LTH: Semantic Structure Extraction using Nonprojective Dependency Trees
نویسندگان
چکیده
We describe our contribution to the SemEval task on Frame-Semantic Structure Extraction. Unlike most previous systems described in literature, ours is based on dependency syntax. We also describe a fully automatic method to add words to the FrameNet lexical database, which gives an improvement in the recall of frame detection.
منابع مشابه
Probabilistic Models of Nonprojective Dependency Trees
A notable gap in research on statistical dependency parsing is a proper conditional probability distribution over nonprojective dependency trees for a given sentence. We exploit the Matrix Tree Theorem (Tutte, 1984) to derive an algorithm that efficiently sums the scores of all nonprojective trees in a sentence, permitting the definition of a conditional log-linear model over trees. While discr...
متن کاملExtended Constituent-to-Dependency Conversion for English
We describe a new method to convert English constituent trees using the Penn Treebank annotation style into dependency trees. The new format was inspired by annotation practices used in other dependency treebanks with the intention to produce a better interface to further semantic processing than existing methods. In particular, we used a richer set of edge labels and introduced links to handle...
متن کاملHyperedge Replacement and Nonprojective Dependency Structures
Synchronous Hyperedge Replacement Graph Grammars (SHRG) can be used to translate between strings and graphs. In this paper, we study the capacity of these grammars to create non-projective dependency graphs. As an example, we use languages that contain cross serial dependencies. Lexicalized hyperedge replacement grammars can derive string languages (as path graphs) that contain an arbitrary num...
متن کاملAnnotating a parallel monolingual treebank with semantic similarity relations
We describe an ongoing effort to build a large-scale parallel and comparable monolingual treebank for Dutch of 1 million words, where nodes of dependency trees are aligned and labeled according to a limited set of semantic similarity relations. We address alignment of sentences and dependency trees, both manual and automatic. We introduce new annotation tools, present results from pilot experim...
متن کاملAnnotating a parallel monolingual treebank with semantic similarity relations
We describe an ongoing effort to build a large-scale parallel/comparable monolingual treebank for Dutch of 1 million words, where nodes of dependency trees are aligned and labeled according to a limited set of semantic similarity relations. We address alignment of sentences and dependency trees, both manual and automatic. We introduce new annotation tools, present results from pilot experiments...
متن کامل