props
props copied to clipboard
PropS offers an output representation designed to explicitly and uniformly express much of the proposition structure which is implied from syntax.
This seems wrong in multiple places: ``` {'lf': {'comp': {'dobj': 'barks', 'pred': 'admired', 'subj': 'we'}, 'pred': 'thought', 'subj': ['they', 'dog']}, 'sentence': 'The dog they thought we admired barks .'} ```
Consider ```The dog they adopted barks```. We get: ``` {'lf': {'dobj': 'barks', 'pred': 'adopted', 'subj': ['dog', 'they']}, 'sentence': 'The dog they adopted barks .'} ``` arguably we want to distinguish...
From the sentence > The Telecom and Energy sectors continue to jockey for the top spot in the third quarter, gaining 7.7% and 7.3%, respectively. we are not able to...
The Stanford parser, like other parsers, makes errors. e.g. ``` Although the UK has long had an ambivalent attitude towards Europe, the hostility of the UK Independence Party towards the...
Consider: ``` The US President Barack Obama lives in Washington, D.C. ``` It would be nice if propS is able to discover that `US President` and `Barack Obama` are in...
Arguably, handling `wh` sentences (`who` / `what` / `when` / `where`) is out of scope for a project that aims to discover the propositional content of sentences. Hence this "issue"...
This example should make it clear: ``` 'sentence': 'An airline may decide to stop serving several airports because its on-time \ performance does not fit within the airlines revised -LRB-...
For knowledge representation and reasoning tasks, it is valuable to represent the information in a sentence in some kind of nested attribute value form. I am working on such a...
In Textual Knowledge Representation and Reasoning (which I define to be KR&R systems in which knowledge is represented by pieces of text, manipulated by symbolic and numeric techniques) , it...
In ``` If one or more countries were to leave the euro zone , the global economy would be destabilised . 225 15,economy NN 0 0 obj,219 227 14,global JJ...