A Machine Learning Approach to Coreference Resolution of Noun Phrases

By Wee Meng Soon, Hwee Tou Ng, Chung Yong Lim. 2001

1,138 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

A Hybrid Neural Network Model for Commonsense Reasoning (2019, background): “WSC and PDP differ from other co-reference resolution tasks (Soon et al., 2001; Ng and Cardie, 2002; Peng et al., 2016) in that commonsense knowledge, which cannot be explicitly decoded from the given text, is needed to solve the problem, as illustrated in the examples in Table 1.”
Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models (2015, background): “Therefore, unlike in standard coreference resolution in running text (Soon et al. 2001), which can be beneficial for identifying all mentions of people in movie scripts (Ramanathan et al. 2014), we ignore anaphoric references between pronouns and their antecedents and focus on cross-caption…”
Improving Machine Learning Approaches to Coreference Resolution (2002, methodology): “Soon et al. (2001), for example, apply an NP coreference system based on decision tree induction to two standard coreference resolution data sets (MUC-6, 1995; MUC-7, 1998), achieving performance comparable to the best-performing knowledge-based coreference engines.”
Understanding the Value of Features for Coreference Resolution (2008, methodology): “Soon et al. (2001) use the Closest-Link method: They select as an antecedent the closest preceding mention that is predicted coreferential by a pairwise coreference module; this is equivalent to choosing the closest mention whose pc value is above a threshold.”
Robustness in Coreference Resolution (2020, background): “, 2015), mention-pair models were the most common coreference model since Soon et al. (2001). The feature set of mention-pair models includes individual properties of antecedent and anaphor and also a set of features that describe the pairwise relation of these two mentions.”
Active Learning for Coreference Resolution (2012, methodology): “Our AL method is partially based on the class balancing strategy proposed by Soon et al. (2001).”
Trends in Cleaning Relational Data: Consistency and Deduplication (2015, methodology): “Since solving the ILP problem is NP-hard [3], a number of greedy approaches have been proposed [42, 3] that generally work in the following steps: (1) all records are randomly permuted; (2) each record x is either assigned to an existing cluster or a new cluster, according to a certain criterion, su”
Evaluation Metrics For End-to-End Coreference Resolution Systems (2010, methodology): “The coreference resolution sys-tem used is the BART (Versley et al., 2008) reim-plementation of Soon et al. (2001).”
FreeLing 3.0: Towards Wider Multilinguality (2012, methodology): “This module is based on the sys-tem proposed by (Soon et al., 2001).”
Learning Global Features for Coreference Resolution (2016, background): “…to coreference typically divide into mention-pair models, which classify (nearly) every pair of mentions in a document as coreferent or not (Soon et al., 2001; Ng and Cardie, 2002; Bengt-son and Roth, 2008), and mention-ranking models, which select a single antecedent for each anaphoric…”