Cross-lingual Short-text Matching

Data Skeptic

Episode | Podcast

Date: Fri, 05 Apr 2019 13:42:53 +0000

<p class="p1"><span class="s1">Modern messaging technology has facilitated a trend towards highly compact, short messages send by users who can presume a great amount of context held between the communicating parties.<span class="Apple-converted-space"> </span> The rules of grammar may be discarded and often visible errors are a normal part of the conversation.</span></p> <p class="p1"><span class="s1">>>> Good mornink</span></p> <p class="p1"><span class="s1">>>> morning</span></p> <p class="p1"><span class="s1">Yet such short messages are also important for businesses whose users are unlikely to read a large block of text upon completing an order.<span class="Apple-converted-space"> </span> Similarly, a business might want to offer assistance and effective question and answering solutions in an automated and ideally multi-lingual way.<span class="Apple-converted-space"> </span> In this episode, we discuss techniques for designing solutions like that.</span></p> <p class="p2"> </p>