Just What You Desire: Constrained Timeline Summarization with Self-Reflection for Enhanced Relevance
Given news articles about an entity, such as a public figure or organization, timeline summarization (TLS) involves generating a timeline that summarizes the key events about the entity. However, the TLS task is too underspecified, since what is of interest to each reader may vary, and hence there i...
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| 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 | Qorib, Muhammad Reza Hu, Qisheng Ng, Hwee Tou |
| description | Given news articles about an entity, such as a public figure or organization,
timeline summarization (TLS) involves generating a timeline that summarizes the
key events about the entity. However, the TLS task is too underspecified, since
what is of interest to each reader may vary, and hence there is not a single
ideal or optimal timeline. In this paper, we introduce a novel task, called
Constrained Timeline Summarization (CTLS), where a timeline is generated in
which all events in the timeline meet some constraint. An example of a
constrained timeline concerns the legal battles of Tiger Woods, where only
events related to his legal problems are selected to appear in the timeline. We
collected a new human-verified dataset of constrained timelines involving 47
entities and 5 constraints per entity. We propose an approach that employs a
large language model (LLM) to summarize news articles according to a specified
constraint and cluster them to identify key events to include in a constrained
timeline. In addition, we propose a novel self-reflection method during summary
generation, demonstrating that this approach successfully leads to improved
performance. |
| doi_str_mv | 10.48550/arxiv.2412.17408 |
| format | Article |
| fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2412_17408</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2412_17408</sourcerecordid><originalsourceid>FETCH-arxiv_primary_2412_174083</originalsourceid><addsrcrecordid>eNqFjk8LgkAUxPfSIaoP0Kn3BTQtJelqRnRUITrJom_xwbob62p_Pn0q3TvNMMwMP8bWvucGURh6W25e1Lu7wN-5_iHwojmrrl1r4VZzC3fdwQlbMniEWKvWGk4KK8ipQTk4yLqm4YY-3JJW8CRbQ4ZSOCkKieUUCm0gUTVX5TBMUWI_2iWbCS5bXP10wTbnJI8vzsRTPAwNv-9i5Comrv3_xhd6qEPw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Just What You Desire: Constrained Timeline Summarization with Self-Reflection for Enhanced Relevance</title><source>arXiv.org</source><creator>Qorib, Muhammad Reza ; Hu, Qisheng ; Ng, Hwee Tou</creator><creatorcontrib>Qorib, Muhammad Reza ; Hu, Qisheng ; Ng, Hwee Tou</creatorcontrib><description>Given news articles about an entity, such as a public figure or organization,
timeline summarization (TLS) involves generating a timeline that summarizes the
key events about the entity. However, the TLS task is too underspecified, since
what is of interest to each reader may vary, and hence there is not a single
ideal or optimal timeline. In this paper, we introduce a novel task, called
Constrained Timeline Summarization (CTLS), where a timeline is generated in
which all events in the timeline meet some constraint. An example of a
constrained timeline concerns the legal battles of Tiger Woods, where only
events related to his legal problems are selected to appear in the timeline. We
collected a new human-verified dataset of constrained timelines involving 47
entities and 5 constraints per entity. We propose an approach that employs a
large language model (LLM) to summarize news articles according to a specified
constraint and cluster them to identify key events to include in a constrained
timeline. In addition, we propose a novel self-reflection method during summary
generation, demonstrating that this approach successfully leads to improved
performance.</description><identifier>DOI: 10.48550/arxiv.2412.17408</identifier><language>eng</language><subject>Computer Science - Computation and Language</subject><creationdate>2024-12</creationdate><rights>http://creativecommons.org/licenses/by-sa/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2412.17408$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2412.17408$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Qorib, Muhammad Reza</creatorcontrib><creatorcontrib>Hu, Qisheng</creatorcontrib><creatorcontrib>Ng, Hwee Tou</creatorcontrib><title>Just What You Desire: Constrained Timeline Summarization with Self-Reflection for Enhanced Relevance</title><description>Given news articles about an entity, such as a public figure or organization,
timeline summarization (TLS) involves generating a timeline that summarizes the
key events about the entity. However, the TLS task is too underspecified, since
what is of interest to each reader may vary, and hence there is not a single
ideal or optimal timeline. In this paper, we introduce a novel task, called
Constrained Timeline Summarization (CTLS), where a timeline is generated in
which all events in the timeline meet some constraint. An example of a
constrained timeline concerns the legal battles of Tiger Woods, where only
events related to his legal problems are selected to appear in the timeline. We
collected a new human-verified dataset of constrained timelines involving 47
entities and 5 constraints per entity. We propose an approach that employs a
large language model (LLM) to summarize news articles according to a specified
constraint and cluster them to identify key events to include in a constrained
timeline. In addition, we propose a novel self-reflection method during summary
generation, demonstrating that this approach successfully leads to improved
performance.</description><subject>Computer Science - Computation and Language</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNqFjk8LgkAUxPfSIaoP0Kn3BTQtJelqRnRUITrJom_xwbob62p_Pn0q3TvNMMwMP8bWvucGURh6W25e1Lu7wN-5_iHwojmrrl1r4VZzC3fdwQlbMniEWKvWGk4KK8ipQTk4yLqm4YY-3JJW8CRbQ4ZSOCkKieUUCm0gUTVX5TBMUWI_2iWbCS5bXP10wTbnJI8vzsRTPAwNv-9i5Comrv3_xhd6qEPw</recordid><startdate>20241223</startdate><enddate>20241223</enddate><creator>Qorib, Muhammad Reza</creator><creator>Hu, Qisheng</creator><creator>Ng, Hwee Tou</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20241223</creationdate><title>Just What You Desire: Constrained Timeline Summarization with Self-Reflection for Enhanced Relevance</title><author>Qorib, Muhammad Reza ; Hu, Qisheng ; Ng, Hwee Tou</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-arxiv_primary_2412_174083</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Computer Science - Computation and Language</topic><toplevel>online_resources</toplevel><creatorcontrib>Qorib, Muhammad Reza</creatorcontrib><creatorcontrib>Hu, Qisheng</creatorcontrib><creatorcontrib>Ng, Hwee Tou</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Qorib, Muhammad Reza</au><au>Hu, Qisheng</au><au>Ng, Hwee Tou</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Just What You Desire: Constrained Timeline Summarization with Self-Reflection for Enhanced Relevance</atitle><date>2024-12-23</date><risdate>2024</risdate><abstract>Given news articles about an entity, such as a public figure or organization,
timeline summarization (TLS) involves generating a timeline that summarizes the
key events about the entity. However, the TLS task is too underspecified, since
what is of interest to each reader may vary, and hence there is not a single
ideal or optimal timeline. In this paper, we introduce a novel task, called
Constrained Timeline Summarization (CTLS), where a timeline is generated in
which all events in the timeline meet some constraint. An example of a
constrained timeline concerns the legal battles of Tiger Woods, where only
events related to his legal problems are selected to appear in the timeline. We
collected a new human-verified dataset of constrained timelines involving 47
entities and 5 constraints per entity. We propose an approach that employs a
large language model (LLM) to summarize news articles according to a specified
constraint and cluster them to identify key events to include in a constrained
timeline. In addition, we propose a novel self-reflection method during summary
generation, demonstrating that this approach successfully leads to improved
performance.</abstract><doi>10.48550/arxiv.2412.17408</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | DOI: 10.48550/arxiv.2412.17408 |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_arxiv_primary_2412_17408 |
| source | arXiv.org |
| subjects | Computer Science - Computation and Language |
| title | Just What You Desire: Constrained Timeline Summarization with Self-Reflection for Enhanced Relevance |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T22%3A48%3A49IST&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=Just%20What%20You%20Desire:%20Constrained%20Timeline%20Summarization%20with%20Self-Reflection%20for%20Enhanced%20Relevance&rft.au=Qorib,%20Muhammad%20Reza&rft.date=2024-12-23&rft_id=info:doi/10.48550/arxiv.2412.17408&rft_dat=%3Carxiv_GOX%3E2412_17408%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 |