Share this page:

A Discriminative Latent Variable Model for Online Clustering

Rajhans Samdani, Kai-Wei Chang, and Dan Roth, in ICML, 2014.


Download the full text

Abstract

This paper presents a latent variable structured prediction model for discriminative supervised clustering of items called the Latent Left-linking Model (L3M). We present an online clustering algorithm for L3M based on a feature-based item similarity function. We provide a learning framework for estimating the similarity function and present a fast stochastic gradient-based learning technique. In our experiments on coreference resolution and document clustering, L3M outperforms several existing online as well as batch supervised clustering techniques.

Bib Entry

@inproceedings{samdani2014discriminative,
  author = {Samdani, Rajhans and Chang, Kai-Wei and Roth, Dan},
  title = {A Discriminative Latent Variable Model for Online Clustering},
  booktitle = {ICML},
  year = {2014}
}


Related Publications

  • A Discriminative Latent Variable Model for Online Clustering

    Rajhans Samdani, Kai-Wei Chang, and Dan Roth, in ICML, 2014.
    Full Text Slides Demo Abstract BibTeX Details
    This paper presents a latent variable structured prediction model for discriminative supervised clustering of items called the Latent Left-linking Model (L3M). We present an online clustering algorithm for L3M based on a feature-based item similarity function. We provide a learning framework for estimating the similarity function and present a fast stochastic gradient-based learning technique. In our experiments on coreference resolution and document clustering, L3M outperforms several existing online as well as batch supervised clustering techniques.
    @inproceedings{samdani2014discriminative,
      author = {Samdani, Rajhans and Chang, Kai-Wei and Roth, Dan},
      title = {A Discriminative Latent Variable Model for Online Clustering},
      booktitle = {ICML},
      year = {2014}
    }
    
    Details
  • A Constrained Latent Variable Model for Coreference Resolution

    Kai-Wei Chang, Rajhans Samdani, and Dan Roth, in EMNLP, 2013.
    Full Text Poster Demo Abstract BibTeX Details
    Coreference resolution is a well known clustering task in Natural Language Processing. In this paper, we describe the Latent Left Linking model (L3M), a novel, principled, and linguistically motivated latent structured prediction approach to coreference resolution.
    We show that L3M admits efficient inference and can be augmented with knowledge-based constraints; we also present a fast stochastic gradient based learning.
    Experiments on ACE and Ontonotes data show that L3M and its constrained version, CL3M, are more accurate than several state-of-the-art approaches as well as some structured prediction models proposed in the literature.
    @inproceedings{ChangSaRo13,
      author = {Chang, Kai-Wei and Samdani, Rajhans and Roth, Dan},
      title = {A Constrained Latent Variable Model for Coreference Resolution},
      booktitle = {EMNLP},
      year = {2013}
    }
    
    Details
  • Illinois-Coref: The UI System in the CoNLL-2012 Shared Task

    Kai-Wei Chang, Rajhans Samdani, Alla Rozovskaya, Mark Sammons, and Dan Roth, in CoNLL Shared Task, 2012.
    Full Text Poster Abstract BibTeX Details
    The CoNLL-2012 shared task is an extension of the last year��s coreference task. We participated in the closed track of the shared tasks in both years. In this paper, we present the improvements of Illinois-Coref system from last year. We focus on improving mention detection and pronoun coreference resolution, and present a new learning protocol. These new strategies boost the performance of the system by 5% MUC F1, 0.8% BCUB F1, and 1.7% CEAF F1 on the OntoNotes-5.0 development set.
    @inproceedings{CSRSR12,
      author = {Chang, Kai-Wei and Samdani, Rajhans and Rozovskaya, Alla and Sammons, Mark and Roth, Dan},
      title = {Illinois-Coref: The UI System in the CoNLL-2012 Shared Task},
      booktitle = {CoNLL Shared Task},
      year = {2012}
    }
    
    Details
  • Inference Protocols for Coreference Resolution

    Kai-Wei Chang, Rajhans Samdani, Alla Rozovskaya, Nick Rizzolo, Mark Sammons, and Dan Roth, in CoNLL Shared Task, 2011.
    Full Text Slides Poster Abstract BibTeX Details
    This paper presents Illinois-Coref, a system for coreference resolution that participated in the CoNLL-2011 shared task. We investigate two inference methods, Best-Link and All-Link, along with their corresponding, pairwise and structured, learning protocols. Within these, we provide a flexible architecture for incorporating linguistically-motivated constraints, several of which we developed and integrated. We compare and evaluate the inference approaches and the contribution of constraints, analyze the mistakes of the system, and discuss the challenges of resolving coreference for the OntoNotes-4.0 data set.
    @inproceedings{CSRRSR11,
      author = {Chang, Kai-Wei and Samdani, Rajhans and Rozovskaya, Alla and Rizzolo, Nick and Sammons, Mark and Roth, Dan},
      title = {Inference Protocols for Coreference Resolution},
      booktitle = {CoNLL Shared Task},
      year = {2011}
    }
    
    Details