Dependency parsing schemata | In order to make the formalism general enough to include these parsers, we define items in terms of sets of partial dependency trees as shown in Figure 1. |
Dependency parsing schemata | Such spans cannot be represented by a single dependency tree . |
Dependency parsing schemata | Therefore, our formalism allows items to be sets of forests of partial dependency trees , instead of sets of trees. |
Introduction | Figure l: The dependency tree for sentence the boy will find it interesting |
Introduction | 1.2 Dependency Trees |
Introduction | Dependency trees reveal long-distance relations between words. |
String-to-Dependency Translation | In one kind, we keep dependency trees with a sub-root, where all the children of the sub-root are complete. |
String-to-Dependency Translation | Figure 5: A dependency tree with flexible combination |
String-to-Dependency Translation | Figure 1 shows a traditional dependency tree . |
Dependency Parsing Model | Given a sentence X = (x1, ..., sun) (cc,- denotes each word in the sentence), we are interested in computing a directed dependency tree , Y, over X. |
Dependency Parsing Model | We assume that a directed dependency tree Y consists of ordered pairs (sci —> any) of words in X such that each word appears in at least one pair and each word has in-degree at most one. |
Dependency Parsing Model | Dependency trees are assumed to be projective here, which means that if there is an arc (cc,- —> 553-), then :0,- is an ancestor of all the words |
Experimental Results | For experiment on English, we used the English Penn Treebank (PTB) (Marcus et al., 1993) and the constituency structures were converted to dependency trees using the same rules as (Yamada and Matsumoto, 2003). |
Introduction | Figure l: A dependency tree |
Semi-supervised Convex Training for Structured SVM | As mentioned in Section 3, a dependency tree Yj is represented as an adjacency matrix. |
Semi-supervised Convex Training for Structured SVM | Thus we need to enforce some constraints in the adjacency matrix to make sure that each Yj satisfies the dependency tree constraints. |
Supervised Structured Large Margin Training | 1We assume all the dependency trees are projective in our work (just as some other researchers do), although in the real word, most languages are non-projective. |
Supervised Structured Large Margin Training | We represent a dependency tree as a k x k adjacency matrix. |
Abstract | We add syntax to this process with a cohesion constraint based on a dependency tree for the source sentence. |
Cohesive Decoding | The decoder stores the flat sentence in the original sentence data structure, and the head-encoded dependency tree in an attached tree data structure. |
Cohesive Phrasal Output | Next, we introduce our source dependency tree T. Each source token e,- is also a node in T. We define T(ei) to be the subtree of T rooted at 61-. |
Cohesive Phrasal Output | spanS 6-, T, am 2 min a -, max ak, ( z 1 > {j|€j€T(€i)} j {k|€k€T(€i)} Consider the simple phrasal translation shown in Figure 1 along with a dependency tree for the English source. |
Conclusion | This algorithm was used to implement a soft cohesion constraint for the Moses decoder, based on a source-side dependency tree . |
Experiments | Since we require source dependency trees , all experiments test English to French translation. |
Experiments | English dependency trees are provided by Minipar (Lin, 1994). |
Evaluation Methodology | For the protein pair IL-8 and CXCR1 in Figure 4, a dependency parser outputs a dependency tree shown in Figure 1. |
Evaluation Methodology | From this dependency tree , we can extract a dependency path shown in Figure 5, which appears to be a strong clue in knowing that these proteins are mentioned as interacting. |
Evaluation Methodology | CoNLL The dependency tree format used in the 2006 and 2007 CoNLL shared tasks on dependency parsing. |
Syntactic Parsers and Their Representations | Figure 1 shows a dependency tree for the sentence “IL-8 recognizes and activates CXCRl.” An advantage of dependency parsing is that dependency trees are a reasonable approximation of the semantics of sentences, and are readily usable in NLP applications. |
Syntactic Parsers and Their Representations | Figure l: CoNLL-X dependency tree |
Introduction | The analytical layer roughly corresponds to the surface syntax of the sentence; the annotation is a single-rooted dependency tree with labeled nodes. |
Introduction | Again, the annotation is a dependency tree with labeled nodes (Hajicova 1998). |
Phenomena and Requirements | The representation of the tectogrammatical annotation of a sentence is a rooted dependency tree . |