<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:atom="http://www.w3.org/2005/Atom"
	xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
		>
<channel>
	<title>Comments on: How to Run Text Summarization with TensorFlow</title>
	<atom:link href="http://pavel.surmenok.com/2016/10/15/how-to-run-text-summarization-with-tensorflow/feed/" rel="self" type="application/rss+xml" />
	<link>http://pavel.surmenok.com/2016/10/15/how-to-run-text-summarization-with-tensorflow/</link>
	<description></description>
	<lastBuildDate>Sat, 13 Apr 2019 17:14:00 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.5.1</generator>
	<item>
		<title>By: David Hansen</title>
		<link>http://pavel.surmenok.com/2016/10/15/how-to-run-text-summarization-with-tensorflow/#comment-163</link>
		<dc:creator>David Hansen</dc:creator>
		<pubDate>Wed, 30 May 2018 20:12:00 +0000</pubDate>
		<guid isPermaLink="false">http://pavel.surmenok.com/?p=213#comment-163</guid>
		<description><![CDATA[Hello, I&#039;m joining the discussion a year (maybe two) late. 

First things first--many thanks to Pavel for the blog--the clearest explanation I have read.

My question:
Summarizing the first two sentences of an article is a good step and like others in this post stream I wish to apply textsum beyond sentences to full article. Wondering if anyone has had a modicum of success in summarizing beyond two sentences. Also wondering if it feasible to treat each paragraph (first two sentences of each) in a larger article as separate &quot;articles&quot;  (round robin fashion) to generate summary. If this is possible it might open way to sum across many full length articles. 

Full disclosure: I am not well versed in writing or running code but manage to stumble through, so I may be blindly dreaming of solution that is not possible.]]></description>
		<content:encoded><![CDATA[<p>Hello, I&#8217;m joining the discussion a year (maybe two) late. </p>
<p>First things first&#8211;many thanks to Pavel for the blog&#8211;the clearest explanation I have read.</p>
<p>My question:<br />
Summarizing the first two sentences of an article is a good step and like others in this post stream I wish to apply textsum beyond sentences to full article. Wondering if anyone has had a modicum of success in summarizing beyond two sentences. Also wondering if it feasible to treat each paragraph (first two sentences of each) in a larger article as separate &#8220;articles&#8221;  (round robin fashion) to generate summary. If this is possible it might open way to sum across many full length articles. </p>
<p>Full disclosure: I am not well versed in writing or running code but manage to stumble through, so I may be blindly dreaming of solution that is not possible.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: TD</title>
		<link>http://pavel.surmenok.com/2016/10/15/how-to-run-text-summarization-with-tensorflow/#comment-159</link>
		<dc:creator>TD</dc:creator>
		<pubDate>Tue, 30 Jan 2018 05:14:00 +0000</pubDate>
		<guid isPermaLink="false">http://pavel.surmenok.com/?p=213#comment-159</guid>
		<description><![CDATA[Excellent, Thanks Pavel. I will look for this link.]]></description>
		<content:encoded><![CDATA[<p>Excellent, Thanks Pavel. I will look for this link.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: surmenok</title>
		<link>http://pavel.surmenok.com/2016/10/15/how-to-run-text-summarization-with-tensorflow/#comment-157</link>
		<dc:creator>surmenok</dc:creator>
		<pubDate>Mon, 29 Jan 2018 22:52:00 +0000</pubDate>
		<guid isPermaLink="false">http://pavel.surmenok.com/?p=213#comment-157</guid>
		<description><![CDATA[Hi Tridib,
I haven&#039;t played with textsum for a while.
I think there could have been some improvement in text summarization algorithms since my post, and it makes sense to look for better models. There were links to Salesforce and IBM research in comments to this article.]]></description>
		<content:encoded><![CDATA[<p>Hi Tridib,<br />
I haven&#8217;t played with textsum for a while.<br />
I think there could have been some improvement in text summarization algorithms since my post, and it makes sense to look for better models. There were links to Salesforce and IBM research in comments to this article.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Tridib dutta</title>
		<link>http://pavel.surmenok.com/2016/10/15/how-to-run-text-summarization-with-tensorflow/#comment-156</link>
		<dc:creator>Tridib dutta</dc:creator>
		<pubDate>Mon, 29 Jan 2018 22:45:00 +0000</pubDate>
		<guid isPermaLink="false">http://pavel.surmenok.com/?p=213#comment-156</guid>
		<description><![CDATA[Hi Pavel, 
Nice post. I am also trying to use textsum in my project. But so far facing lot of issues. I am just wondering whether you have further played around with it. Eventually I would like to use it once I get over the issues I am facing. Thanks]]></description>
		<content:encoded><![CDATA[<p>Hi Pavel,<br />
Nice post. I am also trying to use textsum in my project. But so far facing lot of issues. I am just wondering whether you have further played around with it. Eventually I would like to use it once I get over the issues I am facing. Thanks</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: surmenok</title>
		<link>http://pavel.surmenok.com/2016/10/15/how-to-run-text-summarization-with-tensorflow/#comment-146</link>
		<dc:creator>surmenok</dc:creator>
		<pubDate>Sun, 10 Dec 2017 21:27:00 +0000</pubDate>
		<guid isPermaLink="false">http://pavel.surmenok.com/?p=213#comment-146</guid>
		<description><![CDATA[No, I haven&#039;t worked with that model and haven&#039;t seen the code for it.]]></description>
		<content:encoded><![CDATA[<p>No, I haven&#8217;t worked with that model and haven&#8217;t seen the code for it.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: TRIDIB DUTTA</title>
		<link>http://pavel.surmenok.com/2016/10/15/how-to-run-text-summarization-with-tensorflow/#comment-145</link>
		<dc:creator>TRIDIB DUTTA</dc:creator>
		<pubDate>Fri, 01 Dec 2017 18:35:00 +0000</pubDate>
		<guid isPermaLink="false">http://pavel.surmenok.com/?p=213#comment-145</guid>
		<description><![CDATA[Thanks for the wonderful description above. I am wondering if you have worked with the salesforce model or do you know of any code at github. Thanks once again.]]></description>
		<content:encoded><![CDATA[<p>Thanks for the wonderful description above. I am wondering if you have worked with the salesforce model or do you know of any code at github. Thanks once again.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Leena Shekhar Singh</title>
		<link>http://pavel.surmenok.com/2016/10/15/how-to-run-text-summarization-with-tensorflow/#comment-144</link>
		<dc:creator>Leena Shekhar Singh</dc:creator>
		<pubDate>Tue, 21 Nov 2017 20:47:00 +0000</pubDate>
		<guid isPermaLink="false">http://pavel.surmenok.com/?p=213#comment-144</guid>
		<description><![CDATA[Thank you so much for the article. Iam wondering if any of you guys have a pre-trained model for this? I am specifically looking for a model trained on CNN/Daily mail dataset. It would be a great help as I cannot train a huge model like this currently given the resources I have.]]></description>
		<content:encoded><![CDATA[<p>Thank you so much for the article. Iam wondering if any of you guys have a pre-trained model for this? I am specifically looking for a model trained on CNN/Daily mail dataset. It would be a great help as I cannot train a huge model like this currently given the resources I have.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Максим Мирошник</title>
		<link>http://pavel.surmenok.com/2016/10/15/how-to-run-text-summarization-with-tensorflow/#comment-140</link>
		<dc:creator>Максим Мирошник</dc:creator>
		<pubDate>Fri, 10 Nov 2017 10:30:00 +0000</pubDate>
		<guid isPermaLink="false">http://pavel.surmenok.com/?p=213#comment-140</guid>
		<description><![CDATA[Это хорошее вступление к обработке BigData]]></description>
		<content:encoded><![CDATA[<p>Это хорошее вступление к обработке BigData</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: surmenok</title>
		<link>http://pavel.surmenok.com/2016/10/15/how-to-run-text-summarization-with-tensorflow/#comment-134</link>
		<dc:creator>surmenok</dc:creator>
		<pubDate>Thu, 06 Jul 2017 00:44:00 +0000</pubDate>
		<guid isPermaLink="false">http://pavel.surmenok.com/?p=213#comment-134</guid>
		<description><![CDATA[Improving accuracy is definitely valuable to work on. Check out this work by Salesforce: https://www.salesforce.com/products/einstein/ai-research/tl-dr-reinforced-model-abstractive-summarization/
It&#039;s the best abstractive summarization model I&#039;ve seen so far.]]></description>
		<content:encoded><![CDATA[<p>Improving accuracy is definitely valuable to work on. Check out this work by Salesforce: <a href="https://www.salesforce.com/products/einstein/ai-research/tl-dr-reinforced-model-abstractive-summarization/" rel="nofollow">https://www.salesforce.com/products/einstein/ai-research/tl-dr-reinforced-model-abstractive-summarization/</a><br />
It&#8217;s the best abstractive summarization model I&#8217;ve seen so far.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Sasanka Kudagoda</title>
		<link>http://pavel.surmenok.com/2016/10/15/how-to-run-text-summarization-with-tensorflow/#comment-133</link>
		<dc:creator>Sasanka Kudagoda</dc:creator>
		<pubDate>Sun, 02 Jul 2017 06:28:00 +0000</pubDate>
		<guid isPermaLink="false">http://pavel.surmenok.com/?p=213#comment-133</guid>
		<description><![CDATA[Hi Pavel Surmenok, I was planing to do text summarization related project for my final year, Could you please point out some areas which i can improve, any new additions or accuracy or anything that i could work out.]]></description>
		<content:encoded><![CDATA[<p>Hi Pavel Surmenok, I was planing to do text summarization related project for my final year, Could you please point out some areas which i can improve, any new additions or accuracy or anything that i could work out.</p>
]]></content:encoded>
	</item>
</channel>
</rss>
