Results 1 - 10
of
263
Non-projective dependency parsing using spanning tree algorithms
- In Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing
, 2005
"... We formalize weighted dependency parsing as searching for maximum spanning trees (MSTs) in directed graphs. Using this representation, the parsing algorithm of Eisner (1996) is sufficient for searching over all projective trees in O(n 3) time. More surprisingly, the representation is extended natura ..."
Abstract
-
Cited by 383 (10 self)
- Add to MetaCart
We formalize weighted dependency parsing as searching for maximum spanning trees (MSTs) in directed graphs. Using this representation, the parsing algorithm of Eisner (1996) is sufficient for searching over all projective trees in O(n 3) time. More surprisingly, the representation is extended naturally to non-projective parsing using Chu-Liu-Edmonds (Chu and Liu, 1965; Edmonds, 1967) MST algorithm, yielding an O(n 2) parsing algorithm. We evaluate these methods on the Prague Dependency Treebank using online large-margin learning techniques (Crammer et al., 2003; McDonald et al., 2005) and show that MST parsing increases efficiency and accuracy for languages with non-projective dependencies. 1
Online large-margin training of dependency parsers
- In Proc. ACL
, 2005
"... We present an effective training algorithm for linearly-scored dependency parsers that implements online largemargin multi-class training (Crammer and Singer, 2003; Crammer et al., 2003) on top of efficient parsing techniques for dependency trees (Eisner, 1996). The trained parsers achieve a competi ..."
Abstract
-
Cited by 306 (23 self)
- Add to MetaCart
We present an effective training algorithm for linearly-scored dependency parsers that implements online largemargin multi-class training (Crammer and Singer, 2003; Crammer et al., 2003) on top of efficient parsing techniques for dependency trees (Eisner, 1996). The trained parsers achieve a competitive dependency accuracy for both English and Czech with no language specific enhancements. 1
Extracting relations with integrated information using kernel methods
- In Proceedings of the annual meeting of ACL
, 2005
"... Entity relation detection is a form of information extraction that finds predefined relations between pairs of entities in text. This paper describes a relation detection approach that combines clues from different levels of syntactic processing using kernel methods. Information from three different ..."
Abstract
-
Cited by 95 (6 self)
- Add to MetaCart
Entity relation detection is a form of information extraction that finds predefined relations between pairs of entities in text. This paper describes a relation detection approach that combines clues from different levels of syntactic processing using kernel methods. Information from three different levels of processing is considered: tokenization, sentence parsing and deep dependency analysis. Each source of information is represented by kernel functions. Then composite kernels are developed to integrate and extend individual kernels so that processing errors occurring at one level can be overcome by information from other levels. We present an evaluation of these methods on the 2004 ACE relation detection task, using Support Vector Machines, and show that each level of syntactic processing contributes useful information for this task. When evaluated on the official test data, our approach produced very competitive ACE value scores. We also compare the SVM with KNN on different kernels. 1
Making Tree Kernels Practical for Natural Language Learning
, 2006
"... In recent years tree kernels have been proposed for the automatic learning of natural language applications. Unfortunately, they show (a) an inherent super linear complexity and (b) a lower accuracy than traditional attribute/value methods. ..."
Abstract
-
Cited by 93 (14 self)
- Add to MetaCart
In recent years tree kernels have been proposed for the automatic learning of natural language applications. Unfortunately, they show (a) an inherent super linear complexity and (b) a lower accuracy than traditional attribute/value methods.
Efficient convolution kernels for dependency and constituent syntactic trees
- In European Conference on Machine Learning (ECML
, 2006
"... Abstract. In this paper, we provide a study on the use of tree kernels to encode syntactic parsing information in natural language learning. In particular, we propose a new convolution kernel, namely the Partial Tree (PT) kernel, to fully exploit dependency trees. We also propose an efficient algori ..."
Abstract
-
Cited by 89 (21 self)
- Add to MetaCart
(Show Context)
Abstract. In this paper, we provide a study on the use of tree kernels to encode syntactic parsing information in natural language learning. In particular, we propose a new convolution kernel, namely the Partial Tree (PT) kernel, to fully exploit dependency trees. We also propose an efficient algorithm for its computation which is futhermore sped-up by applying the selection of tree nodes with non-null kernel. The experiments with Support Vector Machines on the task of semantic role labeling and question classification show that (a) the kernel running time is linear on the average case and (b) the PT kernel improves on the other tree kernels when applied to the appropriate parsing paradigm. 1
Learning to extract relations from the web using minimal supervision
- In Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics (ACL’07
, 2007
"... We present a new approach to relation extraction that requires only a handful of training examples. Given a few pairs of named entities known to exhibit or not exhibit a particular relation, bags of sentences containing the pairs are extracted from the web. We extend an existing relation extraction ..."
Abstract
-
Cited by 80 (2 self)
- Add to MetaCart
(Show Context)
We present a new approach to relation extraction that requires only a handful of training examples. Given a few pairs of named entities known to exhibit or not exhibit a particular relation, bags of sentences containing the pairs are extracted from the web. We extend an existing relation extraction method to handle this weaker form of supervision, and present experimental results demonstrating that our approach can reliably extract relations from web documents. 1
Relation Extraction with Matrix Factorization and Universal Schemas
"... Traditional relation extraction predicts relations within some fixed and finite target schema. Machine learning approaches to this task require either manual annotation or, in the case of distant supervision, existing structured sources of the same schema. The need for existing datasets can be avoid ..."
Abstract
-
Cited by 77 (12 self)
- Add to MetaCart
Traditional relation extraction predicts relations within some fixed and finite target schema. Machine learning approaches to this task require either manual annotation or, in the case of distant supervision, existing structured sources of the same schema. The need for existing datasets can be avoided by using a universal schema: the union of all involved schemas (surface form predicates as in OpenIE, and relations in the schemas of preexisting databases). This schema has an almost unlimited set of relations (due to surface forms), and supports integration with existing structured data (through the relation types of existing databases). To populate a database of such schema we present matrix factorization models that learn latent feature vectors for entity tuples and relations. We show that such latent models achieve substantially higher accuracy than a traditional classification approach. More importantly, by operating simultaneously on relations observed in text and in pre-existing structured DBs such as Freebase, we are able to reason about unstructured and structured data in mutually-supporting ways. By doing so our approach outperforms stateof-the-art distant supervision. 1
Exploring various knowledge in relation extraction
- In Proceedings of the 43rd Meeting of the ACL
, 2005
"... All in-text references underlined in blue are linked to publications on ResearchGate, letting you access and read them immediately. ..."
Abstract
-
Cited by 74 (8 self)
- Add to MetaCart
All in-text references underlined in blue are linked to publications on ResearchGate, letting you access and read them immediately.
Incremental integer linear programming for non-projective dependency parsing
- In EMNLP
, 2006
"... Integer Linear Programming has recently been used for decoding in a number of probabilistic models in order to enforce global constraints. However, in certain applications, such as non-projective dependency parsing and machine translation, the complete formulation of the decoding problem as an integ ..."
Abstract
-
Cited by 63 (6 self)
- Add to MetaCart
(Show Context)
Integer Linear Programming has recently been used for decoding in a number of probabilistic models in order to enforce global constraints. However, in certain applications, such as non-projective dependency parsing and machine translation, the complete formulation of the decoding problem as an integer linear program renders solving intractable. We present an approach which solves the problem incrementally, thus we avoid creating intractable integer linear programs. This approach is applied to Dutch dependency parsing and we show how the addition of linguistically motivated constraints can yield a significant improvement over stateof-the-art. 1
Tree kernels for semantic role labeling
- Computational Linguistics
, 2008
"... The availability of large scale data sets of manually annotated predicate–argument structures has recently favored the use of machine learning approaches to the design of automated semantic role labeling (SRL) systems. The main research in this area relates to the design choices for feature represen ..."
Abstract
-
Cited by 60 (14 self)
- Add to MetaCart
(Show Context)
The availability of large scale data sets of manually annotated predicate–argument structures has recently favored the use of machine learning approaches to the design of automated semantic role labeling (SRL) systems. The main research in this area relates to the design choices for feature representation and for effective decompositions of the task in different learning models. Regarding the former choice, structural properties of full syntactic parses are largely employed as they represent ways to encode different principles suggested by the linking theory between syntax and semantics. The latter choice relates to several learning schemes over global views of the parses. For example, re-ranking stages operating over alternative predicate–argument sequences of the same sentence have shown to be very effective. In this article, we propose several kernel functions to model parse tree properties in kernelbased machines, for example, perceptrons or support vector machines. In particular, we define different kinds of tree kernels as general approaches to feature engineering in SRL. Moreover, we extensively experiment with such kernels to investigate their contribution to individual stages of an SRL architecture both in isolation and in combination with other traditional manually coded features. The results for boundary recognition, classification, and re-ranking stages provide systematic evidence about the significant impact of tree kernels on the overall accuracy, especially when the amount of training data is small. As a conclusive result, tree kernels allow for a general and easily portable feature engineering method which is applicable to a large family of natural language processing tasks. 1.
