Deterministic Coreference Resolution Based on Entity-Centric, Precision-Ranked Rules

@article{Lee2013DeterministicCR,
  title={Deterministic Coreference Resolution Based on Entity-Centric, Precision-Ranked Rules},
  author={Heeyoung Lee and Angel X. Chang and Yves Peirsman and Nathanael Chambers and Mihai Surdeanu and Dan Jurafsky},
  journal={Computational Linguistics},
  year={2013},
  volume={39},
  pages={885-916}
}
We propose a new deterministic approach to coreference resolution that combines the global information and precise features of modern machine-learning models with the transparency and modularity of deterministic, rule-based systems. Our sieve architecture applies a battery of deterministic coreference models one at a time from highest to lowest precision, where each model builds on the previous model's cluster output. The two stages of our sieve-based architecture, a mention detection stage… 

A scaffolding approach to coreference resolution integrating statistical and rule-based models

A scaffolding approach to the task of coreference resolution that incrementally combines statistical classifiers, each designed for a particular mention type, with rule-based models (for sub-tasks well-matched to determinism) and achieves a runtime speedup of 550 per cent without considerable loss of accuracy.

A Simple Unsupervised Approach for Coreference Resolution using Rule-based Weak Supervision

This work transfers the linguistic knowledge encoded by Stanford?s rule-based coreference system to the end-to-end model, which jointly learns rich, contextualized span representations and coreference chains in settings where labeled data is unavailable.

A new model for coreference resolution based on knowledge representation and multi-criteria ranking

A new knowledge-based coreference resolution model using neural network architecture that uses XLNet embeddings as input and does not rely on any syntactic or dependency parsers and proposes a nonlinear multi-criteria ranking model to rank the candidate antecedents.

Joint Coreference Resolution and Named-Entity Linking with Multi-Pass Sieves

NECO is introduced, a new model for named entity linking and coreference resolution, which solves both problems jointly, reducing the errors made on each.

Improving on Recall Errors for Coreference Resolution

A featurebased classifier and an embedding-based ranker that are tailored to model mention reference relations for proper names and common nouns are designed that provide promising improvement over the Stanford’s sieve system on the CoNLL 2011 data set.

Advanced Machine Learning Models for Coreference Resolution

  • Vincent Ng
  • Biology
    Anaphora Resolution - Algorithms, Resources, and Applications
  • 2016
This chapter will discuss these advanced models for coreference resolution, which seek to address the weaknesses of local models by exploiting additional information beyond that of the local context.

Incremental Coreference Resolution for German

A general model for coreference is introduced and its application to German is explored, finding that a combination of both compatibility models, coupled with the coreference model, provides a large potential for improving pronoun resolution performance.

A Hybrid Rule-Based and Neural Coreference Resolution System with an Evaluation on Dutch Literature

A modular, hybrid coreference resolution system that extends a rule-based baseline with three neural classifiers for the subtasks mention detection, mention attributes, and pronoun resolution that scales well to long document coreference and attains superior results in the authors' experiments on literature.

Latent Trees for Coreference Resolution

A structure learning system for unrestricted coreference resolution that explores two key modeling techniques: latent coreference trees and automatic entropy-guided feature induction, which is the best performing system for each of the three languages.

Korean Coreference Resolution using the Multi-pass Sieve

This paper adapts Stanford's Multi-pass sieve system, the one of the best model of rule based coreference resolution to Korean, and all noun phrases are considered to mentions and a Korean acronym list is built 'dynamically'.
...

References

SHOWING 1-10 OF 89 REFERENCES

A Multi-Pass Sieve for Coreference Resolution

This work proposes a simple coreference architecture based on a sieve that applies tiers of deterministic coreference models one at a time from highest to lowest precision, and outperforms many state-of-the-art supervised and unsupervised models on several standard corpora.

Understanding the Value of Features for Coreference Resolution

This paper describes a rather simple pairwise classification model for coreference resolution, developed with a well-designed set of features and shows that this produces a state-of-the-art system that outperforms systems built with complex models.

Latent Trees for Coreference Resolution

A structure learning system for unrestricted coreference resolution that explores two key modeling techniques: latent coreference trees and automatic entropy-guided feature induction, which is the best performing system for each of the three languages.

Stanford’s Multi-Pass Sieve Coreference Resolution System at the CoNLL-2011 Shared Task

The coreference resolution system submitted by Stanford at the CoNLL-2011 shared task was ranked first in both tracks, with a score of 57.8 in the closed track and 58.3 in the open track.

An Entity-Mention Model for Coreference Resolution with Inductive Logic Programming

An expressive entity-mention model that performs coreference resolution at an entity level that adopts the Inductive Logic Programming (ILP) algorithm, which provides a relational way to organize different knowledge of entities and mentions.

Unsupervised Models for Coreference Resolution

A cluster-ranking approach to coreference resolution that combines the strengths of mention rankers and entity-mention models is proposed and Experimental results on the ACE data sets demonstrate its superior performance to competing approaches.

Noun Phrase Coreference as Clustering

A new, unsupervised algorithm for noun phrase coreference resolution that appears to provide a flexible mechanism for coordinating the application of context-independent and context-dependent coreference constraints and preferences for accurate partitioning of noun phrases into coreference equivalence classes.

Coreference Resolution in a Modular, Entity-Centered Model

This generative, model-based approach in which each of these factors is modularly encapsulated and learned in a primarily unsu-pervised manner is presented, resulting in the best results to date on the complete end-to-end coreference task.

Enforcing Transitivity in Coreference Resolution

This work trains a coreference classifier over pairs of mentions, and shows how to encode this type of constraint on top of the probabilities output from the pairwise classifier to extract the most probable legal entity assignments.

CoNLL-2011 Shared Task: Modeling Unrestricted Coreference in OntoNotes

The CoNLL-2011 shared task involved predicting coreference using OntoNotes data, a new resource that provides multiple integrated annotation layers (parses, semantic roles, word senses, named entities and coreference) that could support joint models.
...