{"version":"1.0","provider_name":"Salesforce","provider_url":"https:\/\/www.salesforce.com\/blog","author_name":"Samson Tan","author_url":"https:\/\/www.salesforce.com\/blog\/author\/samson-tan\/","title":"Code-Mixing : Multilingual Adversaries for Multilingual Models | Salesforce AI Research","type":"rich","width":600,"height":338,"html":"<blockquote class=\"wp-embedded-content\" data-secret=\"HQbkUQXTix\"><a href=\"https:\/\/www.salesforce.com\/blog\/code-mixing\/\">Code-Mixing on Sesame Street: Multilingual Adversaries for Multilingual Models<\/a><\/blockquote><iframe sandbox=\"allow-scripts\" security=\"restricted\" src=\"https:\/\/www.salesforce.com\/blog\/code-mixing\/embed\/#?secret=HQbkUQXTix\" width=\"600\" height=\"338\" title=\"&#8220;Code-Mixing on Sesame Street: Multilingual Adversaries for Multilingual Models&#8221; &#8212; Salesforce\" data-secret=\"HQbkUQXTix\" frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\" class=\"wp-embedded-content\"><\/iframe><script>\n\/*! This file is auto-generated *\/\n!function(d,l){\"use strict\";l.querySelector&&d.addEventListener&&\"undefined\"!=typeof URL&&(d.wp=d.wp||{},d.wp.receiveEmbedMessage||(d.wp.receiveEmbedMessage=function(e){var t=e.data;if((t||t.secret||t.message||t.value)&&!\/[^a-zA-Z0-9]\/.test(t.secret)){for(var s,r,n,a=l.querySelectorAll('iframe[data-secret=\"'+t.secret+'\"]'),o=l.querySelectorAll('blockquote[data-secret=\"'+t.secret+'\"]'),c=new RegExp(\"^https?:$\",\"i\"),i=0;i<o.length;i++)o[i].style.display=\"none\";for(i=0;i<a.length;i++)s=a[i],e.source===s.contentWindow&&(s.removeAttribute(\"style\"),\"height\"===t.message?(1e3<(r=parseInt(t.value,10))?r=1e3:~~r<200&&(r=200),s.height=r):\"link\"===t.message&&(r=new URL(s.getAttribute(\"src\")),n=new URL(t.value),c.test(n.protocol))&&n.host===r.host&&l.activeElement===s&&(d.top.location.href=t.value))}},d.addEventListener(\"message\",d.wp.receiveEmbedMessage,!1),l.addEventListener(\"DOMContentLoaded\",function(){for(var e,t,s=l.querySelectorAll(\"iframe.wp-embedded-content\"),r=0;r<s.length;r++)(t=(e=s[r]).getAttribute(\"data-secret\"))||(t=Math.random().toString(36).substring(2,12),e.src+=\"#?secret=\"+t,e.setAttribute(\"data-secret\",t)),e.contentWindow.postMessage({message:\"ready\",secret:t},\"*\")},!1)))}(window,document);\n\/\/# sourceURL=https:\/\/wp-bn.salesforce.com\/blog\/wp-includes\/js\/wp-embed.min.js\n<\/script>\n","description":"Speakers in multilingual communities often code-mix (blending multiple languages in each sentence), and NLP systems need to perform reliably on code-mixed input to allow such communities to fully express themselves. However, most cross-lingual datasets are unable to test for code-mixing. To address this limitation, we created 2 highly effective multilingual adversarial attacks that push the ability of state-of-the-art NLP models to handle code-mixed input.","thumbnail_url":"https:\/\/lh4.googleusercontent.com\/Lw7nrZVAn83Y8kSLScPSo8qwVfzOSCoA3iHhymKx529bNPAPNoDevzljQlU_sEd_kv4rlg6NH0lTXn-51ZmGdH6-4qeEnY4edg9Yj3Aa-SUv46_P2DvwWISddXb8vUSF18s-4Lg_"}