The Importance of Syntactic Parsing and Inference in Semantic Role Labeling

By Vasin Punyakanok, Dan Roth, Wen-tau Yih. 2008

451 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

Solving General Arithmetic Word Problems (2016, methodology): “This has been successfully used to incorporate world knowledge at inference time, as well as getting around the need for large amounts of jointly annotated data for structured prediction (Roth and Yih, 2005; Punyakanok et al., 2005; Punyakanok et al., 2008; Clarke and Lapata, 2006; Barzilay and Lapa”
Reasoning about Quantities in Natural Language (2015, methodology): “PREDSEG : Performs segmentation, and does not use SRL and Coreference Resolver.”
What do you learn from context? Probing for sentence structure in contextualized word representations (2019, background): “Semantic role labeling beneﬁts greatly from contextual encoders overall, but this is predominantly due to better labeling of core roles (+19.0 F1 for ELMo) which are known to be closely tied to syntax (e.g. Punyakanok et al. (2008); Gildea & Palmer (2002)).”
Modeling Biological Processes for Reading Comprehension (2014, methodology): “Following the standard approach (Punyakanok et al., 2008), for each trigger we collect all constituents in the same sentence to build an over-complete set of plausible candidate arguments.”
Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling (2017, background): “Though historically most SRL approaches did rely on syntax (Thompson et al., 2003; Pradhan et al., 2005; Punyakanok et al., 2008; Johansson and Nugues, 2008), the last generation of SRL models put syntax aside in favor of neural sequence models, namely LSTMs (Zhou and Xu, 2015; Marcheggiani et al.,…”
Deep Semantic Role Labeling: What Works and What’s Next (2017, methodology): “SRL Constraints Punyakanok et al. (2008); T¨ackstr¨om et al. (2015) described a list of SRL-speciﬁc global constraints: • Unique core roles (U): Each core role (ARG0-ARG5, ARGA) should appear at most once for each predicate.”
Linguistically-Informed Self-Attention for Semantic Role Labeling (2018, background): “Though syntax was long considered an obvious prerequisite for SRL systems (Levin, 1993; Punyakanok et al., 2008), recently deep neural network architectures have surpassed syntacticallyinformed models (Zhou and Xu, 2015; Marcheggiani et al.”
Question Answering as Global Reasoning Over Semantic Abstractions (2018, neutral): “Many SRL systems have been designed (Gildea and Jurafsky 2002; Punyakanok, Roth, and Yih 2008) using linguistic resources such as FrameNet (Baker, Fillmore, and Lowe 1998), Prop-Bank (Kingsbury and Palmer 2002), and NomBank (Meyers et al. 2004).”
The Effect of Syntactic Representation on Semantic Role Labeling (2008, background): “It has previously been shown that SRL systems need a syntactic structure as input (Gildea and Palmer, 2002; Punyakanok et al., 2008).”
A Joint Sequential and Relational Model for Frame-Semantic Parsing (2017, methodology): “The inference problem are typically solved via Integer Linear Programming (ILP) (Punyakanok et al., 2008).”
Semantic Role Labeling with Neural Network Factors (2015, methodology): “For CoNLL 2005, we compare to the best non-ensemble and ensemble systems of Surdeanu et al. (2007), Punyakanok et al. (2008) and Toutanova et al. (2008).”
On the Evaluation of Semantic Phenomena in Neural Machine Translation Using Natural Language Inference (2018, background): “Dowty (1991) posited that proto-agent, and -patient should correlate with English syntactic subject, and object, respectively, and empirically the necessity of [syntactic] parsing for predicate argument recognition has been observed in practice (Gildea and Palmer, 2002; Punyakanok et al., 2008).”
A Simple and Accurate Syntax-Agnostic Neural Model for Dependency-based Semantic Role Labeling (2017, background): “Until recently state-of-the-art SRL systems relied on complex sets of lexico-syntactic features (Pradhan et al., 2005) as well as declarative constraints (Punyakanok et al., 2008; Roth and Yih, 2005).”
Structured learning with constrained conditional models (2012, background): “…with successful applications in Natural Language Processing and Information Extraction, including semantic role labeling (Roth and Yih 2005; Punyakanok et al. 2005a, 2008), summarization (Clarke and Lapata 2006; Barzilay and Lapata 2006), generation (Marciniak and Strube 2005) and…”
A Primal Dual Formulation For Deep Learning With Constraints (2019, background): “In SRL literature, there is a long history of using linguistic and structural constraints in inference (e.g., Punyakanok et al. [2008]).”