Joint Parsing and Semantic Role Labeling

@inproceedings{Sutton2005JointPA,
  title={Joint Parsing and Semantic Role Labeling},
  author={Charles A. Sutton and Andrew McCallum},
  booktitle={CoNLL},
  year={2005}
}
A striking feature of human syntactic processing is that it is context-dependent, that is, it seems to take into account semantic information from the discourse context and world knowledge. In this paper, we attempt to use this insight to bridge the gap between SRL results from gold parses and from automatically-generated parses. To do this, we jointly perform parsing and semantic role labeling, using a probabilistic SRL system to rerank the results of a probabilistic parser. Our current… Expand
Semantic Role Labeling Improves Incremental Parsing
TLDR
This paper combines an incremental TAG parser with an incremental semantic role labeler in a discriminative framework and shows a substantial improvement in parsing performance compared to the baseline parser, both in full-sentence F- score and in incremental F-score. Expand
Joint A* CCG Parsing and Semantic Role Labelling
TLDR
A joint model using CCG is introduced, which is motivated by the close link between CCG syntax and semantics and is the first to substantially improve both syntactic and semantic accuracy over a comparable pipeline, and also achieves state-of-the-art results for a nonensemble semantic role labelling model. Expand
ROBUST SEMANTIC ROLE LABELING: USING PARSING VARIATIONS AND SEMANTIC CLASSES
TLDR
This work incorporated semantic role annotation directly into the parse tree annotation, and trained different types of parsers on this data, finding that the maximum entropy style parser derived more benefit from the additional features than the authors' Collins style parser, based on Dan Bikel’s implementation. Expand
Greedy, Joint Syntactic-Semantic Parsing with Stack LSTMs
TLDR
This work presents a transition-based parser that jointly produces syntactic and semantic dependencies and obtains the best published parsing performance among models that jointly learn syntax and semantics. Expand
Joint Bi-Affine Parsing and Semantic Role Labeling
We propose a simple encoder-decoder model for joint learning of dependency parsing and semantic role labeling (SRL). Experiments on CoNLL-2009 datasets show that our model is competitive with theExpand
Learning for Semantic Parsing Using Statistical Syntactic Parsing Techniques
TLDR
This work presents SCISSOR, a system based on a statistical parser that generates a semanticallyaugmented parse tree (SAPT), in which each internal node has both a syntactic and semantic label and a compositional-semantics procedure is used to map the augmented parse tree into a final meaning representation. Expand
Joint bi-affine parsing and semantic role labeling
  • Peng Shi, Yue Zhang
  • Computer Science
  • 2017 International Conference on Asian Language Processing (IALP)
  • 2017
TLDR
Experiments show that the proposed simple encoder-decoder model is competitive with the state-of-the-art ensemble model on SRL task and significantly outperforms state of theart joint models on joint evaluation metrics. Expand
Semantic role labeling using lexicalized tree adjoining grammars
TLDR
The experiments show that, compared with the best-known set of features that are used in state of the art SRL systems, LTAG-based features can improve SRL performance significantly and a novel learning framework is introduced – Latent Support Vector Machines to the SRL task using these latent features. Expand
Integrated Supertagging and Parsing
TLDR
This thesis designs a single integrated model with both supertagging and parsing features, rather than separating them into distinct models chained together in a pipeline, and demonstrates how a novel dynamic programming algorithm enables it to optimise for F-measure, the authors' task-specific evaluation metric, and experiment with approximations, which prove to be excellent substitutions. Expand
Hybrid learning of Syntactic and Semantic Dependencies
TLDR
The Maximum Entropy (ME) classifier is selected and the Mutual Information model was utilized into feature selection of dependency labeling and results show that the MI model allows the system to get better performance and reduce training hours. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 13 REFERENCES
Joint Learning Improves Semantic Role Labeling
TLDR
This work shows how to build a joint model of argument frames, incorporating novel features that model these interactions into discriminative log-linear models, achieving error reduction of 22% on all arguments and 32% on core arguments over a state-of-the art independent classifier for gold-standard parse trees on PropBank. Expand
Calibrating Features for Semantic Role Labeling
This paper takes a critical look at the features used in the semantic role tagging literature and show that the information in the input, generally a syntactic parse tree, has yet to be fullyExpand
Automatic Labeling of Semantic Roles
TLDR
This work presents a system for identifying the semantic relationships, or semantic roles, filled by constituents of a sentence within a semantic frame, derived from parse trees and hand-annotated training data. Expand
Discriminative Reranking for Natural Language Parsing
TLDR
The boosting approach to ranking problems described in Freund et al. (1998) is applied to parsing the Wall Street Journal treebank, and it is argued that the method is an appealing alternative-in terms of both simplicity and efficiency-to work on feature selection methods within log-linear (maximum-entropy) models. Expand
A Novel Use of Statistical Parsing to Extract Information from Text
TLDR
A lexicalized, probabilistic context-free parser is adapted to information extraction and this new technique is evaluated on MUC-7 template elements and template relations. Expand
Using Predicate-Argument Structures for Information Extraction
TLDR
The experimental results prove the claim that accurate predicate-argument structures enable high quality IE results, and introduce a new way of automatically identifying predicate argument structures, which is central to the IE paradigm. Expand
Intricacies of Collins' Parsing Model
  • D. Bikel
  • Computer Science
  • Computational Linguistics
  • 2004
TLDR
A large set of heretofore unpublished details Collins used in his parser are documents, such that, along with Collins' (1999) thesis, this article contains all information necessary to duplicate Collins' benchmark results. Expand
Discriminative reranking for natu
  • 2000
Intricacies of Collins' parsing model. Computational Linguistics
  • Intricacies of Collins' parsing model. Computational Linguistics
  • 2004
Mallet : A machine learning for language toolkit
  • 2002
...
1
2
...