Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Bias e limiti","local":"bias-e-limiti","sections":[],"depth":1}"> | |
| <link href="/docs/course/pr_1069/it/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/it/_app/immutable/entry/start.693d748d.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/it/_app/immutable/chunks/scheduler.37c15a92.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/it/_app/immutable/chunks/singletons.60b4c7a2.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/it/_app/immutable/chunks/index.18351ede.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/it/_app/immutable/chunks/paths.43b6516c.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/it/_app/immutable/entry/app.e9cfd099.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/it/_app/immutable/chunks/index.2bf4358c.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/it/_app/immutable/nodes/0.bb8a536c.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/it/_app/immutable/chunks/each.e59479a4.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/it/_app/immutable/nodes/11.d7cb8a66.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/it/_app/immutable/chunks/CodeBlock.4e987730.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/it/_app/immutable/chunks/CourseFloatingBanner.9ff4c771.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/it/_app/immutable/chunks/DocNotebookDropdown.efc1fb7c.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/it/_app/immutable/chunks/getInferenceSnippets.24b50994.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Bias e limiti","local":"bias-e-limiti","sections":[],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="bias-e-limiti" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#bias-e-limiti"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Bias e limiti</span></h1> <div class="flex space-x-1 absolute z-10 right-0 top-0"><a href="https://discuss.huggingface.co/t/chapter-1-questions" target="_blank"><img alt="Ask a Question" class="!m-0" src="https://img.shields.io/badge/Ask%20a%20question-ffcb4c.svg?logo=data:image/svg+xml;base64,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"></a> <a href="https://colab.research.google.com/github/huggingface/notebooks/blob/master/course/it/chapter1/section8.ipynb" target="_blank"><img alt="Open In Colab" class="!m-0" src="https://colab.research.google.com/assets/colab-badge.svg"></a> <a href="https://studiolab.sagemaker.aws/import/github/huggingface/notebooks/blob/master/course/it/chapter1/section8.ipynb" target="_blank"><img alt="Open In Studio Lab" class="!m-0" src="https://studiolab.sagemaker.aws/studiolab.svg"></a></div> <p data-svelte-h="svelte-fwj8uu">Se intendi utilizzare un modello pre-addestrato o una versione affinata in produzione, sii consapevole che i modelli sono degli strumenti potenti, ma hanno dei limiti. Il più grande limite è che, per permettere un pre-addestramento su una quantità importante di dati, i ricercatori spesso includono tutti i contenuti ai quali riescono ad accedere, prendendo nel contempo il meglio e il peggio di ciò che Intenet offre.</p> <p data-svelte-h="svelte-algpv3">Per vederne una rappresentazione rapida, torniamo all’esempio della pipeline <code>fill-mask</code> con il modello BERT:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> pipeline | |
| unmasker = pipeline(<span class="hljs-string">"fill-mask"</span>, model=<span class="hljs-string">"bert-base-uncased"</span>) | |
| result = unmasker(<span class="hljs-string">"This man works as a [MASK]."</span>) | |
| <span class="hljs-built_in">print</span>([r[<span class="hljs-string">"token_str"</span>] <span class="hljs-keyword">for</span> r <span class="hljs-keyword">in</span> result]) | |
| result = unmasker(<span class="hljs-string">"This woman works as a [MASK]."</span>) | |
| <span class="hljs-built_in">print</span>([r[<span class="hljs-string">"token_str"</span>] <span class="hljs-keyword">for</span> r <span class="hljs-keyword">in</span> result])<!-- HTML_TAG_END --></pre></div> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->[<span class="hljs-string">'lawyer'</span>, <span class="hljs-string">'carpenter'</span>, <span class="hljs-string">'doctor'</span>, <span class="hljs-string">'waiter'</span>, <span class="hljs-string">'mechanic'</span>] | |
| [<span class="hljs-string">'nurse'</span>, <span class="hljs-string">'waitress'</span>, <span class="hljs-string">'teacher'</span>, <span class="hljs-string">'maid'</span>, <span class="hljs-string">'prostitute'</span>]<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-16mavt8">Quando domandiamo al modello di trovare la parola mancante in queste due frasi, questo produce solo una risposta senza genere predeterminato (‘waiter/waitress’). Le altre parole si riferiscono a professioni che sono solitamente associate ad un genere specifico; inoltre, come potete vedere, ‘prostitute’ finisce tra le 5 associazioni più probabili che il modello predice per “woman” e “work”. Ciò succede nonostante BERT sia uno dei rari modelli Transformer che non sono costruiti recuperando dati di ogni sorta da internet, ma utilizzando dati apparentemente neutri (è addestrato sui dataset <a href="https://huggingface.co/datasets/wikipedia" rel="nofollow">English Wikipedia</a> e <a href="https://huggingface.co/datasets/bookcorpus" rel="nofollow">BookCorpus</a>).</p> <p data-svelte-h="svelte-fr28fs">Nell’utilizzare questi strumenti, è perciò necessario tenere a mente che il modello d’origine in corso di utilizzazione potrebbe facilmente generare contenuti sessisti, razzisti oppure omofobici. Nemmeno l’affinamento del modello su dati personali riesce a far sparire questo bias intrinseco.</p> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/course/blob/main/chapters/it/chapter1/8.mdx" target="_blank"><span data-svelte-h="svelte-1kd6by1"><</span> <span data-svelte-h="svelte-x0xyl0">></span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a> <p></p> | |
| <script> | |
| { | |
| __sveltekit_u8ez91 = { | |
| assets: "/docs/course/pr_1069/it", | |
| base: "/docs/course/pr_1069/it", | |
| env: {} | |
| }; | |
| const element = document.currentScript.parentElement; | |
| const data = [null,null]; | |
| Promise.all([ | |
| import("/docs/course/pr_1069/it/_app/immutable/entry/start.693d748d.js"), | |
| import("/docs/course/pr_1069/it/_app/immutable/entry/app.e9cfd099.js") | |
| ]).then(([kit, app]) => { | |
| kit.start(app, element, { | |
| node_ids: [0, 11], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 11.7 kB
- Xet hash:
- ff0dc779a279e4dfd008758e3220ec57e62eb3756fc709948c7f1d6fb967b356
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.