There are a few different tools you might want to look at: MITIEMIT's new tool supports basic relationship extraction. Included in the distribution are 21 English binary relation extraction models trained on a combination of Wikipedia and Freebase data. You can also train your own custom relation detectors. I ran the OpenIE 4.1 binary but got the following error: The US president Barack Obama gave speech to thousands of people on Tuesday. Exception in thread 'main' java.lang.NullPointerException at com.googlecode.clearnlp.tokenization.EnglishTokenizer.protectEmoticon s(EnglishTokenizer.java:335) at com.googlecode.clearnlp.tokenization.EnglishTokenizer.getTokenList(En glishTokenizer.java:109) at com.googlecode.clearnlp.tokenization.AbstractTokenizer.getTokens(Abst ractTokenizer.java:58) at edu.knowitall.tool.tokenize.ClearTokenizer.tokenize(ClearTokenizer.sc ala:22)–Dec 25 '14 at 19:29. The MIML-RE relation extractor could also be useful, if you're looking for one of the relations in the KBP relation set (see ).
Durutti Column Lyrics
Admittedly, this is a much bigger system that's more of a pain to set up than the 'relation' annotator in CoreNLP.Probably the easiest way to get started with this option, is to download (make sure to also download the models, as well as all of the dependencies). From there, there are a bunch of relatively low-barrier entry methods in SlotfillingTasks (e.g., getSlotsInSentence gets all relations for a given entity, or classifyRelation classifies the relation between two entities in a sentence). You might also want to take a look at. It performs Open Information Extraction, that is, you don't need to specify the type of relationships to extract. It automatically identifies and extracts all kinds of verb-mediated relationships between two nouns/nouns-phrases.It's based on simple rules over part-of-speech tags therefore its extremely fast, that is, compared to other systems which rely on syntactic parsing.The code is availableUPDATE: I've written in a blog post, how to use ReVerb PoS-patterns to extract relational triples from news articles.