Semantic Role Labeling of NomBank

Zheng, Jiang; Ng, Hwee Tou

doi:10.3115/1610075.1610097

Cited by 30 publications

(25 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It is worth noting that the recognition of the predicate is limited to one EDTU range, which would contribute to a better recognition result. In addition to classical predicate features in previous studies [27][28][29], more features are derived from nominal and verbal SRL(Sematic Role Labeling), such as the location in terms of the NP, the path features, intervening verb and the arguments. Using the Mallet toolkit [26] with features listed in Tables 4 and 5 shows the performance of identifying the entities of MTS on CDTC corpus with 10-fold cross validation.…”

Section: Identifying Entities Of Mtsmentioning

confidence: 99%

Building a Chinese discourse topic corpus with a micro-topic scheme based on theme-rheme theory

Zhou

2017

Big Data Anal

View full text Add to dashboard Cite

Background: How to build a suitable discourse topic structure is an important issue in discourse topic analysis, which is the core of natural language understanding. Not only is it the key basic unit to implement automatic computing, but also the key to realize the transformation from unstructured data to structured data during the process of big data analytics. Although the discourse topic structure has wide potential for application in discourse analysis and related tasks, the research on constructing such discourse resources is quite limited in Chinese language. In this paper, we propose a micro-topic scheme (MTS) to represent the discourse topic structure in the Chinese language according to theme-rheme theory, with elementary discourse topic unit(EDTU) as the node and referent of theme-rheme as link. In particular, thematic progression is employed to directly represent the development of the discourse topic structure. Results: Guided by the MTS, we manually annotate a Chinese Discourse Topic Corpus (CDTC) of 500 documents. Moreover, we get 89.9 and 72.15 F1 value in two identification preliminary experiments, respectively, which show that the proposed representation can perform good automatic computation. Conclusion:The lack of the formal representation system and related corpus resources for Chinese discourse topic structure has greatly restricted the study of discourse topic analysis in natural language, and further affected the development of natural language understanding. To address the above issues, a micro-topic scheme(MTS) representation is proposed based on functional grammar theory, and the corresponding corpus resources(i.e., CDTC) are constructed. Our preliminary evaluation justifies the appropriateness of the MTS for Chinese discourse analysis and the usefulness of our CDTC.

show abstract

Section: Identifying Entities Of Mtsmentioning

confidence: 99%

Building a Chinese discourse topic corpus with a micro-topic scheme based on theme-rheme theory

Zhou

2017

Big Data Anal

View full text Add to dashboard Cite

show abstract

“…Note that along the path from a given word to the root of a syntactic tree, the first/last verb is called its low/high support verb, respectively. This notion is widely adopted in the field (Toutanova et al, 2005;Xue, 2006;Jiang & Ng, 2006). 5 In this work, we extend it to both nouns and prepositions.…”

Section: Feature Elementmentioning

confidence: 99%

“…Given n candidate feature templates, the algorithm by Ding and Chang (2008) requires O(n 2 ) time to execute a training/test routine, whereas the one by Jiang and Ng (2006) requires O(n) time, assuming that the initial set of feature templates is "good" enough and the others can be handled in a strictly incremental way. The time complexity of our algorithm can also be analyzed in terms of the execution time of the training-and-test routine scr(M (.…”

Section: Feature Template Selectionmentioning

confidence: 99%

Integrative Semantic Dependency Parsing via Efficient Large-scale Feature Selection

Zhao¹,

Zhang²,

Kit³

2013

jair

View full text Add to dashboard Cite

Semantic parsing, i.e., the automatic derivation of meaning representation such as an instantiated predicate-argument structure for a sentence, plays a critical role in deep processing of natural language. Unlike all other top systems of semantic dependency parsing that have to rely on a pipeline framework to chain up a series of submodels each specialized for a specific subtask, the one presented in this article integrates everything into one model, in hopes of achieving desirable integrity and practicality for real applications while maintaining a competitive performance. This integrative approach tackles semantic parsing as a word pair classification problem using a maximum entropy classifier. We leverage adaptive pruning of argument candidates and large-scale feature selection engineering to allow the largest feature space ever in use so far in this field, it achieves a state-of-the-art performance on the evaluation data set for CoNLL-2008 shared task, on top of all but one top pipeline system, confirming its feasibility and effectiveness.

show abstract

“…Gildea and Jurafsky (2002) presented an early FrameNet-based SRL system that targeted both verbal and nominal predicates. Jiang and Ng (2006) and Liu and Ng (2007) have tested the hypothesis that methodologies and representations used in PropBank SRL (Pradhan et al, 2005) can be ported to the task of NomBank SRL. These studies report argument F 1 scores of 0.6914 and 0.7283, respectively.…”

Section: Related Workmentioning

confidence: 99%

“…In the NomBank corpus, only markable instances have been annotated. Previous evaluations (e.g., those by Jiang and Ng (2006) and Liu and Ng (2007)) have been based on markable instances, which constitute 57% of all instances of nominals from the NomBank lexicon. In order to use nominal SRL systems for downstream processing, it is important to develop and evaluate techniques that can handle markable as well as unmarkable nominal instances.…”

Section: Introductionmentioning

confidence: 99%

The role of implicit argumentation in nominal SRL

Gerber

Chai

Meyers

2009

Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Com

View full text Add to dashboard Cite

Nominals frequently surface without overtly expressed arguments. In order to measure the potential benefit of nominal SRL for downstream processes, such nominals must be accounted for. In this paper, we show that a state-of-the-art nominal SRL system with an overall argument F 1 of 0.76 suffers a performance loss of more than 9% when nominals with implicit arguments are included in the evaluation. We then develop a system that takes implicit argumentation into account, improving overall performance by nearly 5%. Our results indicate that the degree of implicit argumentation varies widely across nominals, making automated detection of implicit argumentation an important step for nominal SRL.

show abstract

Semantic Role Labeling of NomBank

Cited by 30 publications

References 11 publications

Building a Chinese discourse topic corpus with a micro-topic scheme based on theme-rheme theory

Building a Chinese discourse topic corpus with a micro-topic scheme based on theme-rheme theory

Integrative Semantic Dependency Parsing via Efficient Large-scale Feature Selection

The role of implicit argumentation in nominal SRL

Contact Info

Product

Resources

About