Просмотр исходного текста страницы Устойчивость к шуму в задаче извлечения аспектов (Валентин Малых, ISPRASOPEN-2018)

;{{SpeakerInfo}}: {{Speaker|Валентин Малых}}
<blockquote>
Aspect extraction from user reviews is one of the sources to make dialog systems, which are on the rise now. 
A typical user of a conversation system has no time to check the spelling or grammar in his or her utterances. Due to that user utterances contain typos and spelling errors, so the noise robustness should be considered as a significant feature of an aspect extraction model. 

We analyze noise-robustness of state-of-the-art Attention-Based Aspect Extraction technique and propose the extensions for this model, which lead to more robust behaviour in presence of typos. Experimental results demonstrate how suitable each of the complements to the model that uses the data containing typos.
</blockquote>

{{VideoSection}}
{{vimeoembed|298786268|800|450}}
{{youtubelink|mtoK9yh9W-0}}
{{letscomment}}

{{SlidesSection}}
[[File:Устойчивость к шуму в задаче извлечения аспектов (Тарас Хахулин, ISPRASOPEN-2018).pdf|left|page=-|300px]]

{{----}}
[[File:{{#setmainimage:Устойчивость к шуму в задаче извлечения аспектов (Тарас Хахулин, ISPRASOPEN-2018)!.jpg}}|center|640px]]
{{LinksSection}}
<!-- * [ Talks page on site] -->
<!-- <blockquote>[©]</blockquote> -->

{{fblink|2246672842252391}}                                          
{{vklink|1391}}                                          
<references/>





<!-- topub -->

[[Категория:ISPRASOPEN-2018]]
[[Категория:Natural Language Processing]]
[[Категория:Machine Learning]]
{{stats|disqus_comments=0|refresh_time=2020-01-22T17:52:22.124249|vimeo_plays=6|youtube_comments=0|youtube_plays=4}}