ixWcM5ILHEPCFFwVHDPz09R8E6tLMgoSixOVXBPzUstSizJL7IHygUUpeZk5mbmJRZVKgSXlKZU8jCwpiXmFKfyQmluBmU31xBnD92CovzC0tTikvis_NKiPKBUvJG5pYGhBRAbGxOnCgAEgzV4</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2790189013</pqid></control><display><type>article</type><title>Is ChatGPT A Good Keyphrase Generator? A Preliminary Study</title><source>Free E- Journals</source><creator>Song, Mingyang ; Jiang, Haiyun ; Shi, Shuming ; Yao, Songfang ; Lu, Shilong ; Feng, Yi ; Liu, Huafeng ; Jing, Liping</creator><creatorcontrib>Song, Mingyang ; Jiang, Haiyun ; Shi, Shuming ; Yao, Songfang ; Lu, Shilong ; Feng, Yi ; Liu, Huafeng ; Jing, Liping</creatorcontrib><description>The emergence of ChatGPT has recently garnered significant attention from the computational linguistics community. To demonstrate its capabilities as a keyphrase generator, we conduct a preliminary evaluation of ChatGPT for the keyphrase generation task. We evaluate its performance in various aspects, including keyphrase generation prompts, keyphrase generation diversity, and long document understanding. Our evaluation is based on six benchmark datasets, and we adopt the prompt suggested by OpenAI while extending it to six candidate prompts. We find that ChatGPT performs exceptionally well on all six candidate prompts, with minor performance differences observed across the datasets. Based on our findings, we conclude that ChatGPT has great potential for keyphrase generation. Moreover, we discover that ChatGPT still faces challenges when it comes to generating absent keyphrases. Meanwhile, in the final section, we also present some limitations and future expansions of this report.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Chatbots ; Datasets ; Linguistics ; Performance evaluation</subject><ispartof>arXiv.org, 2023-12</ispartof><rights>2023. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</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>780,784</link.rule.ids></links><search><creatorcontrib>Song, Mingyang</creatorcontrib><creatorcontrib>Jiang, Haiyun</creatorcontrib><creatorcontrib>Shi, Shuming</creatorcontrib><creatorcontrib>Yao, Songfang</creatorcontrib><creatorcontrib>Lu, Shilong</creatorcontrib><creatorcontrib>Feng, Yi</creatorcontrib><creatorcontrib>Liu, Huafeng</creatorcontrib><creatorcontrib>Jing, Liping</creatorcontrib><title>Is ChatGPT A Good Keyphrase Generator? A Preliminary Study</title><title>arXiv.org</title><description>The emergence of ChatGPT has recently garnered significant attention from the computational linguistics community. To demonstrate its capabilities as a keyphrase generator, we conduct a preliminary evaluation of ChatGPT for the keyphrase generation task. We evaluate its performance in various aspects, including keyphrase generation prompts, keyphrase generation diversity, and long document understanding. Our evaluation is based on six benchmark datasets, and we adopt the prompt suggested by OpenAI while extending it to six candidate prompts. We find that ChatGPT performs exceptionally well on all six candidate prompts, with minor performance differences observed across the datasets. Based on our findings, we conclude that ChatGPT has great potential for keyphrase generation. Moreover, we discover that ChatGPT still faces challenges when it comes to generating absent keyphrases. Meanwhile, in the final section, we also present some limitations and future expansions of this report.</description><subject>Chatbots</subject><subject>Datasets</subject><subject>Linguistics</subject><subject>Performance evaluation</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mSw8ixWcM5ILHEPCFFwVHDPz09R8E6tLMgoSixOVXBPzUstSizJL7IHygUUpeZk5mbmJRZVKgSXlKZU8jCwpiXmFKfyQmluBmU31xBnD92CovzC0tTikvis_NKiPKBUvJG5pYGhBRAbGxOnCgAEgzV4</recordid><startdate>20231222</startdate><enddate>20231222</enddate><creator>Song, Mingyang</creator><creator>Jiang, Haiyun</creator><creator>Shi, Shuming</creator><creator>Yao, Songfang</creator><creator>Lu, Shilong</creator><creator>Feng, Yi</creator><creator>Liu, Huafeng</creator><creator>Jing, Liping</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20231222</creationdate><title>Is ChatGPT A Good Keyphrase Generator? A Preliminary Study</title><author>Song, Mingyang ; Jiang, Haiyun ; Shi, Shuming ; Yao, Songfang ; Lu, Shilong ; Feng, Yi ; Liu, Huafeng ; Jing, Liping</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_27901890133</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Chatbots</topic><topic>Datasets</topic><topic>Linguistics</topic><topic>Performance evaluation</topic><toplevel>online_resources</toplevel><creatorcontrib>Song, Mingyang</creatorcontrib><creatorcontrib>Jiang, Haiyun</creatorcontrib><creatorcontrib>Shi, Shuming</creatorcontrib><creatorcontrib>Yao, Songfang</creatorcontrib><creatorcontrib>Lu, Shilong</creatorcontrib><creatorcontrib>Feng, Yi</creatorcontrib><creatorcontrib>Liu, Huafeng</creatorcontrib><creatorcontrib>Jing, Liping</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</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 Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Song, Mingyang</au><au>Jiang, Haiyun</au><au>Shi, Shuming</au><au>Yao, Songfang</au><au>Lu, Shilong</au><au>Feng, Yi</au><au>Liu, Huafeng</au><au>Jing, Liping</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Is ChatGPT A Good Keyphrase Generator? A Preliminary Study</atitle><jtitle>arXiv.org</jtitle><date>2023-12-22</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>The emergence of ChatGPT has recently garnered significant attention from the computational linguistics community. To demonstrate its capabilities as a keyphrase generator, we conduct a preliminary evaluation of ChatGPT for the keyphrase generation task. We evaluate its performance in various aspects, including keyphrase generation prompts, keyphrase generation diversity, and long document understanding. Our evaluation is based on six benchmark datasets, and we adopt the prompt suggested by OpenAI while extending it to six candidate prompts. We find that ChatGPT performs exceptionally well on all six candidate prompts, with minor performance differences observed across the datasets. Based on our findings, we conclude that ChatGPT has great potential for keyphrase generation. Moreover, we discover that ChatGPT still faces challenges when it comes to generating absent keyphrases. Meanwhile, in the final section, we also present some limitations and future expansions of this report.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | EISSN: 2331-8422 |
ispartof | arXiv.org, 2023-12 |
issn | 2331-8422 |
language | eng |
recordid | cdi_proquest_journals_2790189013 |
source | Free E- Journals |
subjects | Chatbots Datasets Linguistics Performance evaluation |
title | Is ChatGPT A Good Keyphrase Generator? A Preliminary Study |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-05T03%3A26%3A01IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Is%20ChatGPT%20A%20Good%20Keyphrase%20Generator?%20A%20Preliminary%20Study&rft.jtitle=arXiv.org&rft.au=Song,%20Mingyang&rft.date=2023-12-22&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2790189013%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2790189013&rft_id=info:pmid/&rfr_iscdi=true |