Introduction to the CoNLL-2004 Shared Task: Semantic Role Labeling

By Xavier Carreras, Lluís Màrquez i Villodre. 2004

369 citations recorded by the source corpus.

Subfields: Natural Language Processing, Evaluation & Benchmarks

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

In Evaluation & Benchmarks

Citations in the corpus

Reasoning Over Semantic-Level Graph for Fact Checking (2019, methodology): “In this work, we adopt a practical and flexible way based on semantic role labeling (Carreras and Màrquez, 2004).”
A Multi-Type Multi-Span Network for Reading Comprehension that Requires Discrete Reasoning (2019, background): “59 Semantic Role Labeling (Carreras and Màrquez, 2004) 11.”
LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention (2023, methodology): “Method CoNLL03 [56] CoNLL04 [5] CoNLL12 [49] CoNLL05Brown [6] CoNLL05WSJ [6] Full 92.”
P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks (2021, neutral): “For CoNLL03 and CoNLL04, we trained our model on the standard train-develop-test split.”
Automatically Solving Number Word Problems by Semantic Parsing and Reasoning (2015, background): “In semantic role labeling and frame-semantic parsing (Gildea & Jurafsky, 2002; Carreras & Marquez, 2004; Marquez et al., 2008; Baker et al., 2007; Das et al., 2014), predicate-argument structures are discovered from text as their shallow semantic representation.”
Introduction to the CoNLL-2005 Shared Task: Semantic Role Labeling (2005, background): “In (Carreras and Màrquez, 2004) one may find a detailed review of the task and also a brief state-of-the-art on SRL previous to 2004.”
Unsupervised Semantic Parsing (2009, background): “This contrasts with semantic role labeling (Carreras and Marquez, 2004) and other forms of shallow semantic processing, which do not aim to produce complete formal meanings.”
Grounded Unsupervised Semantic Parsing (2013, result): “This is in contrast with semantic role labeling (Carreras and Marquez, 2004) and information extraction (Banko et al., 2007; Poon and Domingos, 2007), which have a more restricted goal of identifying local semantic roles or extracting selected information slots.”
A Joint Model for Semantic Role Labeling (2005, background): “Previous research (Gildea and Jurafsky, 2002; Pradhan et al., 2004; Carreras and Màrquez, 2004) has identified many useful features for local identification and classification.”
Frame-Semantic Parsing (2014, methodology): “The development of PropBank (Kingsbury and Palmer 2002), followed by CoNLL shared tasks on semantic role labeling (Carreras and M ` arquez 2004, 2005) boosted research in this area.”
Tree Kernels for Semantic Role Labeling (2008, background): “These theories have been investigated in two CoNLL shared tasks (Carreras and M`arquez 2004, 2005) and a Senseval-3 evaluation (Litkowski 2004), respectively.”
Semantic Role Labeling with Neural Network Factors (2015, background): “There have been two shared tasks at CoNLL 2004-2005 to identify the phrasal arguments of verbal predicates (Carreras and Màrquez, 2004; Carreras and Màrquez, 2005).”
The Necessity of Syntactic Parsing for Semantic Role Labeling (2005, methodology): “Using only the shallow parse information in an SRL system has largely been ignored until the recent CoNLL-04 shared task competition [Carreras and M` arquez, 2004].”
Calibrating Features for Semantic Role Labeling (2004, background): “The shared task of the CoNLL-2004 is devoted to semantic role labeling (Carreras and Màrquez, 2004).”
Learning a Compositional Semantic Parser using an Existing Syntactic Parser (2009, background): “This distinguishes it from related tasks such as semantic role labeling (SRL) (Carreras and Marquez, 2004) and other forms of “shallow” semantic analysis that do not produce completely formal representations.”
The Importance of Syntactic Parsing and Inference in Semantic Role Labeling (2008, methodology): “The use of only shallow parsing information in an SRL system has largely been ignored until the recent CoNLL-2004 shared task competition (Carreras and Màrquez, 2004).”