SLATE: A Sequence Labeling Approach for Task Extraction from Free-form Inked Content
We present SLATE, a sequence labeling approach for extracting tasks from free-form content such as digitally handwritten (or "inked") notes on a virtual whiteboard. Our approach allows us to create a single, low-latency model to simultaneously perform sentence segmentation and classificati...
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 | Gandhi, Apurva Serrao, Ryan Fang, Biyi Antonius, Gilbert Hong, Jenna Nguyen, Tra My Yi, Sheng Nosakhare, Ehi Shaffer, Irene Srinivasan, Soundararajan Gupta, Vivek |
| description | We present SLATE, a sequence labeling approach for extracting tasks from
free-form content such as digitally handwritten (or "inked") notes on a virtual
whiteboard. Our approach allows us to create a single, low-latency model to
simultaneously perform sentence segmentation and classification of these
sentences into task/non-task sentences. SLATE greatly outperforms a baseline
two-model (sentence segmentation followed by classification model) approach,
achieving a task F1 score of 84.4%, a sentence segmentation (boundary
similarity) score of 88.4% and three times lower latency compared to the
baseline. Furthermore, we provide insights into tackling challenges of
performing NLP on the inking domain. We release both our code and dataset for
this novel task. |
| doi_str_mv | 10.48550/arxiv.2211.04454 |
| format | Article |
| fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2211_04454</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2211_04454</sourcerecordid><originalsourceid>FETCH-LOGICAL-a674-a8e8477a527cfcc59600f2dfb37ec72019a48654d1c0eb3aeb3207b01f3eec1e3</originalsourceid><addsrcrecordid>eNotz7FOwzAUBVAvDKjwAUy8H0iwHTtO2aIohUqRGOo9enGeIWrjBDeg8veU0uHqDle60mHsQfBUFVrzJ4yn4TuVUoiUK6XVLbO7prT1M5Swo88vCo6gwY4OQ3iHcp7jhO4D_BTB4nEP9WmJ6JZhCuDjNMImEiXndYRt2FMP1RQWCssdu_F4ONL9tVfMbmpbvSbN28u2KpsEc6MSLKhQxqCWxnnn9Drn3Mved5khZyQXa1RFrlUvHKcuw3MkNx0XPiNygrIVe_y_vbDaOQ4jxp_2j9deeNkviH5J_A</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>SLATE: A Sequence Labeling Approach for Task Extraction from Free-form Inked Content</title><source>arXiv.org</source><creator>Gandhi, Apurva ; Serrao, Ryan ; Fang, Biyi ; Antonius, Gilbert ; Hong, Jenna ; Nguyen, Tra My ; Yi, Sheng ; Nosakhare, Ehi ; Shaffer, Irene ; Srinivasan, Soundararajan ; Gupta, Vivek</creator><creatorcontrib>Gandhi, Apurva ; Serrao, Ryan ; Fang, Biyi ; Antonius, Gilbert ; Hong, Jenna ; Nguyen, Tra My ; Yi, Sheng ; Nosakhare, Ehi ; Shaffer, Irene ; Srinivasan, Soundararajan ; Gupta, Vivek</creatorcontrib><description>We present SLATE, a sequence labeling approach for extracting tasks from
free-form content such as digitally handwritten (or "inked") notes on a virtual
whiteboard. Our approach allows us to create a single, low-latency model to
simultaneously perform sentence segmentation and classification of these
sentences into task/non-task sentences. SLATE greatly outperforms a baseline
two-model (sentence segmentation followed by classification model) approach,
achieving a task F1 score of 84.4%, a sentence segmentation (boundary
similarity) score of 88.4% and three times lower latency compared to the
baseline. Furthermore, we provide insights into tackling challenges of
performing NLP on the inking domain. We release both our code and dataset for
this novel task.</description><identifier>DOI: 10.48550/arxiv.2211.04454</identifier><language>eng</language><subject>Computer Science - Computation and Language ; Computer Science - Learning</subject><creationdate>2022-11</creationdate><rights>http://creativecommons.org/licenses/by-nc-nd/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/2211.04454$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2211.04454$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Gandhi, Apurva</creatorcontrib><creatorcontrib>Serrao, Ryan</creatorcontrib><creatorcontrib>Fang, Biyi</creatorcontrib><creatorcontrib>Antonius, Gilbert</creatorcontrib><creatorcontrib>Hong, Jenna</creatorcontrib><creatorcontrib>Nguyen, Tra My</creatorcontrib><creatorcontrib>Yi, Sheng</creatorcontrib><creatorcontrib>Nosakhare, Ehi</creatorcontrib><creatorcontrib>Shaffer, Irene</creatorcontrib><creatorcontrib>Srinivasan, Soundararajan</creatorcontrib><creatorcontrib>Gupta, Vivek</creatorcontrib><title>SLATE: A Sequence Labeling Approach for Task Extraction from Free-form Inked Content</title><description>We present SLATE, a sequence labeling approach for extracting tasks from
free-form content such as digitally handwritten (or "inked") notes on a virtual
whiteboard. Our approach allows us to create a single, low-latency model to
simultaneously perform sentence segmentation and classification of these
sentences into task/non-task sentences. SLATE greatly outperforms a baseline
two-model (sentence segmentation followed by classification model) approach,
achieving a task F1 score of 84.4%, a sentence segmentation (boundary
similarity) score of 88.4% and three times lower latency compared to the
baseline. Furthermore, we provide insights into tackling challenges of
performing NLP on the inking domain. We release both our code and dataset for
this novel task.</description><subject>Computer Science - Computation and Language</subject><subject>Computer Science - Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz7FOwzAUBVAvDKjwAUy8H0iwHTtO2aIohUqRGOo9enGeIWrjBDeg8veU0uHqDle60mHsQfBUFVrzJ4yn4TuVUoiUK6XVLbO7prT1M5Swo88vCo6gwY4OQ3iHcp7jhO4D_BTB4nEP9WmJ6JZhCuDjNMImEiXndYRt2FMP1RQWCssdu_F4ONL9tVfMbmpbvSbN28u2KpsEc6MSLKhQxqCWxnnn9Drn3Mved5khZyQXa1RFrlUvHKcuw3MkNx0XPiNygrIVe_y_vbDaOQ4jxp_2j9deeNkviH5J_A</recordid><startdate>20221108</startdate><enddate>20221108</enddate><creator>Gandhi, Apurva</creator><creator>Serrao, Ryan</creator><creator>Fang, Biyi</creator><creator>Antonius, Gilbert</creator><creator>Hong, Jenna</creator><creator>Nguyen, Tra My</creator><creator>Yi, Sheng</creator><creator>Nosakhare, Ehi</creator><creator>Shaffer, Irene</creator><creator>Srinivasan, Soundararajan</creator><creator>Gupta, Vivek</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20221108</creationdate><title>SLATE: A Sequence Labeling Approach for Task Extraction from Free-form Inked Content</title><author>Gandhi, Apurva ; Serrao, Ryan ; Fang, Biyi ; Antonius, Gilbert ; Hong, Jenna ; Nguyen, Tra My ; Yi, Sheng ; Nosakhare, Ehi ; Shaffer, Irene ; Srinivasan, Soundararajan ; Gupta, Vivek</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a674-a8e8477a527cfcc59600f2dfb37ec72019a48654d1c0eb3aeb3207b01f3eec1e3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computer Science - Computation and Language</topic><topic>Computer Science - Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Gandhi, Apurva</creatorcontrib><creatorcontrib>Serrao, Ryan</creatorcontrib><creatorcontrib>Fang, Biyi</creatorcontrib><creatorcontrib>Antonius, Gilbert</creatorcontrib><creatorcontrib>Hong, Jenna</creatorcontrib><creatorcontrib>Nguyen, Tra My</creatorcontrib><creatorcontrib>Yi, Sheng</creatorcontrib><creatorcontrib>Nosakhare, Ehi</creatorcontrib><creatorcontrib>Shaffer, Irene</creatorcontrib><creatorcontrib>Srinivasan, Soundararajan</creatorcontrib><creatorcontrib>Gupta, Vivek</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Gandhi, Apurva</au><au>Serrao, Ryan</au><au>Fang, Biyi</au><au>Antonius, Gilbert</au><au>Hong, Jenna</au><au>Nguyen, Tra My</au><au>Yi, Sheng</au><au>Nosakhare, Ehi</au><au>Shaffer, Irene</au><au>Srinivasan, Soundararajan</au><au>Gupta, Vivek</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>SLATE: A Sequence Labeling Approach for Task Extraction from Free-form Inked Content</atitle><date>2022-11-08</date><risdate>2022</risdate><abstract>We present SLATE, a sequence labeling approach for extracting tasks from
free-form content such as digitally handwritten (or "inked") notes on a virtual
whiteboard. Our approach allows us to create a single, low-latency model to
simultaneously perform sentence segmentation and classification of these
sentences into task/non-task sentences. SLATE greatly outperforms a baseline
two-model (sentence segmentation followed by classification model) approach,
achieving a task F1 score of 84.4%, a sentence segmentation (boundary
similarity) score of 88.4% and three times lower latency compared to the
baseline. Furthermore, we provide insights into tackling challenges of
performing NLP on the inking domain. We release both our code and dataset for
this novel task.</abstract><doi>10.48550/arxiv.2211.04454</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | DOI: 10.48550/arxiv.2211.04454 |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_arxiv_primary_2211_04454 |
| source | arXiv.org |
| subjects | Computer Science - Computation and Language Computer Science - Learning |
| title | SLATE: A Sequence Labeling Approach for Task Extraction from Free-form Inked Content |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-02T17%3A21%3A09IST&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=SLATE:%20A%20Sequence%20Labeling%20Approach%20for%20Task%20Extraction%20from%20Free-form%20Inked%20Content&rft.au=Gandhi,%20Apurva&rft.date=2022-11-08&rft_id=info:doi/10.48550/arxiv.2211.04454&rft_dat=%3Carxiv_GOX%3E2211_04454%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 |