Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Ask HN: How to use Machine Learning to extract facts from the text?

news.ycombinator.com

Post reply on HN
Print view View original

11–20 of 23 posts

Re: Ask HN: How to use Machine Learning to extract facts from the text?

#11

Post by gtani »

dartwing wrote: post #7
gtani wrote: post #5

Earlier quoted context omitted.

Depends on the corpus. If your problem fits a conLL task, you can read lots of papers about it. If you can build on an existing wikipedia entity/relation graph, dictionary, gazzette that's a big boost. For academic research papers, look at citations for your input stream then SVM tf-idf bigrams. If sentiment/quality analysis, that's another tack

Right now I'm hoping to extract entities and relations between them to use as facts for relevant domain specific search and validation. Reading up the articles, YCombinator included: https://blog.ycombinator.com/how-to-get-into-natural-languag...

I think these PIs at UIUC communicate clearly about all the processes necessary (Han wrote a good text on data mining, but probably outdated from 2011):

http://xren7.web.engr.illinois.edu/www17-StructNet-part1.pdf

http://xren7.web.engr.illinois.edu/cikm16-profile.pdf

Also solr/lucene/elastic indexes are good tools for filtering your inputs and deciding what the unit doc will be (sentence, paragraph, numbered section of research paper etc

Re: Ask HN: How to use Machine Learning to extract facts from the text?

#12

Post by grizzles »

Facts are simply assertions that have met some burden of proof. Determining that threshold is a subjective exercise, not an objective one. I know you want an algorithm to do this, but there is no sentient algorithm smart enough to do this. So, from an epistemological perspective, you are basically asking - what are the facts as determined by someone else?

The tragedy of subjectivity is, for most people, some random ranting into a youtube video for 15 minutes about eg. Hillary Clinton constitutes "evidence" sufficient to determine fact.

Re: Ask HN: How to use Machine Learning to extract facts from the text?

#13

Post by dartwing »

gtani wrote: post #11
dartwing wrote: post #7

Earlier quoted context omitted.

Right now I'm hoping to extract entities and relations between them to use as facts for relevant domain specific search and validation. Reading up the articles, YCombinator included: https://blog.ycombinator.com/how-to-get-into-natural-languag...

I think these PIs at UIUC communicate clearly about all the processes necessary (Han wrote a good text on data mining, but probably outdated from 2011): http://xren7.web.engr.illinois.edu/www17-StructNet-part1.pdf http://xren7.web.engr.illinois.edu/cikm16-profile.pdf Also solr/lucene/elastic indexes are good tools for filtering your inputs and deciding what the unit doc will be (sentence, paragraph, numbered section…

Thank you! Reading through the papers.

Re: Ask HN: How to use Machine Learning to extract facts from the text?

#14

Post by gauravnsit »

dartwing wrote: post #7
gtani wrote: post #5

Earlier quoted context omitted.

Depends on the corpus. If your problem fits a conLL task, you can read lots of papers about it. If you can build on an existing wikipedia entity/relation graph, dictionary, gazzette that's a big boost. For academic research papers, look at citations for your input stream then SVM tf-idf bigrams. If sentiment/quality analysis, that's another tack

Right now I'm hoping to extract entities and relations between them to use as facts for relevant domain specific search and validation. Reading up the articles, YCombinator included: https://blog.ycombinator.com/how-to-get-into-natural-languag...

I am also trying to find relations from textual entities, could you suggest any good paper or book to read and good python library to apply this.

Re: Ask HN: How to use Machine Learning to extract facts from the text?

#15

Post by lwhsiao »

DrNuke wrote: post #4

Looking for something similar for .pdf academic papers in my field but nothing really useful to automatise the extraction process exists, so the best path is still to extract data manually, homogenise data in a standard protocol, fed ML algos. Once a data protocol becomes a widespread standard and maybe a ISO or similar, there is a chance automated extraction will work at the finest level, as necessary for complex in…

On system for extracting information from PDFs is Fonduer[1], which is built on the Snorkel framework from Stanford. It may be worth checking out for your use case. Here's a blog post introducing it [2].

Disclosure: I worked on the project.

[1] https://arxiv.org/abs/1703.05028

[2] https://hazyresearch.github.io/snorkel/blog/fonduer.html

Re: Ask HN: How to use Machine Learning to extract facts from the text?

#16

Post by dartwing »

gauravnsit wrote: post #14
dartwing wrote: post #7

Earlier quoted context omitted.

Right now I'm hoping to extract entities and relations between them to use as facts for relevant domain specific search and validation. Reading up the articles, YCombinator included: https://blog.ycombinator.com/how-to-get-into-natural-languag...

I am also trying to find relations from textual entities, could you suggest any good paper or book to read and good python library to apply this.

I am starting to play around with: https://github.com/tensorflow/models/tree/master/syntaxnet

I expect that I will be able to match capabilities of this service and customize it to my needs: https://cloud.google.com/natural-language/

Re: Ask HN: How to use Machine Learning to extract facts from the text?

#17

Post by dartwing »

BjoernKW wrote: post #10

What exactly is a fact? There's no easy answer to that question, particularly with natural rather than formal languages. 'Facts' and statements depend on context. The meaning of a natural language statement usually is derived from these layers building on each other: - syntax (the structure of a sentence) - semantics (the isolated meaning of a sentence) - pragmatics (the meaning of a sentence in context) Anaphora (re…

Fact for me is structured information extracted from the document. My task is to extract what I can from the documents of the specific domain. I am fine to start with high precision and low recall, I think. Need to try in action and see if relevance of domain specific search and automatic validation can be improved with this approach.

Re: Ask HN: How to use Machine Learning to extract facts from the text?

#18

Post by BjoernKW »

dartwing wrote: post #17
BjoernKW wrote: post #10

What exactly is a fact? There's no easy answer to that question, particularly with natural rather than formal languages. 'Facts' and statements depend on context. The meaning of a natural language statement usually is derived from these layers building on each other: - syntax (the structure of a sentence) - semantics (the isolated meaning of a sentence) - pragmatics (the meaning of a sentence in context) Anaphora (re…

Fact for me is structured information extracted from the document. My task is to extract what I can from the documents of the specific domain. I am fine to start with high precision and low recall, I think. Need to try in action and see if relevance of domain specific search and automatic validation can be improved with this approach.

In that case the information extraction frameworks Apache UIMA and GATE might be helpful, too.

Re: Ask HN: How to use Machine Learning to extract facts from the text?

#19

Post by dartwing »

BjoernKW wrote: post #18
dartwing wrote: post #17

Earlier quoted context omitted.

Fact for me is structured information extracted from the document. My task is to extract what I can from the documents of the specific domain. I am fine to start with high precision and low recall, I think. Need to try in action and see if relevance of domain specific search and automatic validation can be improved with this approach.

In that case the information extraction frameworks Apache UIMA and GATE might be helpful, too.

Thank you! Will take a look.

Re: Ask HN: How to use Machine Learning to extract facts from the text?

#20

Post by dartwing »

grizzles wrote: post #12

Facts are simply assertions that have met some burden of proof. Determining that threshold is a subjective exercise, not an objective one. I know you want an algorithm to do this, but there is no sentient algorithm smart enough to do this. So, from an epistemological perspective, you are basically asking - what are the facts as determined by someone else? The tragedy of subjectivity is, for most people, some random r…

I define facts as structured piece of the information, which I need to extract for specific domain area automatically. I do hope extraction to work automatically in order for the project to make sense.

Eventually it will be measured for precision and recall using human judgement. The quality of that judgement would impact greatly on improvements and sustainability of the algorithm overall.

Post reply on HN