Partial Knowledge In Embeddings
Representing domain knowledge is crucial for any task. There has been a wide range of techniques developed to represent this knowledge, from older logic based approaches to the more recent deep learning based techniques (i.e. embeddings). In this paper, we discuss some of these methods, focusing on...
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| 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 | Guha, Ramanathan V |
| description | Representing domain knowledge is crucial for any task. There has been a wide
range of techniques developed to represent this knowledge, from older logic
based approaches to the more recent deep learning based techniques (i.e.
embeddings). In this paper, we discuss some of these methods, focusing on the
representational expressiveness tradeoffs that are often made. In particular,
we focus on the the ability of various techniques to encode `partial knowledge'
- a key component of successful knowledge systems. We introduce and describe
the concepts of `ensembles of embeddings' and `aggregate embeddings' and
demonstrate how they allow for partial knowledge. |
| doi_str_mv | 10.48550/arxiv.1710.10538 |
| format | Article |
| fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1710_10538</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1710_10538</sourcerecordid><originalsourceid>FETCH-LOGICAL-a678-ac5553d9f6bee27b0fda2ff196400de775848912dc66e6128e5743529f6a72233</originalsourceid><addsrcrecordid>eNotzksLgkAUBeDZtAjrB7TSP2DNwzszLiN6SEEt2su1uSOCWlj0-PfZY3XgwDl8jE0EnyYWgM-we1b3qTB9ITgoO2ThAbtbhXW0bc-PmlxJUdZGy6Yg56q2vI7YwGN9pfE_A3ZcLY-LTbzbr7PFfBejNjbGEwAol3pdEElTcO9Qei9SnXDuyBiwiU2FdCetSQtpCUyiQPYDNFIqFbDwd_sV5peuarB75R9p_pWqNx5KNp0</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Partial Knowledge In Embeddings</title><source>arXiv.org</source><creator>Guha, Ramanathan V</creator><creatorcontrib>Guha, Ramanathan V</creatorcontrib><description>Representing domain knowledge is crucial for any task. There has been a wide
range of techniques developed to represent this knowledge, from older logic
based approaches to the more recent deep learning based techniques (i.e.
embeddings). In this paper, we discuss some of these methods, focusing on the
representational expressiveness tradeoffs that are often made. In particular,
we focus on the the ability of various techniques to encode `partial knowledge'
- a key component of successful knowledge systems. We introduce and describe
the concepts of `ensembles of embeddings' and `aggregate embeddings' and
demonstrate how they allow for partial knowledge.</description><identifier>DOI: 10.48550/arxiv.1710.10538</identifier><language>eng</language><subject>Computer Science - Artificial Intelligence</subject><creationdate>2017-10</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</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/1710.10538$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1710.10538$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Guha, Ramanathan V</creatorcontrib><title>Partial Knowledge In Embeddings</title><description>Representing domain knowledge is crucial for any task. There has been a wide
range of techniques developed to represent this knowledge, from older logic
based approaches to the more recent deep learning based techniques (i.e.
embeddings). In this paper, we discuss some of these methods, focusing on the
representational expressiveness tradeoffs that are often made. In particular,
we focus on the the ability of various techniques to encode `partial knowledge'
- a key component of successful knowledge systems. We introduce and describe
the concepts of `ensembles of embeddings' and `aggregate embeddings' and
demonstrate how they allow for partial knowledge.</description><subject>Computer Science - Artificial Intelligence</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2017</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotzksLgkAUBeDZtAjrB7TSP2DNwzszLiN6SEEt2su1uSOCWlj0-PfZY3XgwDl8jE0EnyYWgM-we1b3qTB9ITgoO2ThAbtbhXW0bc-PmlxJUdZGy6Yg56q2vI7YwGN9pfE_A3ZcLY-LTbzbr7PFfBejNjbGEwAol3pdEElTcO9Qei9SnXDuyBiwiU2FdCetSQtpCUyiQPYDNFIqFbDwd_sV5peuarB75R9p_pWqNx5KNp0</recordid><startdate>20171028</startdate><enddate>20171028</enddate><creator>Guha, Ramanathan V</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20171028</creationdate><title>Partial Knowledge In Embeddings</title><author>Guha, Ramanathan V</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a678-ac5553d9f6bee27b0fda2ff196400de775848912dc66e6128e5743529f6a72233</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2017</creationdate><topic>Computer Science - Artificial Intelligence</topic><toplevel>online_resources</toplevel><creatorcontrib>Guha, Ramanathan V</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Guha, Ramanathan V</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Partial Knowledge In Embeddings</atitle><date>2017-10-28</date><risdate>2017</risdate><abstract>Representing domain knowledge is crucial for any task. There has been a wide
range of techniques developed to represent this knowledge, from older logic
based approaches to the more recent deep learning based techniques (i.e.
embeddings). In this paper, we discuss some of these methods, focusing on the
representational expressiveness tradeoffs that are often made. In particular,
we focus on the the ability of various techniques to encode `partial knowledge'
- a key component of successful knowledge systems. We introduce and describe
the concepts of `ensembles of embeddings' and `aggregate embeddings' and
demonstrate how they allow for partial knowledge.</abstract><doi>10.48550/arxiv.1710.10538</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | DOI: 10.48550/arxiv.1710.10538 |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_arxiv_primary_1710_10538 |
| source | arXiv.org |
| subjects | Computer Science - Artificial Intelligence |
| title | Partial Knowledge In Embeddings |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T00%3A13%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=Partial%20Knowledge%20In%20Embeddings&rft.au=Guha,%20Ramanathan%20V&rft.date=2017-10-28&rft_id=info:doi/10.48550/arxiv.1710.10538&rft_dat=%3Carxiv_GOX%3E1710_10538%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 |