<?xml version="1.0"?>
<feed xmlns="http://www.w3.org/2005/Atom" xml:lang="it">
	<id>https://wiki.mindmaker.it/index.php?action=history&amp;feed=atom&amp;title=None</id>
	<title>None - Cronologia</title>
	<link rel="self" type="application/atom+xml" href="https://wiki.mindmaker.it/index.php?action=history&amp;feed=atom&amp;title=None"/>
	<link rel="alternate" type="text/html" href="https://wiki.mindmaker.it/index.php?title=None&amp;action=history"/>
	<updated>2026-05-01T17:06:35Z</updated>
	<subtitle>Cronologia della pagina su questo sito</subtitle>
	<generator>MediaWiki 1.41.0</generator>
	<entry>
		<id>https://wiki.mindmaker.it/index.php?title=None&amp;diff=3028&amp;oldid=prev</id>
		<title>Mindmakerbot il 10:20, 6 set 2024</title>
		<link rel="alternate" type="text/html" href="https://wiki.mindmaker.it/index.php?title=None&amp;diff=3028&amp;oldid=prev"/>
		<updated>2024-09-06T10:20:53Z</updated>

		<summary type="html">&lt;p&gt;&lt;/p&gt;
&lt;table style=&quot;background-color: #fff; color: #202122;&quot; data-mw=&quot;interface&quot;&gt;
				&lt;col class=&quot;diff-marker&quot; /&gt;
				&lt;col class=&quot;diff-content&quot; /&gt;
				&lt;col class=&quot;diff-marker&quot; /&gt;
				&lt;col class=&quot;diff-content&quot; /&gt;
				&lt;tr class=&quot;diff-title&quot; lang=&quot;it&quot;&gt;
				&lt;td colspan=&quot;2&quot; style=&quot;background-color: #fff; color: #202122; text-align: center;&quot;&gt;← Versione meno recente&lt;/td&gt;
				&lt;td colspan=&quot;2&quot; style=&quot;background-color: #fff; color: #202122; text-align: center;&quot;&gt;Versione delle 10:20, 6 set 2024&lt;/td&gt;
				&lt;/tr&gt;&lt;tr&gt;&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot; id=&quot;mw-diff-left-l7&quot;&gt;Riga 7:&lt;/td&gt;
&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot;&gt;Riga 7:&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;}}&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;}}&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;br&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;br&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;Questo articolo &lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;introduce &lt;/del&gt;un nuovo tipo di rappresentazione di parole contestualizzate che modella sia le caratteristiche complesse dell&#039;uso delle parole (ad esempio, sintassi e semantica), sia &lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;il modo in cui &lt;/del&gt;questi usi variano a seconda dei contesti linguistici (ovvero, per modellare la polisemia).&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;Questo articolo &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;presenta &lt;/ins&gt;un nuovo tipo di rappresentazione di parole contestualizzate &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;profonde &lt;/ins&gt;che modella sia &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;(1) &lt;/ins&gt;le caratteristiche complesse dell&#039;uso delle parole (ad esempio, sintassi e semantica), sia &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;(2) come &lt;/ins&gt;questi usi variano a seconda dei contesti linguistici (ovvero, per modellare la polisemia). I vettori di parole sono funzioni apprese degli stati interni di un modello linguistico bidirezionale profondo (biLM), &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;che è &lt;/ins&gt;pre-addestrato su un ampio corpus di testo. &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;Gli autori dimostrano che queste rappresentazioni possono essere facilmente aggiunte ai modelli esistenti e migliorare significativamente lo stato dell&#039;arte in sei sfidanti problemi &lt;/ins&gt;di &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;PNL, tra cui il question answering, l&#039;implicazione testuale &lt;/ins&gt;e &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;l&#039;analisi del sentiment. Presentano inoltre un&#039;analisi che mostra che esporre gli interni profondi della rete pre-addestrata è fondamentale, consentendo &lt;/ins&gt;ai &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;modelli a valle di combinare diversi tipi di segnali di semi-supervisione&lt;/ins&gt;.&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt; &lt;/div&gt;&lt;/td&gt;&lt;td colspan=&quot;2&quot; class=&quot;diff-side-added&quot;&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;I vettori di parole sono funzioni apprese degli stati interni di un modello linguistico bidirezionale profondo (biLM), pre-addestrato su un ampio corpus di testo. &lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;Questo approccio consente &lt;/del&gt;di &lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;ottenere rappresentazioni più ricche &lt;/del&gt;e &lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;informative rispetto &lt;/del&gt;ai &lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;tradizionali word embedding statici&lt;/del&gt;.&lt;/div&gt;&lt;/td&gt;&lt;td colspan=&quot;2&quot; class=&quot;diff-side-added&quot;&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt; &lt;/div&gt;&lt;/td&gt;&lt;td colspan=&quot;2&quot; class=&quot;diff-side-added&quot;&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;[[Categoria:Pubblicazione]]&lt;/del&gt;&lt;/div&gt;&lt;/td&gt;&lt;td colspan=&quot;2&quot; class=&quot;diff-side-added&quot;&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;br&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;br&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;{{#seo:&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;{{#seo:&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;             |title=Deep Contextualized Word Representations&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;             |title=Deep Contextualized Word Representations&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;             |title_mode=append&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;             |title_mode=append&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;             |keywords=&lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;rappresentazioni di &lt;/del&gt;parole, &lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;word embedding, modelli linguistici&lt;/del&gt;, elaborazione del linguaggio naturale&lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;, apprendimento profondo, reti neurali&lt;/del&gt;, semantica, sintassi, polisemia&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;             |keywords=&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;rappresentazione delle &lt;/ins&gt;parole, &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;apprendimento profondo&lt;/ins&gt;, elaborazione del linguaggio naturale, semantica, sintassi, polisemia&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;, modelli linguistici, word embedding&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;             |description=Questa pubblicazione presenta un nuovo tipo di rappresentazione di parole contestualizzate, &lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;modellando &lt;/del&gt;sia le caratteristiche complesse dell&#039;uso delle parole che le loro variazioni in base al contesto &lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;linguistico&lt;/del&gt;. &lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;Questo approccio&lt;/del&gt;, &lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;basato su un modello linguistico bidirezionale profondo, genera rappresentazioni più ricche rispetto ai tradizionali word embedding statici&lt;/del&gt;.&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;             |description=Questa pubblicazione presenta un nuovo tipo di rappresentazione di parole contestualizzate, &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;che modella &lt;/ins&gt;sia le caratteristiche complesse dell&#039;uso delle parole che le loro variazioni in base al contesto. &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;Gli autori dimostrano che queste rappresentazioni migliorano significativamente lo stato dell&#039;arte in diversi problemi di PNL&lt;/ins&gt;, &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;come il question answering e l&#039;analisi del sentiment&lt;/ins&gt;.&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;              &lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;              &lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;             }}&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot;&gt;&lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;             }}&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;/table&gt;</summary>
		<author><name>Mindmakerbot</name></author>
	</entry>
	<entry>
		<id>https://wiki.mindmaker.it/index.php?title=None&amp;diff=3027&amp;oldid=prev</id>
		<title>Mindmakerbot: Creata pagina con &quot;{{template pubblicazione  |data=2018  |autori=Matthew E. Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, Luke Zettlemoyer  |URL=https://www.semanticscholar.org/paper/3febb2bed8865945e7fddc99efd791887bb7e14f  |topic=Word embedding  |citazioni=11008  }}    Questo articolo introduce un nuovo tipo di rappresentazione di parole contestualizzate che modella sia le caratteristiche complesse dell&#039;uso delle parole (ad esempio, sintassi e semantica)...&quot;</title>
		<link rel="alternate" type="text/html" href="https://wiki.mindmaker.it/index.php?title=None&amp;diff=3027&amp;oldid=prev"/>
		<updated>2024-09-06T10:18:17Z</updated>

		<summary type="html">&lt;p&gt;Creata pagina con &amp;quot;{{template pubblicazione  |data=2018  |autori=Matthew E. Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, Luke Zettlemoyer  |URL=https://www.semanticscholar.org/paper/3febb2bed8865945e7fddc99efd791887bb7e14f  |topic=Word embedding  |citazioni=11008  }}    Questo articolo introduce un nuovo tipo di rappresentazione di parole contestualizzate che modella sia le caratteristiche complesse dell&amp;#039;uso delle parole (ad esempio, sintassi e semantica)...&amp;quot;&lt;/p&gt;
&lt;p&gt;&lt;b&gt;Nuova pagina&lt;/b&gt;&lt;/p&gt;&lt;div&gt;{{template pubblicazione&lt;br /&gt;
|data=2018&lt;br /&gt;
|autori=Matthew E. Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, Luke Zettlemoyer&lt;br /&gt;
|URL=https://www.semanticscholar.org/paper/3febb2bed8865945e7fddc99efd791887bb7e14f&lt;br /&gt;
|topic=Word embedding&lt;br /&gt;
|citazioni=11008&lt;br /&gt;
}}&lt;br /&gt;
&lt;br /&gt;
Questo articolo introduce un nuovo tipo di rappresentazione di parole contestualizzate che modella sia le caratteristiche complesse dell&amp;#039;uso delle parole (ad esempio, sintassi e semantica), sia il modo in cui questi usi variano a seconda dei contesti linguistici (ovvero, per modellare la polisemia).&lt;br /&gt;
&lt;br /&gt;
I vettori di parole sono funzioni apprese degli stati interni di un modello linguistico bidirezionale profondo (biLM), pre-addestrato su un ampio corpus di testo. Questo approccio consente di ottenere rappresentazioni più ricche e informative rispetto ai tradizionali word embedding statici.&lt;br /&gt;
&lt;br /&gt;
[[Categoria:Pubblicazione]]&lt;br /&gt;
&lt;br /&gt;
{{#seo:&lt;br /&gt;
            |title=Deep Contextualized Word Representations&lt;br /&gt;
            |title_mode=append&lt;br /&gt;
            |keywords=rappresentazioni di parole, word embedding, modelli linguistici, elaborazione del linguaggio naturale, apprendimento profondo, reti neurali, semantica, sintassi, polisemia&lt;br /&gt;
            |description=Questa pubblicazione presenta un nuovo tipo di rappresentazione di parole contestualizzate, modellando sia le caratteristiche complesse dell&amp;#039;uso delle parole che le loro variazioni in base al contesto linguistico. Questo approccio, basato su un modello linguistico bidirezionale profondo, genera rappresentazioni più ricche rispetto ai tradizionali word embedding statici.&lt;br /&gt;
            &lt;br /&gt;
            }}&lt;/div&gt;</summary>
		<author><name>Mindmakerbot</name></author>
	</entry>
</feed>