The task of Semantic Role Labeling (SRL) is often divided into two sub-tasks: verb argument identification, and argument classification. Current SRL algorithms show lower results on the identification sub-task. Moreover, most SRL algorithms are supervised, relying on large amounts of manually created data. In this paper we present an unsupervised algorithm for identifying verb arguments, where the only type of annotation required is POS tagging. The algorithm makes use of a fully unsupervised syntactic parser, using its output in order to detect clauses and gather candidate argument collocation statistics. We evaluate our algorithm on PropBank10, achieving a precision of 56%, as opposed to 47 % of a strong baseline. We also obtain an 8 % increase in precision for a Spanish corpus. This is the first paper that tackles unsupervised verb argument identification without using manually encoded rules or extensive lexical or syntactic resources. 1

This paper describes a system for the CoNLL-2005 Shared Task on Semantic Role Labeling. We trained two parsers with the training corpus in which the semantic argument information is attached to the constituent labels, we then used the resulting parse trees as the input of the pipelined SRL system. We present our results of combining the output of various SRL systems using different parsers. 1

Parse-tree paths are commonly used to incorporate information from syntactic parses into NLP systems. These systems typically treat the paths as atomic (or nearly atomic) features; these features are quite sparse due to the immense variety of syntactic expression. In this paper, we propose a general method for learning how to iteratively simplify a sentence, thus decomposing complicated syntax into small, easy-to-process pieces. Our method applies a series of hand-written transformation rules corresponding to basic syntactic patterns — for example, one rule “depassivizes ” a sentence. The model is parameterized by learned weights specifying preferences for some rules over others. After applying all possible transformations to a sentence, we are left with a set of candidate simplified sentences. We apply our simplification system to semantic role labeling (SRL). As we do not have labeled examples of correct simplifications, we use labeled training data for the SRL task to jointly learn both the weights of the simplification model and of an SRL model, treating the simplification as a hidden variable. By extracting and labeling simplified sentences, this combined simplification/SRL system better generalizes across syntactic variation. It achieves a statistically significant 1.2 % F1 measure increase over a strong baseline on the Conll-2005 SRL task, attaining near-state-of-the-art performance. 1

In this paper, we propose a method that exploits full parsing information by representing it as features of argument classification models and as constraints in integer linear learning programs. In addition, to take advantage of SVM-based and Maximum Entropy-based argument classification models, we incorporate their scoring matrices, and use the combined matrix in the above-mentioned integer linear programs. The experimental results show that full parsing information not only increases the F-score of argument classification models by 0.7%, but also effectively removes all labeling inconsistencies, which increases the F-score by 0.64%. The ensemble of SVM and ME also boosts the F-score by 0.77%. Our system achieves an F-score of 76.53 % in the development set and 76.38 % in Test WSJ. 1

We approached the temporal relation identification tasks of TempEval 2007 as pair-wise classification tasks. We introduced a variety of syntactically and semantically motivated features, including temporal-logicbased features derived from running our Task B system on the Task A and C data. We trained support vector machine models and achieved the second highest accuracies on the tasks: 61 % on Task A, 75 % on Task B and 54 % on Task C. 1

Recent natural language learning research has shown that structural kernels can be effectively used to induce accurate models of linguistic phenomena.

We present a series of empirical studies aimed at illuminating more precisely the likely contribution of semantic roles in improving statistical machine translation accuracy. The experiments reported study several aspects key to success: (1) the frequencies of types of SMT errors where semantic parsing and role labeling could help, and (2) if and where semantic roles offer more accurate guidance to SMT than merely syntactic annotation, and (3) the potential quantitative impact of realistic semantic role guidance to SMT systems, in terms of BLEU and METEOR scores. 1

In this paper, we construct a biomedical semantic role labeling (SRL) system that can be used to facilitate relation extraction. First, we construct a proposition bank on top of the popular biomedical GENIA treebank following the PropBank annotation scheme. We only annotate the predicate-argument structures (PAS’s) of thirty frequently used biomedical predicates and their corresponding arguments. Second, we use our proposition bank to train a biomedical SRL system, which uses a maximum entropy (ME) model. Thirdly, we automatically generate argument-type templates which can be used to improve classification of biomedical argument types. Our experimental results show that a newswire SRL system that achieves an F-score of 86.29 % in the newswire domain can maintain an F-score of 64.64% when ported to the biomedical domain. By using our annotated biomedical corpus, we can increase that F-score by 22.9%. Adding automatically generated template features further increases overall F-score by 0.47 % and adjunct arguments (AM) Fscore by 1.57%, respectively. 1

This article describes how semantic role resources can be exploited for preposition disambiguation. The main resources include the semantic role annotations provided by the Penn Treebank and FrameNet tagged corpora. The resources also include the assertions contained in the Factotum knowledge base, as well as information from Cyc and Conceptual Graphs. A common inventory is derived from these in support of definition analysis, which is the motivation for this work. The disambiguation concentrates on relations indicated by prepositional phrases, and is framed as word-sense disambiguation for the preposition in question. A new type of feature for word-sense disambiguation is introduced, using WordNet hypernyms as collocations rather than just words. Various experiments over the Penn Treebank and FrameNet data are presented, including prepositions classified separately versus together, and illustrating the effects of filtering. Similar experimentation is done over the Factotum data, including a method for inferring likely preposition usage from corpora, as knowledge bases do not generally indicate how relationships are expressed in English (in contrast to the explicit annotations on this in the Penn Treebank and FrameNet). Other experiments are included with the FrameNet data mapped into the common relation inventory developed for definition analysis, illustrating how preposition disambiguation might be applied in lexical acquisition. 1.

Analogical reasoning is crucial to robust and flexible highlevel cognition. However, progress on computational models of analogy has been impeded by our inability to quickly and accurately collect large numbers (100+) of semantically annotated texts. The Story Workbench is a tool that facilitates such annotation by using natural language processing techniques to make a guess at the annotation, followed by approval, correction, and elaboration of that guess by a human annotator. Central to this approach is the use of a sophisticated graphical user interface that can guide even an untrained annotator through the annotation process. I describe five desiderata that govern the design of the Story Workbench, and demonstrate how each principle was fulfilled in the current implementation. The Story Workbench enables numerous experiments that previously were prohibitively laborious, of which I describe three currently underway in my lab. Analogical reasoning underlies many important cognitive processes, including learning, categorization, planning, and natural language understanding (Gentner, Holyoak, and Kokinov 2001). It is crucial to robust and flexible highlevel cognition. Despite great strides early in the computational understanding of analogical reasoning (Gick and