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.

We perform multi-document summarization by generating compressed versions of source sentences as summary candidates and using weighted features of these candidates to construct summaries. We combine a parse-and-trim approach with a novel technique for producing multiple alternative compressions for source sentences. In addition, we use a novel method for tuning the feature weights that maximizes the change in the ROUGE-2 score (∆ROUGE) between the already existing summary state and the new state that results from the addition of the candidate under consideration. We also describe experiments using a new paraphrase-based feature for redundancy checking. Finally, we present the results of our DUC2007 submissions and some ideas for future work. 1

In this paper we present a method for unsupervised semantic role induction which we formalize as a graph partitioning problem. Argument instances of a verb are represented as vertices in a graph whose edge weights quantify their role-semantic similarity. Graph partitioning is realized with an algorithm that iteratively assigns vertices to clusters based on the cluster assignments of neighboring vertices. Our method is algorithmically and conceptually simple, especially with respect to how problem-specific knowledge is incorporated into the model. Experimental results on the CoNLL 2008 benchmark dataset demonstrate that our model is competitive with other unsupervised approaches in terms of F1 whilst attaining significantly higher cluster purity.

Abstract. In this paper we introduce a system that automatically summarizes multiple biomedical documents relevant to a question. The system extracts biomedical and general concepts by utilizing concept-level knowledge from domain-specific and domain-independent sources. Semantic role labeling, semantic subgraph-based sentence selection and automatic post-editing are involved in the process of finding the information need. Due to the absence of expert-written summaries of biomedical documents, we propose an approximate evaluation by taking MEDLINE abstracts as expert-written summaries. Evaluation results indicate that our system does help in answering questions and the automatically generated summaries are comparable to abstracts of biomedical articles, as evaluated using the ROUGE measure. 1

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:

Abstract not found

Abstract not found

This paper presents a novel approach to semantic role annotation implementing an entailmentbased view of the concept of semantic role. I propose to represent arguments of predicates with grammatically relevant primitive properties entailed by the semantics of predicates. Such meaning components generalise over a range of semantic relations which humans tend to express systematically through language. In a preliminary study, I show that we can model linguistic knowledge at a general, principled syntax-semantics interface by incorporating a layer of skeletal, entailment-based representation of word meaning in large-scale corpus annotation. 1

In this paper we describe an unsupervised method for semantic role induction which holds promise for relieving the data acquisition bottleneck associated with supervised role labelers. We present an algorithm that iteratively splits and merges clusters representing semantic roles, thereby leading from an initial clustering to a final clustering of better quality. The method is simple, surprisingly effective, and allows to integrate linguistic knowledge transparently. By combining role induction with a rule-based component for argument identification we obtain an unsupervised end-to-end semantic role labeling system. Evaluation on the CoNLL 2008 benchmark dataset demonstrates that our method outperforms competitive unsupervised approaches by a wide margin. 1

Large-scale annotated corpora are a prerequisite to developing high-performance semantic role labeling systems. Unfortunately, such corpora are expensive to produce, limited in size, and may not be representative. Our work aims to reduce the annotation effort involved in creating resources for semantic role labeling via semi-supervised learning. The key idea of our approach is to find novel instances for classifier training based on their similarity to manually labeled seed instances. The underlying assumption is that sentences that are similar in their lexical material and syntactic structure are likely to share a frame semantic analysis. We formalize the detection of similar sentences and the projection of role annotations as a graph alignment problem, which we solve exactly using integer linear programming. Experimental results on semantic role labeling show that the automatic annotations produced by our method improve performance over using hand-labeled instances alone. 1.