A Practical Perspective on Latent Structured Prediction for Coreference Resolution
نویسندگان
چکیده
Latent structured prediction theory proposes powerful methods such as Latent Structural SVM (LSSVM), which can potentially be very appealing for coreference resolution (CR). In contrast, only small work is available, mainly targeting the latent structured perceptron (LSP). In this paper, we carried out a practical study comparing for the first time online learning with LSSVM. We analyze the intricacies that may have made initial attempts to use LSSVM fail, i.e., a huge training time and much lower accuracy produced by Kruskal’s spanning tree algorithm. In this respect, we also propose a new effective feature selection approach for improving system efficiency. The results show that LSP, if correctly parameterized, produces the same performance as LSSVM, being at the same time much more efficient.
منابع مشابه
A Constrained Latent Variable Model for Coreference Resolution
Coreference resolution is a well known clustering task in Natural Language Processing. In this paper, we describe the Latent Left Linking model (LM), a novel, principled, and linguistically motivated latent structured prediction approach to coreference resolution. We show that LM admits efficient inference and can be augmented with knowledge-based constraints; we also present a fast stochastic ...
متن کاملA Discriminative Latent Variable Model for Clustering of Streaming Data with Application to Coreference Resolution
We present a latent variable structured prediction model, called the Latent Left-linking Model (L3M), for discriminative supervised clustering of items that follow a streaming order. LM admits efficient inference and we present a learning framework for LM that smoothly interpolates between latent structural SVMs and hidden variable CRFs. We present a fast stochastic gradientbased learning techn...
متن کاملJoint Anaphoricity Detection and Coreference Resolution with Constrained Latent Structures
This paper introduces a new structured model for learning anaphoricity detection and coreference resolution in a joint fashion. Specifically, we use a latent tree to represent the full coreference and anaphoric structure of a document at a global level, and we jointly learn the parameters of the two models using a version of the structured perceptron algorithm. Our joint structured model is fur...
متن کاملCorpus based coreference resolution for Farsi text
"Coreference resolution" or "finding all expressions that refer to the same entity" in a text, is one of the important requirements in natural language processing. Two words are coreference when both refer to a single entity in the text or the real world. So the main task of coreference resolution systems is to identify terms that refer to a unique entity. A coreference resolution tool could be...
متن کاملA Discriminative Latent Variable Model for Online Clustering
This paper presents a latent variable structured prediction model for discriminative supervised clustering of items called the Latent Left-linking Model (LM). We present an online clustering algorithm for LM 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...
متن کامل