• Documents
  • Authors
  • Tables
  • Log in
  • Sign up
  • MetaCart
  • DMCA
  • Donate

CiteSeerX logo

Advanced Search Include Citations
Advanced Search Include Citations | Disambiguate

Ecient convolution kernels for dependency and constituent syntactic trees (2006)

by A Moschitti
Venue:In ECML
Add To MetaCart

Tools

Sorted by:
Results 1 - 10 of 79
Next 10 →

Exploiting syntactic and shallow semantic kernels for question answer classification

by Alessandro Moschitti, Silvia Quarteroni, Roberto Basili, Suresh Manandhar - In Proc. of ACL-07 , 2007
"... We study the impact of syntactic and shallow semantic information in automatic classification of questions and answers and answer re-ranking. We define (a) new tree structures based on shallow semantics encoded in Predicate Argument Structures (PASs) and (b) new kernel functions to exploit the repre ..."
Abstract - Cited by 73 (27 self) - Add to MetaCart
We study the impact of syntactic and shallow semantic information in automatic classification of questions and answers and answer re-ranking. We define (a) new tree structures based on shallow semantics encoded in Predicate Argument Structures (PASs) and (b) new kernel functions to exploit the representational power of such structures with Support Vector Machines. Our experiments suggest that syntactic information helps tasks such as question/answer classification and that shallow semantics gives remarkable contribution when a reliable set of PASs can be extracted, e.g. from answers. 1
(Show Context)

Citation Context

...tic structures in machine learning algorithms is the use of tree kernel (TK) functions (Collins and Duffy, 2002), which have been successfully applied to question classification (Zhang and Lee, 2003; =-=Moschitti, 2006-=-) and other tasks, e.g. relation extraction (Zelenko et al., 2003; Moschitti, 2006). In more complex tasks such as computing the relatedness between questions and answers in answer re-ranking, to our ...

Kernel methods, syntax and semantics for relational text categorization

by Alessandro Moschitti - In: CIKM , 2008
"... Previous work on Natural Language Processing for Information Retrieval has shown the inadequateness of semantic and syntac-tic structures for both document retrieval and categorization. The main reason is the high reliability and effectiveness of language models, which are sufficient to accurately s ..."
Abstract - Cited by 42 (15 self) - Add to MetaCart
Previous work on Natural Language Processing for Information Retrieval has shown the inadequateness of semantic and syntac-tic structures for both document retrieval and categorization. The main reason is the high reliability and effectiveness of language models, which are sufficient to accurately solve such retrieval tasks. However, when the latter involve the computation of relational se-mantics between text fragments simple statistical models may re-sult ineffective. In this paper, we show that syntactic and semantic structures can be used to greatly improve complex categorization tasks such as determining if an answer correctly responds to a ques-tion. Given the high complexity of representing semantic/syntactic structures in learning algorithms, we applied kernel methods along with Support Vector Machines to better exploit the needed rela-tional information. Our experiments on answer classification on Web and TREC data show that our models greatly improve on bag-of-words.
(Show Context)

Citation Context

...s and Kernel Methods have recently been applied to natural language tasks with promising results, e.g. [7, 20, 11, 32, 10, 21, 37, 17, 44]. More specifically, in question classification, tree kernels =-=[43, 25]-=- have shown accuracy comparable to the best models, e.g. [23]. Moreover, [31, 28, 24] have shown that shallow semantic information in the form of predicate argument structures (PASs) [14, 16] improves...

Tree Edit Models for Recognizing Textual Entailments, Paraphrases, and Answers to Questions

by Michael Heilman, Noah A. Smith
"... We describe tree edit models for representing sequences of tree transformations involving complex reordering phenomena and demonstrate that they offer a simple, intuitive, and effective method for modeling pairs of semantically related sentences. To efficiently extract sequences of edits, we employ ..."
Abstract - Cited by 38 (1 self) - Add to MetaCart
We describe tree edit models for representing sequences of tree transformations involving complex reordering phenomena and demonstrate that they offer a simple, intuitive, and effective method for modeling pairs of semantically related sentences. To efficiently extract sequences of edits, we employ a tree kernel as a heuristic in a greedy search routine. We describe a logistic regression model that uses 33 syntactic features of edit sequences to classify the sentence pairs. The approach leads to competitive performance in recognizing textual entailment, paraphrase identification, and answer selection for question answering. 1

oro.open.ac.uk Semantic Sentiment Analysis of Twitter

by Hassan Saif, Yulan He, Harith Alani
"... For guidance on citations see FAQs. ..."
Abstract - Cited by 33 (6 self) - Add to MetaCart
For guidance on citations see FAQs.
(Show Context)

Citation Context

...features. Apart from simply combining various features, they also designed a tree representation of tweets to combine many categories of features in one succinct representation. A partial tree kernel =-=[8]-=- was used to calculate the similarity between two trees. They found that the most important features are those that combine prior polarity of words with their POS tags. All other features only play a ...

A syntactic tree matching approach to finding similar questions in community-based qa services

by Kai Wang, Zhaoyan Ming, Tat-seng Chua - In ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2009 , 2009
"... While traditional question answering (QA) systems tailored to the TREC QA task work relatively well for simple questions, they do not suffice to answer real world questions. The community-based QA systems offer this service well, as they contain large archives of such questions where manually crafte ..."
Abstract - Cited by 33 (4 self) - Add to MetaCart
While traditional question answering (QA) systems tailored to the TREC QA task work relatively well for simple questions, they do not suffice to answer real world questions. The community-based QA systems offer this service well, as they contain large archives of such questions where manually crafted answers are directly available. However, finding similar questions in the QA archive is not trivial. In this paper, we propose a new retrieval framework based on syntactic tree structure to tackle the similar question matching problem. We build a ground-truth set from Yahoo! Answers, and experimental results show that our method outperforms traditional bag-of-word or tree kernel based methods by 8.3 % in mean average precision. It further achieves up to 50% improvement by incorporating semantic features as well as matching of potential answers. Our model does not rely on training, and it is demonstrated to be robust against grammatical errors as well.
(Show Context)

Citation Context

...e parsing tree into several sub-trees and computes the inner product between two vectors of sub-trees. Although there 187have been some successful applications using it, like Question Classification =-=[3,13,19]-=-, the tree kernel-like function has not been directly applied to finding similar questions in the QA archive. Moreover, its matching scheme is too strict to be directly employed to our question matchi...

Fast and Effective Kernels for Relational Learning from Texts

by Alessandro Moschitti, Fabio Massimo Zanzotto
"... In this paper, we define a family of syntactic kernels for automatic relational learning from pairs of natural language sentences. We provide an efficient computation of such models by optimizing the dynamic programming algorithm of the kernel evaluation. Experiments with Support Vector Machines and ..."
Abstract - Cited by 23 (16 self) - Add to MetaCart
In this paper, we define a family of syntactic kernels for automatic relational learning from pairs of natural language sentences. We provide an efficient computation of such models by optimizing the dynamic programming algorithm of the kernel evaluation. Experiments with Support Vector Machines and the above kernels show the effectiveness and efficiency of our approach on two very important natural language tasks, Textual Entailment Recognition and Question Answering. 1.
(Show Context)

Citation Context

...hrases (Bikel et al., 1999), to a higher level of semantic relation search, e.g. relation extraction between Named Entities (Zelenko et al., 2003; Cumby & Roth, 2003) or predicate argument relations (=-=Moschitti, 2006-=-). Lately, the most challenging natural language processing goal has been the extraction of complex relations between entire text fragments. On this subject two main related tasks have captured the at...

UDDI project --- Universal Description, Discovery and Integration

by Stephan Bloehdorn, Ro Moschitti - Advances in Information Retrieval - Proceedings of the 29th European Conference on Information Retrieval (ECIR 2007
"... Abstract. The exploitation of syntactic structures and semantic background knowledge has always been an appealing subject in the context of text retrieval and information management. The usefulness of this kind of information has been shown most prominently in highly specialized tasks, such as class ..."
Abstract - Cited by 19 (6 self) - Add to MetaCart
Abstract. The exploitation of syntactic structures and semantic background knowledge has always been an appealing subject in the context of text retrieval and information management. The usefulness of this kind of information has been shown most prominently in highly specialized tasks, such as classification in Question Answering (QA) scenarios. So far, however, additional syntactic or semantic information has been used only individually. In this paper, we propose a principled approach for jointly exploiting both types of information. We propose a new type of kernel, the Semantic Syntactic Tree Kernel (SSTK), which incorporates linguistic structures, e.g. syntactic dependencies, and semantic background knowledge, e.g. term similarity based on WordNet, to automatically learn question categories in QA. We show the power of this approach in a series of experiments with a well known Question Classification dataset. 1
(Show Context)

Citation Context

...ctor Machines have become a prominent framework for using such a-priori knowledge about the problem domain by means of a specific choice of the employed kernel function. On the oneshand, Tree Kernels =-=[3,4]-=- have been used as a powerful way to encode the syntactic structure of the textual input in the form of parse trees and have shown good results in many natural language applications. On the other hand...

Structural relationships for large-scale learning of answer reranking

by Aliaksei Severyn, Alessandro Moschitti - In SIGIR , 2012
"... Supervised learning applied to answer re-ranking can highly improve on the overall accuracy of question answering (QA) systems. The key aspect is that the relationships and prop-erties of the question/answer pair composed of a question and the supporting passage of an answer candidate, can be effici ..."
Abstract - Cited by 18 (10 self) - Add to MetaCart
Supervised learning applied to answer re-ranking can highly improve on the overall accuracy of question answering (QA) systems. The key aspect is that the relationships and prop-erties of the question/answer pair composed of a question and the supporting passage of an answer candidate, can be efficiently compared with those captured by the learnt model. In this paper, we define novel supervised approaches that exploit structural relationships between a question and their candidate answer passages to learn a re-ranking model. We model structural representations of both questions and answers and their mutual relationships by just using an off-the-shelf shallow syntactic parser. We encode structures in Support Vector Machines (SVMs) by means of sequence and tree kernels, which can implicitly represent question and an-swer pairs in huge feature spaces. Such models together with the latest approach to fast kernel-based learning enabled the training of our rerankers on hundreds of thousands of instances, which previously rendered intractable for kernel-ized SVMs. The results on two different QA datasets, e.g., Answerbag and Jeopardy! data, show that our models de-liver large improvement on passage re-ranking tasks, reduc-ing the error in Recall of BM25 baseline by about 18%. One of the key findings of this work is that, despite its simplicity, shallow syntactic trees allow for learning complex relational structures, which exhibits a steep learning curve with the increase in the training size.
(Show Context)

Citation Context

...ubstructures describing the objects above. The most general kind of kernels used in NLP are string kernels (SKs), e.g., [28], the Syntactic Tree Kernels (STKs) [8] and the Partial Tree Kernels (PTKs) =-=[20]-=-. 3.1 String Kernels The String Kernels (SK) that we consider count the number of subsequences shared by two strings of symbols, s1 and s2. Some symbols during the matching process can be skipped. Thi...

Kernels on Linguistic Structures for Answer Extraction

by Ro Moschitti, Silvia Quarteroni
"... Natural Language Processing (NLP) for Information Retrieval has always been an interesting and challenging research area. Despite the high expectations, most of the results indicate that successfully using NLP is very complex. In this paper, we show how Support Vector Machines along with kernel func ..."
Abstract - Cited by 17 (8 self) - Add to MetaCart
Natural Language Processing (NLP) for Information Retrieval has always been an interesting and challenging research area. Despite the high expectations, most of the results indicate that successfully using NLP is very complex. In this paper, we show how Support Vector Machines along with kernel functions can effectively represent syntax and semantics. Our experiments on question/answer classification show that the above models highly improve on bag-of-words on a TREC dataset. 1
(Show Context)

Citation Context

..., (3) the Syntactic Tree Kernel (STK) (Collins and Duffy, 2002) on syntactic parse trees (PTs), (4) the Shallow Semantic Tree Kernel (SSTK) (Moschitti et al., 2007) and the Partial Tree Kernel (PTK) (=-=Moschitti, 2006-=-) on PASs. In particular, POS-tag sequences and PAS trees used with SK and PTK yield to two innovative kernels, i.e. POSSK and PAS-PTK 2 . In the next sections, we describe in more detail the data str...

Coreference Systems based on Kernels Methods

by Yannick Versley, Alessandro Moschitti, Massimo Poesio, Xiaofeng Yang
"... Various types of structural information-e.g., about the type of constructions in which binding constraints apply, or about the structure of names- play a central role in coreference resolution, often in combination with lexical information (as in expletive detection). Kernel functions appear to be a ..."
Abstract - Cited by 15 (4 self) - Add to MetaCart
Various types of structural information-e.g., about the type of constructions in which binding constraints apply, or about the structure of names- play a central role in coreference resolution, often in combination with lexical information (as in expletive detection). Kernel functions appear to be a promising candidate to capture structure-sensitive similarities and complex feature combinations, but care is required to ensure they are exploited in the best possible fashion. In this paper we propose kernel functions for three subtasks of coreference resolution- binding constraint detection, expletive identification, and aliasing- together with an architecture to integrate them within the standard framework for coreference resolution. 1
(Show Context)

Citation Context

...o be a viable approach to feature engineering for natural language processing for any task in which structural information plays a role, e.g. (Collins and Duffy 2002; Zelenko et al. 2003; Giuglea and =-=Moschitti 2006-=-; Zanzotto and Moschitti 2006; Moschitti et al. 2007). Indeed, they have already been used in NLP to encode the type of structural information that plays a role in binding constraints (Yang et al. 200...

Powered by: Apache Solr
  • About CiteSeerX
  • Submit and Index Documents
  • Privacy Policy
  • Help
  • Data
  • Source
  • Contact Us

Developed at and hosted by The College of Information Sciences and Technology

© 2007-2019 The Pennsylvania State University