{"version":"1.0","provider_name":"Microsoft Research","provider_url":"https:\/\/www.microsoft.com\/en-us\/research","author_name":"Akiko Eriguchi","author_url":"https:\/\/www.microsoft.com\/en-us\/research\/people\/akikoe\/","title":"Neural Text Generation with Artificial Negative Examples to Address Repeating and Dropping Errors - Microsoft Research","type":"rich","width":600,"height":338,"html":"<blockquote class=\"wp-embedded-content\" data-secret=\"XCzNiIO3ki\"><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/neural-text-generation-with-artificial-negative-examples-to-address-repeating-and-dropping-errors\/\">Neural Text Generation with Artificial Negative Examples to Address Repeating and Dropping Errors<\/a><\/blockquote><iframe sandbox=\"allow-scripts\" security=\"restricted\" src=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/neural-text-generation-with-artificial-negative-examples-to-address-repeating-and-dropping-errors\/embed\/#?secret=XCzNiIO3ki\" width=\"600\" height=\"338\" title=\"&#8220;Neural Text Generation with Artificial Negative Examples to Address Repeating and Dropping Errors&#8221; &#8212; Microsoft Research\" data-secret=\"XCzNiIO3ki\" frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\" class=\"wp-embedded-content\"><\/iframe><script type=\"text\/javascript\">\n\/* <![CDATA[ *\/\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\/* ]]> *\/\n<\/script>\n","description":"Neural text generation models that are conditioned on a given input (e.g., machine translation and image captioning) are typically trained through maximum likelihood estimation of the target text. However, models trained in this manner often suffer from various types of errors when making subsequent inferences. In this study, we propose suppressing an arbitrary type of [&hellip;]"}