We propose Bilingual Tree Kernels (BTKs) to capture the structural similarities across a pair of syntactic translational equivalences and apply BTKs to subtree alignment along with some plain features.

Our study reveals that the structural features embedded in a bilingual parse tree pair are very effective for subtree alignment and the bilingual tree kernels can well capture such features.

2.1 Independent Bilingual Tree Kernel (iBTK)

In order to compute the dot product of the feature vectors in the exponentially high dimensional feature space, we introduce the tree kernel functions as follows:

The iBTK is defined as a composite kernel consisting of a source tree kernel and a target tree kernel which measures the source and the target structural similarity respectively.

Alternatively, convolution parse tree kernels (Collins and Duffy, 2001), which implicitly explore the tree structure information, have been successfully applied in many NLP tasks, such as Semantic parsing (Moschitti, 2004) and Relation Extraction (Zhang et al.

In multilingual tasks such as machine translation, tree kernels are seldom applied.

In this paper, we propose Bilingual Tree Kernels (BTKs) to model the bilingual translational equivalences, in our case, to conduct subtree alignment.

In this paper we propose using tree kernel based approach to automatically mine the syntactic information from the parse trees for discourse analysis, applying kernel function to the tree structures directly.

The experiment shows tree kernel approach is able to give statistical significant improvements over flat syntactic path feature.

We also illustrate that tree kernel approach covers more structure information than the production rules, which allows tree kernel to further incorporate information from a higher dimension space for possible better discrimination.

In this paper we propose using tree kernel based method to automatically mine the syntactic

The experiment shows that tree kernel is able to effectively incorporate syntactic structural information and produce statistical significant improvements over flat syntactic path feature for the recognition of both explicit and implicit relation in Penn Discourse Treebank (PDTB; Prasad et al., 2008).

We also illustrate that tree kernel approach covers more structure information than the production rules, which allows tree kernel to further work on a higher dimensional space for possible better discrimination.

Tree Kernel based Approach in NLP.

While the feature based approach may not be able to fully utilize the syntactic information in a parse tree, an alternative to the feature-based methods, tree kernel methods (Haussler, 1999) have been proposed to implicitly explore features in a high dimensional space by employing a kernel function to calculate the similarity between two objects directly.

Other sub-trees beyond 2-level (e. g. Tf- 7}) are only captured in the tree kernel, which allows tree kernel to further leverage on information from higher dimension space for possible better discrimination.

In fact, lexical information is highly affected by data-sparseness, thus tree kernels combined with semantic information created from additional resources should provide a way to obtain a more robust system.

The idea is to (i) learn semantic similarity between words on the pivot corpus and (ii) use tree kernels embedding such a similarity to learn a RE system on the source, which allows to generalize to the new target domain.

We encode word clusters or similarity in tree kernels , which, in turn, produce spaces of tree fragments.

Rather than only matching the surface string of words, lexical similarity enables soft matches between similar words in convolution tree kernels .

In the empirical evaluation on Automatic Content Extraction (ACE) data, we evaluate the impact of convolution tree kernels embedding lexical semantic similarities.

Semantic syntactic tree kernels have been previously used for question classification (Bloehdorn and Moschitti, 2007a; Bloehdorn and Moschitti, 2007b; Croce et al., 2011).

Thus, we present a novel application of semantic syntactic tree kernels and Brown clusters for domain adaptation of tree-kernel based relation extraction.

Commonly used kernels in NLP are string kernels (Lodhi et al., 2002) and tree kernels (Moschitti, 2006; Moschitti, 2008).

Figure l: Syntactic tree kernel (STK).

Syntactic tree kernels (Collins and Duffy, 2001) compute the similarity between two trees T1 and T2 by counting common sub-trees (cf.

Convolution tree kernels are an efficient and effective method for comparing syntactic structures in NLP methods.

However, current kernel methods such as subset tree kernel and partial tree kernel understate the similarity of very similar tree structures.

2.1 Syntax-based Tree Kernels

Syntax-based tree kernels quantify the similarity between two constituent parses by counting their common substructures.

The partial tree kernel (PTK) relaxes the definition of subtrees to allow partial production rule

Convolution kernels over syntactic trees ( tree kernels ) offer a potential solution to this problem by providing relatively efficient algorithms for computing similarities between entire discrete structures.

However, conventional tree kernels are sensitive to pattern variations.

For example, two trees in Figure 1(a) sharing the same structure except for one terminal symbol are deemed at most 67% similar by the conventional tree kernel (PTK) (Moschitti, 2006).

Compared with the previous tree kernels , our descending path kernel has the following advantages: l) the substructures are simplified so that they are more likely to be shared among trees, and therefore the sparse feature issues of previous kernels could be alleviated by this representation; 2) soft matching between two similar structures (e.g., NP—>DT JJ NN versus NP—>DT NN) have high similarity without reference to any corpus or grammar rules;

Tree kernel is an effective technique for relation extraction.

In this paper, we propose a new tree kernel, called feature-enriched tree kernel (F TK ), which can enhance the traditional tree kernel by: 1) refining the syntactic tree representation by annotating each tree node with a set of discriminant features; and 2) proposing a new tree kernel which can better measure the syntactic tree similarity by taking all features into consideration.

Experimental results show that our method can achieve a 5.4% F—measure improvement over the traditional convolution tree kernel .

An effective technique is the tree kernel (Zelenko et al., 2003; Zhou et al., 2007; Zhang et al., 2006; Qian et al., 2008), which can exploit syntactic parse tree information for relation extraction.

Then the similarity between two trees are computed using a tree kernel, e. g., the convolution tree kernel proposed by Collins and Duffy (2001).

Unfortunately, one main shortcoming of the traditional tree kernel is that the syntactic tree representation usually cannot accurately capture the

Then, we design advanced similarity functions between such structures, i.e., semantic tree kernel functions, for exploiting distributional and grammatical information in Support Vector Machines.

available; and (ii) in 76% of the errors only 2 or less argument heads are included in the extracted tree, therefore tree kernels cannot exploit enough lexical information to disambiguate verb senses.

the capability of tree kernels to implicitly trigger useful linguistic inductions for complex semantic tasks.

Recently, DMs have been also proposed in integrated syntacticsemantic structures that feed advanced learning functions, such as the semantic tree kernels discussed in (Bloehdorn and Moschitti, 2007a; Bloehdorn and Moschitti, 2007b; Mehdad et al., 2010; Croce et al., 2011).

In particular, we design new models for verb classification by adopting algorithms for structural similarity, known as Smoothed Partial Tree Kernels (SPTKs) (Croce et al., 2011).

3.2 Tree Kernels driven by Semantic Similarity To our knowledge, two main types of tree kernels exploit lexical similarity: the syntactic semantic tree kernel defined in (Bloehdom and Moschitti, 2007a) applied to constituency trees and the smoothed partial tree kernels (SPTKs) defined in (Croce et al., 2011), which generalizes the former.

The A function determines the richness of the kernel space and thus induces different tree kernels, for example, the syntactic tree kernel (STK) (Collins and Duffy, 2002) or the partial tree kernel (PTK) (Moschitti, 2006).

Here, we apply tree pruning to reduce the computational complexity of tree kernels as it is proportional to the number of nodes in the input trees.

To encode dependency structure information in a tree (so that we can use it in tree kernels ), we use (i) lexemes as nodes of our tree, (ii) their dependencies as edges between the nodes and (iii) the dependency labels, e. g., grammatical functions (GR), and POS-Tags, again as tree nodes.

We rely on the tree kernel technology to automatically extract and learn features with better generalization power than bag-of-words.

In particular, we define an efficient tree kernel derived from the Partial Tree Kernel , (Moschitti, 2006a), suitable for encoding structural representation of comments into Support Vector Machines (SVMs).

These trees are input to tree kernel functions for generating structural features.

The latter are automatically generated and learned by SVMs with expressive tree kernels .

In other words, the tree fragment: [S [negative—VP [negative—V [destroy] ] [PRODUCT-NP [PRODUCT-N [xoom] ] ] ] is a strong feature (induced by tree kernels ) to help the classifier to discriminate such hard cases.

We introduce a novel tree representation, and use it to train predictive models with tree kernels using support vector machines.

Our semantic frame-based model benefits from tree kernel learning using support vector machines.

To analyze which were the best performing features within sectors, we extracted the best performing frame fragments for the polarity task using a tree kernel feature engineering method presented in Pighin and Moschitti (2009).

3'SVM-light: http://svmlight.joachims.org and Tree Kernels in SVM-light: http://disi.unitn.it/moschitti/Tree-Kernel.htm.

The second is a tree representation that encodes semantic frame features, and depends on tree kernel measures for support vector machine classification.

The tree kernel (Moschitti, 2006; Collins and Duffy, 2002) is a function of tree similarity, based on common substructures (tree fragments).

the domain context tree kernel contributed to produce more precise outputs.

Our composite kernel consists of a history sequence and a domain context tree kernels , both of which are composed based on similar textual units in Wikipedia articles to a given dialog context.

Our composite kernel consists of two different kernels: a history sequence kernel and a domain context tree kernel .

3.2 Domain Context Tree Kernel

Since this constructed tree structure represents semantic, discourse, and structural information extracted from the similar Wikipedia paragraphs to each given instance, we can explore these more enriched features to build the topic tracking model using a subset tree kernel (Collins and Duffy, 2002) which computes the similarity between each pair of trees in the feature space as follows:

Many of them focus on using tree kernels to learn parse tree structure related features (Collins and Duffy, 2001; Culotta and Sorensen, 2004; Bunescu and Mooney, 2005).

For example, by combining tree kernels and convolution string kernels, (Zhang et al., 2006) achieved the state of the art performance on ACE data (ACE, 2004).

We compare our approaches to three state-of-the-art approaches including SVM with convolution tree kernels (Collins and Duffy, 2001), linear regression and SVM with linear kernels (Scholkopf and Smola, 2002).

To adapt the tree kernel to medical domain, we followed the approach in (Nguyen et al., 2009) to take the syntactic structures into consideration.

We also added the argument types as features to the tree kernel .

In this field, the tree kernel based method commonly uses the parse tree to capture the structure information (Zelenko et al., 2003; Culotta and Sorensen, 2004).

(2012) proposed a convolution tree kernel .

(2010) employed a model, combining both the feature based and the tree kernel based methods.

(2008; 2010) also pointed out that, due to the inaccuracy of Chinese word segmentation and parsing, the tree kernel based approach is inappropriate for Chinese relation extraction.

2.2 Tree kernels

Tree Kernel methods have gained popularity in the last decade for capturing syntactic information in the structure of parse trees (Collins and Duffy, 2002; Moschitti, 2006).

(2013) have attempted to provide formulations to incorporate semantics into tree kernels through the use of distributional word vectors at the individual word-nodes.

A number of metrics have been proposed to measure the similarity between two labeled trees, e. g., Tree Edit Distance (Tai, 1979) and Tree Kernels (Collins and Duffy, 2001; Moschitti and Basili, 2006).

Tree kernels (TKs) provide an effective way to integrate arbitrary tree structures in kernel-based machine learning algorithms like SVMs.

the nuclearity and the relations, in order to allow the tree kernel to give partial credit to subtrees that differ in labels but match in their skeletons.

Counting the number of matched dependencies is essentially a simplified tree kernel for QA (e.g., see (Moschitti et al., 2007)) matching only trees of depth 2.

Experiments with full dependency tree kernels based on several variants of the convolution kernels of Collins and Duffy (2001) did not yield improvements.

We conjecture that the mistakes of the syntactic parser may be amplified in tree kernels , which consider an exponential number of sub-trees.