This paper focuses on semantic role labeling using automatically-generated syntactic information. A simple and robust strategy for system combination is presented, which allows to partially recover from input parsing errors and to significantly boost results of individual systems. This combination scheme is also very flexible since the individual systems are not required to provide any information other than their solution. Extensive experimental evaluation in the CoNLL-2005 shared task framework supports our previous claims. The proposed architecture outperforms the best results reported in that evaluation exercise.

Wikipedia provides a semantic network for computing semantic relatedness in a more structured fashion than a search engine and with more coverage than WordNet. We present experiments on using Wikipedia for computing semantic relatedness and compare it to WordNet on various benchmarking datasets. Existing relatedness measures perform better using Wikipedia than a baseline given by Google counts, and we show that Wikipedia outperforms WordNet on some datasets. We also address the question whether and how Wikipedia can be integrated into NLP applications as a knowledge base. Including Wikipedia improves the performance of a machine learning based coreference resolution system, indicating that it represents a valuable resource for NLP applications. Finally, we show that our method can be easily used for languages other than English by computing semantic relatedness for a German dataset.

reproduced, without authorization, under the conditions for Fair Dealing. Therefore, limited reproduction of this work for the purposes of private study, research, criticism, review and news reporting is likely to be in accordance with the law, particularly if cited appropriately. APPROVAL Name: Degree:

This paper explores Chinese semantic role labeling (SRL) for nominal predicates. Besides those widely used features in verbal SRL, various nominal SRL-specific features are first included. Then, we improve the performance of nominal SRL by integrating useful features derived from a state-of-the-art verbal SRL system. Finally, we address the issue of automatic predicate recognition, which is essential for a nominal SRL system. Evaluation on Chinese NomBank shows that our research in integrating various features derived from verbal SRL significantly improves the performance. It also shows that our nominal SRL system much outperforms the state-of-the-art ones. 1.

In this paper, we employ the centering theory in pronoun resolution from the semantic perspective. First, diverse semantic role features with regard to different predicates in a sentence are explored. Moreover, given a pronominal anaphor, its relative ranking among all the pronouns in a sentence, according to relevant semantic role information and its surface position, is incorporated. In particular, the use of both the semantic role features and the relative pronominal ranking feature in pronoun resolution is guided by extending the centering theory from the grammatical level to the semantic level in tracking the local discourse focus. Finally, detailed pronominal subcategory features are incorporated to enhance the discriminative power of both the semantic role features and the relative pronominal ranking feature. Experimental results on the ACE 2003 corpus show that the centeringmotivated features contribute much to pronoun resolution. 1

In this paper, we describe a coreference solver based on the extensive use of lexical features and features extracted from dependency graphs of the sentences. The solver uses Soon et al. (2001)’s classical resolution algorithm based on a pairwise classification of the mentions. We applied this solver to the closed track of the CoNLL 2011 shared task (Pradhan et al., 2011). We carried out a systematic optimization of the feature set using cross-validation that led us to retain 24 features. Using this set, we reached a MUC score of 58.61 on the test set of the shared task. We analyzed the impact of the features on the development set and we show the importance of lexicalization as well as of properties related to dependency links in coreference resolution. 1

Abstract- Automatic semantic annotation based on domain-specific ontologies is a one of the critical issues for the success of the semantic web. Most existing approaches focused on the detection of concepts such as named entities, dates, monetary amounts. This study explores automatic semantic annotation techniques for applications using relation-centric ontologies which represent domain knowledge using a set of concepts with many inter-class relations. We propose a framework to detect event-based concepts and inter-concept relations using semantic role labeling and coreference resolution techniques. We gave an illustration of the processes by a semantic annotation application using CIDOC-CRM as the underlying ontology. Experiments using archives with a large number of image descriptions were conducted. The primitive results show that the accuracy is about 80% or so.

Conventional keyword-based indexing and retrieval techniques for textual documents lack of precision when a long query string is employed in order to discover documents containing a specific “event”, such as “Einstein discovered relativity”. This paper proposes a framework to resolve such a problem. In our proposal, we apply semantic role labeling and coreference techniques in order to parse each sentence within textual documents into three elements: subject, object and predicates. These elements can subsequently be used for indexing and retrieval. Our primitive evaluation experiments have shown that this promising methodology raises the retrieval precision if we compared it to conventional literal termmatching techniques.