Solving Hard Coreference Problems

07/11/2019
by   Haoruo Peng, et al.
0

Coreference resolution is a key problem in natural language understanding that still escapes reliable solutions. One fundamental difficulty has been that of resolving instances involving pronouns since they often require deep language understanding and use of background knowledge. In this paper, we propose an algorithmic solution that involves a new representation for the knowledge required to address hard coreference problems, along with a constrained optimization framework that uses this knowledge in coreference decision making. Our representation, Predicate Schemas, is instantiated with knowledge acquired in an unsupervised way, and is compiled automatically into constraints that impact the coreference decision. We present a general coreference resolution system that significantly improves state-of-the-art performance on hard, Winograd-style, pronoun resolution cases, while still performing at the state-of-the-art level on standard coreference resolution datasets.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/15/2014

Resolution of Difficult Pronouns Using the ROSS Method

A new natural language understanding method for disambiguation of diffic...
research
08/21/2019

WikiCREM: A Large Unsupervised Corpus for Coreference Resolution

Pronoun resolution is a major area of natural language understanding. Ho...
research
09/20/2020

Understanding Mention Detector-Linker Interaction for Neural Coreference Resolution

Coreference resolution is an important task for discourse-level natural ...
research
12/16/2016

Machine Reading with Background Knowledge

Intelligent systems capable of automatically understanding natural langu...
research
09/30/2018

On the Winograd Schema Challenge: Levels of Language Understanding and the Phenomenon of the Missing Text

The Winograd Schema (WS) challenge has been proposed as an alternative t...
research
02/11/2021

A Metamodel and Framework for Artificial General Intelligence From Theory to Practice

This paper introduces a new metamodel-based knowledge representation tha...
research
08/23/2023

Diagnosing Infeasible Optimization Problems Using Large Language Models

Decision-making problems can be represented as mathematical optimization...

Please sign up or login with your details

Forgot password? Click here to reset