We present a PropBank semantic role labeling system for English that is integrated with a dependency parser. To tackle the problem of joint syntactic–semantic analysis, the system relies on a syntactic and a semantic subcomponent. The syntactic model is a projective parser using pseudo-projective transformations, and the semantic model uses global inference mechanisms on top of a pipeline of classifiers. The complete syntactic–semantic output is selected from a candidate pool generated by the subsystems. We evaluate the system on the CoNLL-2005 test sets using segment-based and dependency-based metrics. Using the segment-based CoNLL-2005 metric, our system achieves a near state-of-the-art F1 figure of 77.97 on the WSJ+Brown test set, or 78.84 if punctuation is treated consistently. Using a dependency-based metric, the F1 figure of our system is 84.29 on the test set from CoNLL-2008. Our system is the first dependency-based semantic role labeler for PropBank that rivals constituent-based systems in terms of performance. 1

Almost all automatic semantic role labeling (SRL) systems rely on a preliminary parsing step that derives a syntactic structure from the sentence being analyzed. This makes the choice of syntactic representation an essential design decision. In this paper, we study the influence of syntactic representation on the performance of SRL systems. Specifically, we compare constituent-based and dependencybased representations for SRL of English in the FrameNet paradigm. Contrary to previous claims, our results demonstrate that the systems based on dependencies perform roughly as well as those based on constituents: For the argument classification task, dependencybased systems perform slightly higher on average, while the opposite holds for the argument identification task. This is remarkable because dependency parsers are still in their infancy while constituent parsing is more mature. Furthermore, the results show that dependency-based semantic role classifiers rely less on lexicalized features, which makes them more robust to domain changes and makes them learn more efficiently with respect to the amount of training data.

This paper contributes a formalization of frame-semantic parsing as a structure prediction problem and describes an implemented parser that transforms an English sentence into a frame-semantic representation. It finds words that evoke FrameNet frames, selects frames for them, and locates the arguments for each frame. The system uses two featurebased, discriminative probabilistic (log-linear) models, one with latent variables to permit disambiguation of new predicate words. The parser is demonstrated to significantly outperform previously published results. 1

Supervised semantic role labeling (SRL) systems are generally claimed to have accuracies in the range of 80 % and higher (Erk and Padó, 2006). These numbers, though, are the result of highly-restricted evaluations, i.e., typically evaluating on hand-picked lemmas for which training data is available. In this paper we consider performance of such systems when we evaluate at the document level rather than on the lemma level. While it is wellknown that coverage gaps exist in the resources available for training supervised SRL systems, what we have been lacking until now is an understanding of the precise nature of this coverage problem and its impact on the performance of SRL systems. We present a typology of five different types of coverage gaps in FrameNet. We then analyze the impact of the coverage gaps on performance of a supervised semantic role labeling system on full texts, showing an average oracle upper bound of 46.8%.

We address the question of which syntactic representation is best suited for role-semantic analysis of English in the FrameNet paradigm. We compare systems based on dependencies and constituents, and a dependency syntax with a rich set of grammatical functions with one with a smaller set. Our experiments show that dependency-based and constituent-based analyzers give roughly equivalent performance, and that a richer set of functions has a positive influence on argument classification for verbs.

In this paper, we describe the SemEval-2010 shared task on “Linking Events and Their Participants in Discourse”. This task is a variant of the classical semantic role labelling task. The novel aspect is that we focus on linking local semantic argument structures across sentence boundaries. Specifically, the task aims at linking locally uninstantiated roles to their coreferents in the wider discourse context (if such co-referents exist). This task is potentially beneficial for a number of NLP applications and we hope that it will not only attract researchers from the semantic role labelling community but also from co-reference resolution and information extraction. 1

An elaboration on (Das et al., 2010), this report formalizes frame-semantic parsing as a structure prediction problem and describes an implemented parser that transforms an English sentence into a frame-semantic representation. SEMAFOR 1.0 finds words that evoke FrameNet frames, selects frames for them, and locates the arguments for each frame. The system uses two feature-based, discriminative probabilistic (log-linear) models, one with latent variables to permit disambiguation of new predicate words. The parser is demonstrated to significantly outperform previously published results and is released for public use.

The development of systems that extract a frame representation of text can lead to deeper semantics being used in natural language processing. We present the development of our system for extracting frames from text. Our system is trained on the FrameNet data and tested on the SemEval 2007: Task 19 Frame Extraction Task data. We use machine learning for labeling frames and frame elements, resulting in system with a good performance. We provide a detailed analysis of our methods, challenges, and results. We also provide enough details and analysis to allow other researchers to develop similar systems.

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.

We present novel methods to construct compact natural language lexicons within a graphbased semi-supervised learning framework, an attractive platform suited for propagating soft labels onto new natural language types from seed data. To achieve compactness, we induce sparse measures at graph vertices by incorporating sparsity-inducing penalties in Gaussian and entropic pairwise Markov networks constructed from labeled and unlabeled data. Sparse measures are desirable for high-dimensional multi-class learning problems such as the induction of labels on natural language types, which typically associate with only a few labels. Compared to standard graph-based learning methods, for two lexicon expansion problems, our approach produces significantly smaller lexicons and obtains better predictive performance. 1