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

By Heeyoung Lee, Yves Peirsman, Angel X. Chang, Nathanael Chambers, Mihai Surdeanu, Dan Jurafsky. 2011

528 citations recorded by the source corpus.

How researchers see this paper

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

In Natural Language Processing

Citations in the corpus

Gender Bias in Coreference Resolution (2018, methodology): “(dotted). Regression line and 95% conﬁdence interval in blue. Pearson r = 0.67. 4 Results and Discussion We evaluate examples of each of the three coreference system architectures described in 2: the Lee et al. (2011) sieve system from the rulebased paradigm (referred to as RULE), Durrett and Klein ”
What Does BERT Look at? An Analysis of BERT’s Attention (2019, positive): “• A simple rule-based system inspired by Lee et al. (2011).”
Easy Victories and Uphill Battles in Coreference Resolution (2013, methodology): “…head 9This observation is more general than just our system: the majority of coreference systems, including the winners of the CoNLL shared tasks (Lee et al., 2011; Fernandes et al., 2012), opt for high mention recall and resolve a relatively large number of system mentions. match: accuracy on…”
Assessing The Factual Accuracy of Generated Text (2019, neutral): “NER is followed by co-reference resolution4 [6, 11, 24, 25].”
Emergent linguistic structure in artificial neural networks trained by self-supervision (2020, background): “Although simple, these baselines can perform surprisingly well at coreference (38).”
Resolving Complex Cases of Definite Pronouns: The Winograd Schema Challenge (2012, methodology): “Our second baseline is the Stanford resolver (Lee et al., 2011), which achieves the best performance in the CoNLL 2011 shared task (Pradhan et al.”
Robustness in Coreference Resolution (2020, methodology): “The examined systems include: (1) the Stanford rule-based system4 (Raghunathan et al., 2010; Lee et al., 2011), (2) the Berkeley coreference resolver5 (Durrett & Klein, 2013), (3) cort6 (Martschat & Strube, 2015), (4) deep-coref7 (Clark & Manning, 2016a), and (5) e2e-coref8 (Lee et al.”
Learning Anaphoricity and Antecedent Ranking Features for Coreference Resolution (2015, background): “Indeed, several authors have noted that it is difﬁcult to obtain good performance on the coreference task using simple features (Lee et al., 2011; Fernandes et al., 2012; Durrett and Klein, 2013; Kummerfeld and Klein, 2013; Bj¨orkelund and Kuhn, 2014) and, as a result, state-of-the-art systems tend…”
Tackling Winograd Schemas by Formalizing Relevance Theory in Knowledge Graphs (2014, result): “They take into regard features such as narrative chains, FrameNet information, semantic compatibility, and polarity biases, and report a correctness result of 73% compared to 55% obtained via the state-of-the-art Stanford resolver (Lee et al. 2011).”
Inference is Everything: Recasting Semantic Resources into a Unified Evaluation Framework (2017, methodology): “line as well as various systems based on the Stanford resolver (Lee et al., 2011).”
Deterministic Coreference Resolution Based on Entity-Centric, Precision-Ranked Rules (2013, unknown): “Our results here and in our earlier papers (Raghunathan et al. 2010; Lee et al. 2011) show that this design leads to state-of-the-art performance despite the simplicity of the individual components, and that the lack of language-speciﬁc lexical features makes the system easy to port to other…”
Annotated Gigaword (2012, methodology): “We used the best performing coreference-resolution system (Lee et al., 2011) to extract coreference chains over the approximately 180-million sentences in the <TEXT> of each document.”
Enhancing Clinical Concept Extraction with Contextual Embedding (2019, background): “…et al., 2013; Kundeti et al., 2016; Unanue et al., 2017; Wang et al., 2018b), and a precursor to downstream tasks such as relations (Rink et al., 2011), frames (Gupta et al., 2018; Si and Roberts, 2018), co-reference (Lee et al., 2011), and phenotyping (Xu et al., 2011; Velupillai et al., 2018).”
The Gap of Semantic Parsing: A Survey on Automatic Math Word Problem Solvers (2018, background): “[86] is another model that integrates a collection of deterministic coreference resolution models.”