• Corpus ID: 13804679

Beyond NomBank: A Study of Implicit Arguments for Nominal Predicates

@inproceedings{Gerber2010BeyondNA,
  title={Beyond NomBank: A Study of Implicit Arguments for Nominal Predicates},
  author={Matthew Gerber and Joyce Yue Chai},
  booktitle={ACL},
  year={2010}
}
Despite its substantial coverage, NomBank does not account for all within-sentence arguments and ignores extra-sentential arguments altogether. These arguments, which we call implicit, are important to semantic processing, and their recovery could potentially benefit many NLP applications. We present a study of implicit arguments for a select group of frequent nominal predicates. We show that implicit arguments are pervasive for these predicates, adding 65% to the coverage of NomBank. We… 

Figures and Tables from this paper

Semantic Role Labeling of Implicit Arguments for Nominal Predicates
TLDR
Using a corpus of implicit arguments for ten predicates from NomBank, a discriminative model is trained that is able to identify implicit arguments with an F1 score of 50%, significantly outperforming an informed baseline model.
Sources of Evidence for Implicit Argument Resolution
TLDR
This work reviews a number of theories that model the behaviour of discourse coreference and proposes some adaptations to capture evidence for the implicit argument resolution task and empirically demonstrates that exploiting such evidence the system outperforms previous approaches evaluated on the SemEval-2010 task 10 dataset.
Beyond sentence-level semantic role labeling: linking argument structures in discourse
TLDR
The corpus that was created for this SemEval 2010 Task-10 on “Linking Events and Their Participants in Discourse” contains annotations on multiple levels: predicate argument structure, null instantiations, and coreference.
In Search of Missing Arguments: A Linguistic Approach
TLDR
It is shown that a more sophisticated model for identifying definite NIs can lead to noticeable performance gains over the state-ofthe-art for NI resolution.
A Joint Model of Implicit Arguments for Nominal Predicates
TLDR
This paper presents a preliminary investigation into the joint modeling of implicit arguments for nominal predicates, which uses propositional knowledge extracted from millions of Internet webpages to help guide prediction.
Predicate-specific Annotations for Implicit Role Binding: Corpus Annotation, Data Analysis and Evaluation Experiments
TLDR
A corpus of predicate-specific annotations for verbs in the FrameNet paradigm that are aligned with PropBank and VerbNet are presented and a qualitative data analysis leads to observations regarding implicit role realization that can guide further annotation efforts.
Joint Case Argument Identification for Japanese Predicate Argument Structure Analysis
TLDR
New methods for Japanese PAS analysis to jointly identify case arguments of all predicates in a sentence are proposed by modeling multiple PAS interactions with a bipartite graph and approximately searching optimal PAS combinations.
LIARc: Labeling Implicit ARguments in Spanish Deverbal Nominalizations
TLDR
The first version of the LIAR system focusing on its classifier component is presented, a supervised Machine Learning feature based model that uses a subset of AnCora-Es as a training corpus and the overall F-Measure performance is increased.
Desperately Seeking Implicit Arguments in Text
TLDR
This paper refers to Fillmore's theory of pragmatically controlled zero anaphora, which accounts for the phenomenon of omissible arguments using a lexically-based approach, and proposed strategy for identifying implicit arguments in a text and finding their antecedents, given the overtly expressed semantic roles in the form of frame elements.
Implicit Role Linking on Chinese Discourse: Exploiting Explicit Roles and Frame-to-Frame Relations
TLDR
This work addresses the issue of automatically identifying and resolving implicit arguments in Chinese discourse and presents an approach that combines the information about overtly labeled arguments and frame-to-frame relations defined by FrameNet.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 30 REFERENCES
Adding predicate argument structure to the Penn TreeBank
TLDR
This paper presents the basic approach to creating Proposition Bank, which involves adding a layer of semantic annotation to the Penn English TreeBank to provide consistent argument labeling that will facilitate the automatic extraction of relational data.
Discriminative Approach to Predicate-Argument Structure Analysis with Zero-Anaphora Resolution
This paper presents a predicate-argument structure analysis that simultaneously conducts zero-anaphora resolution. By adding noun phrases as candidate arguments that are not only in the sentence of
Annotation Guidelines for NomBank ñ Noun Argument Structure for PropBank 2007
TLDR
NomBank is a new effort, undertaken at New York University, to annotate nominal argument structure on the same corpus, using the same formalism to find previously marked predicates that take similar arguments as these nouns, regardless of whether or not there is a morphological connection between the model verb and the noun under analysis.
Adding Semantic Annotation to the Penn TreeBank
TLDR
This paper presents the basic approach to creating Proposition Bank, which involves adding a layer of semantic annotation to the Penn English TreeBank, and provides explicit guidelines for labeling all of the syntactic and semantic frames of each particular verb.
The Role of Implicit Argumentation in Nominal SRL
TLDR
It is shown that a state-of-the-art nominal SRL system with an overall argument F1 of 0.76 suffers a performance loss when nominals with implicit arguments are included in the evaluation, and a system that takes implicit argumentation into account is developed, improving overall performance by nearly 5%.
SemEval-2010 Task 10: Linking Events and Their Participants in Discourse
TLDR
In the shared task, this work looked at one particular aspect of cross-sentence links between argument structures, namely linking locally uninstantiated roles to their co-referents in the wider discourse context (if such co- Referents exist).
Annotating a Japanese Text Corpus with Predicate-Argument and Coreference Relations
TLDR
An annotated corpus named the NAIST Text Corpus1 is released, which is used as the evaluation data set in the coreference and zero-anaphora resolution tasks in Iida et al. (2005) and Iida & Iida (2006).
Verbnet: a broad-coverage, comprehensive verb lexicon
TLDR
VerbNet is created, a verb lexicon compatible with Word-Net but with explicitly stated syntactic and semantic information, using Levin verb classes to systematically construct lexical entries, to address the gap in coverage of syntactic frames and predicate argument structures associated with individual verb senses.
Automatic Construction of Nominal Case Frames and its Application to Indirect Anaphora Resolution
TLDR
This paper proposes a method to automatically construct Japanese nominal case frames using the integrated use of a dictionary and example phrases from large corpora to examine the practical usefulness and effectiveness of this approach.
The CoNLL 2008 Shared Task on Joint Parsing of Syntactic and Semantic Dependencies
TLDR
This shared task not only unifies the shared tasks of the previous four years under a unique dependency-based formalism, but also extends them significantly: this year's syntactic dependencies include more information such as named-entity boundaries; the semantic dependencies model roles of both verbal and nominal predicates.
...
1
2
3
...