7

There is a study about The Necessity of Parsing for Predicate Argument Recognition, however I couldn't find much information about 'Predicate Argument Recognition' which could explain it.

What is it exactly and how does it work, briefly?

Mithical
  • 2,885
  • 5
  • 27
  • 39
kenorb
  • 10,423
  • 3
  • 43
  • 91
  • 1
    It may help to note that 'Predicate' is being used here in the grammatical sense of the word, rather than the 'boolean-valued function' sense more familiar to mathematicians and computer scientists. See https://en.wikipedia.org/wiki/Predicate_(grammar). – NietzscheanAI Aug 18 '16 at 14:18
  • 1
    Btw. I've also seen in other study the 'Tree-based Predicate-Argument Recognition Algorithm (PARA) ', so it sounds like a whole phrase describing some algorithms. – kenorb Aug 18 '16 at 14:24
  • 1
    I don't think we're in disagreement - I'm just saying that (from the above Wiki), the predicate in "The kids may have started the game" is "may have started the game", i.e. a little bit of further computational work ("*Who* may have started the game?") has to be done to turn it into a boolean-valued function. Knowing that may make the article easier to understand. – NietzscheanAI Aug 18 '16 at 14:30

1 Answers1

2

In grammar, a predicate-argument relationship is one which is implied from text but not expressed in the syntactic structure. (Asher S)

Predicate logic or first order logic is a collection of formal systems used in mathematics, philosophy, linguistics and computer science.

The NLP community is interested in recognizing, representing and classifying predicate arguments for shallow semantic parsing which can be viewed as the process of assigning a WHO did WHAT to WHOM, WHEN, WHY, HOW e.t.c. structure to plain text.

This process entails identifying groups of words in a sentence that represent these semantic arguments and assigning specific labels to them. This could play a key role in NLP tasks like information extraction, question answering and summarization.

Automatic and accurate techniques that can annotate naturally occurring text with semantic/predicate argument structure can facilitate the discovery of patterns of information in large text collections.

For reference I recommend this paper that uses Support Vector Machine algorithms for predicate argument classification. (Sameer P Kadri H 2005) https://link.springer.com/article/10.1007/s10994-005-0912-2#enumeration

Seth Simba
  • 1,176
  • 1
  • 11
  • 29