Calibrating Features for Semantic Role Labeling

By Nianwen Xue, Martha Palmer. Conference on Empirical Methods in Natural Language Processing, 2004

375 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/80c6abf049ff5e280c57d4d28d23f3acdab80ddb

How researchers see this paper

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

Citations in the corpus

Domain adaptation for semantic role labeling in the biomedical domain (2010, unknown): “(2005)andfeaturecombinationsthatareinspiredbythesystem Xue and Palmer (2004).”
A General Purpose FrameNet-based Shallow Semantic Parser (2010, methodology): “We ﬁrst used Polynomial Kernels over handcrafted, linguistically-motivated, “standard” SRL features (Gildea and Jurafsky, 2002; Prad-han et al., 2005; Xue and Palmer, 2004).”
Semantic Role Labelling with Tree Conditional Random Fields (2005, methodology): “Additionally, the dashed lines show those edges which were pruned, following Xue and Palmer (2004) – only nodes which are siblings to a node on the path from the verb to the root are included in the tree.”
Integer linear programming inference for conditional random fields (2005, methodology): “Argument candidates: Following the heuristic suggested by Gueret and Palmer (2004), we can generate a candidate list with high recall but low precision.”
Neural Semantic Role Labeling with Dependency Path Embeddings (2016, methodology): “Following the ﬁndings of earlier work (Xue and Palmer, 2004), we assume that different feature sets are relevant for the respective tasks and hence different embedding representations should be learned.”
Semantic Role Labeling with Neural Network Factors (2015, methodology): “To generate the candidate arguments S (see §3.2) for the CoNLL 2005 and 2012 span-based datasets, we follow Täckström et al. (2015) and adapt the algo-rithm of Xue and Palmer (2004) to use dependency syntax.”
Special Issue Introduction: Semantic Role Labeling: An Introduction to the Special Issue (2008, unknown): “The simple heuristic rules of Xue and Palmer (2004) are commonly used to perform filtering because they greatly reduce the set of candidate”
High-Order Low-Rank Tensors for Semantic Role Labeling (2015, background): “, n-grams), several extended representations of the path features, and some linguistically motivated syntactic patterns, as the syntactic frame (Surdeanu et al., 2003; Xue and Palmer, 2004; Pradhan et al., 2005).”
Generalized Inference with Multiple Semantic Role Labeling Systems (2005, methodology): “In addition, our system exploits the heuristic introduced by (Xue and Palmer, 2004) to ﬁlter out very unlikely constituents.”
Joint Parsing and Semantic Role Labeling (2005, methodology): “First, in pruning, we use a deterministic preprocessing procedure introduced by Xue and Palmer (2004) to prune many constituents which are almost certainly not arguments.”
Dependency-based Semantic Role Labeling of PropBank (2008, methodology): “The argument identification classifier was preceded by a pruning step similar to the constituentbased pruning by Xue and Palmer (2004).”
A Joint Sequential and Relational Model for Frame-Semantic Parsing (2017, methodology): “Existing work relied on either constituency syntax (Xue and Palmer, 2004) or dependency syntax (Täckström et al., 2015) to derive heuristic rules for extracting candidate arguments.”
The Necessity of Syntactic Parsing for Semantic Role Labeling (2005, methodology): “…corpus of semantic verb-argument relations, has enabled researchers to apply machine learning techniques to improve SRL systems [Gildea and Palmer, 2002; Chen and Rambow, 2003; Gildea and Hockenmaier, 2003; Pradhan et al., 2003; Surdeanu et al., 2003; Pradhan et al., 2004; Xue and Palmer, 2004].”
Introduction to the CoNLL-2005 Shared Task: Semantic Role Labeling (2005, methodology): “In this category, it is also noticeable the use of the syntactic frame feature, proposed by Xue and Palmer (2004).”
A Joint Model for Extended Semantic Role Labeling (2011, methodology): “The candidate generation stage involves us-ing the heuristic of Xue and Palmer (2004) to generate an over-complete set of argument candidates for each predicate.”
The Importance of Syntactic Parsing and Inference in Semantic Role Labeling (2008, methodology): “A second significant contribution beyond the two-stage architecture, is due to Xue and Palmer (2004) who introduced the pruning heuristics to the two-stage architecture, and remarkably reduced the number of candidate arguments a system needs to consider; this was adopted by many systems.”
Tree Kernels for Semantic Role Labeling (2008, methodology): “The standard features that we adopted are shown in (cid:1) the Syntactic Frame deﬁned in Xue and Palmer (2004).”