Developing features has been shown crucial to advancing the state-of-the-art in Semantic Role Labeling (SRL). To improve Chinese SRL, we propose a set of additional features, some of which are designed to better capture structural information. Our system achieves 93.49 Fmeasure, a significant improvement over the best reported performance 92.0. We are further concerned with the effect of parsin...

Constructing a lexical resource for Swedish, where compounding is highly productive, requires a well-structured policy of encoding. This paper presents the treatment and encoding of a certain class of compounds in Swedish FrameNet, and proposes a new approach for the automatic analysis of Swedish compounds, i.e. one that leverages existing FrameNet (Ruppenhofer et al., 2010) and Swedish FrameNe...

This paper provides an exhaustive account of the semantic features and the logical structure of causative active accomplishment verbs of movement. Following the approach of Componential Analysis, and described within the theoretical framework of Role and Reference Grammar, these verbs are arranged into three subgroups according to a number of semantic variables related to their argument structu...

We present a comparison between two systems for establishing syntactic and semantic dependencies: one that performs dependency parsing and semantic role labeling as a single task, and another that performs the two tasks in isolation. The systems are based on local memorybased classifiers predicting syntactic and semantic dependency relations between pairs of words. In a second global phase, the...

When (if ever) a judicial action can be an unconstitutional taking of private property has long been an open question in American constitutional law. Nested within this larger question are a host of detailed issues concerning both substance and procedure. Despite passing references in some cases, and a more direct discussion in one concurring opinion, the Supreme Court of the United States—unti...

In this paper we describe the CoNLL-2004 shared task: semantic role labeling. We introduce the specification and goal of the task, describe the data sets and evaluation methods, and present a general overview of the systems that have contributed to the task, providing comparative description.

In this paper we describe the CoNLL2005 shared task on Semantic Role Labeling. We introduce the specification and goals of the task, describe the data sets and evaluation methods, and present a general overview of the 19 systems that have contributed to the task, providing a comparative description and results.

We propose a novel approach to crosslingual model transfer based on feature representation projection. First, a compact feature representation relevant for the task in question is constructed for either language independently and then the mapping between the two representations is determined using parallel data. The target instance can then be mapped into the source-side feature representation ...

The extremely weak propagation mechanisms of real business cycle (RBC) models are well acknowledged, and some effort has been devoted to improving the models on this dimension. This paper builds on these efforts to provide an explicit explanation of why various existing RBC models do not replicate real world business cycles, and discusses modifications necessary to bring real business cycle the...