Results 1 - 10
of
93
BART: A modular toolkit for coreference resolution
- In Association for Computational Linguistics (ACL) Demo Session
, 2008
"... Developing a full coreference system able to run all the way from raw text to semantic interpretation is a considerable engineering effort. Accordingly, there is very limited availability of off-the shelf tools for researchers whose interests are not primarily in coreference or others who want to co ..."
Abstract
-
Cited by 32 (4 self)
- Add to MetaCart
(Show Context)
Developing a full coreference system able to run all the way from raw text to semantic interpretation is a considerable engineering effort. Accordingly, there is very limited availability of off-the shelf tools for researchers whose interests are not primarily in coreference or others who want to concentrate on a specific aspect of the problem. We present BART, a highly modular toolkit for developing coreference applications. In the Johns Hopkins workshop on using lexical and encyclopedic knowledge for entity disambiguation, the toolkit was used to extend a reimplementation of the Soon et al. (2001) proposal with a variety of additional syntactic and knowledge-based features, and experiment with alternative resolution processes, preprocessing tools, and classifiers. 1.
Semantic role labeling via tree kernel joint inference
- IN PROCEEDINGS OF CONLL-X
, 2006
"... Recent work on Semantic Role Labeling (SRL) has shown that to achieve high accuracy a joint inference on the whole predicate argument structure should be applied. In this paper, we used syntactic subtrees that span potential argument structures of the target predicate in tree kernel functions. This ..."
Abstract
-
Cited by 30 (11 self)
- Add to MetaCart
(Show Context)
Recent work on Semantic Role Labeling (SRL) has shown that to achieve high accuracy a joint inference on the whole predicate argument structure should be applied. In this paper, we used syntactic subtrees that span potential argument structures of the target predicate in tree kernel functions. This allows Support Vector Machines to discern between correct and incorrect predicate structures and to re-rank them based on the joint probability of their arguments. Experiments on the PropBank data show that both classification and re-ranking based on tree kernels can improve SRL systems.
Syntactic and semantic structure for opinion expression detection
- In Proceedings of the 14th Conference on Computational Natural Language Learning
, 2010
"... We demonstrate that relational features derived from dependency-syntactic and semantic role structures are useful for the task of detecting opinionated expressions in natural-language text, significantly improving over conventional models based on sequence labeling with local features. These feature ..."
Abstract
-
Cited by 21 (4 self)
- Add to MetaCart
(Show Context)
We demonstrate that relational features derived from dependency-syntactic and semantic role structures are useful for the task of detecting opinionated expressions in natural-language text, significantly improving over conventional models based on sequence labeling with local features. These features allow us to model the way opinionated expressions interact in a sentence over arbitrary distances. While the relational features make the prediction task more computationally expensive, we show that it can be tackled effectively by using a reranker. We evaluate a number of machine learning approaches for the reranker, and the best model results in a 10-point absolute improvement in soft recall on the MPQA corpus, while decreasing precision only slightly. 1
Task-oriented Evaluation of Syntactic Parsers and Their Representations
- PROCEEDINGS OF THE 46TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES
, 2008
"... This paper presents a comparative evaluation of several state-of-the-art English parsers based on different frameworks. Our approach is to measure the impact of each parser when it is used as a component of an information extraction system that performs protein-protein interaction (PPI) identificati ..."
Abstract
-
Cited by 20 (3 self)
- Add to MetaCart
This paper presents a comparative evaluation of several state-of-the-art English parsers based on different frameworks. Our approach is to measure the impact of each parser when it is used as a component of an information extraction system that performs protein-protein interaction (PPI) identification in biomedical papers. We evaluate eight parsers (based on dependency parsing, phrase structure parsing, or deep parsing) using five different parse representations. We run a PPI system with several combinations of parser and parse representation, and examine their impact on PPI identification accuracy. Our experiments show that the levels of accuracy obtained with these different parsers are similar, but that accuracy improvements vary when the parsers are retrained with domain-specific data.
A.: Cross-language frame semantics transfer in bilingual corpora
- In: Proc. of 10th Int. Conf. on Intelligent Text Processing and Computational Linguistics (CICLing 2009
, 2009
"... Abstract. Recent work on the transfer of semantic information across languages has been recently applied to the development of resources annotated with Frame information for different non-English European languages. These works are based on the assumption that parallel corpora annotated for English ..."
Abstract
-
Cited by 14 (2 self)
- Add to MetaCart
(Show Context)
Abstract. Recent work on the transfer of semantic information across languages has been recently applied to the development of resources annotated with Frame information for different non-English European languages. These works are based on the assumption that parallel corpora annotated for English can be used to transfer the semantic information to the other target languages. In this paper, a robust method based on a statistical machine translation step augmented with simple rule-based post-processing is presented. It alleviates problems related to preprocessing errors and the complex optimization required by syntax-dependent models of the cross-lingual mapping. Different alignment strategies are here in-vestigated against the Europarl corpus. Results suggest that the quality of the de-rived annotations is surprisingly good and well suited for training semantic role labeling systems. 1
Syntactic/semantic structures for textual entailment recognition
- In Proceedings of NAACL
, 2010
"... All in-text references underlined in blue are linked to publications on ResearchGate, letting you access and read them immediately. ..."
Abstract
-
Cited by 13 (9 self)
- Add to MetaCart
(Show Context)
All in-text references underlined in blue are linked to publications on ResearchGate, letting you access and read them immediately.
Prior derivation models for formally syntax-based translation using linguistically syntactic parsing and tree kernels
- In Proceedings of the ACL’08: HLT SSST-2
, 2008
"... This paper presents an improved formally syntax-based SMT model, which is enriched by linguistically syntactic knowledge obtained from statistical constituent parsers. We propose a linguistically-motivated prior derivation model to score hypothesis derivations on top of the baseline model during the ..."
Abstract
-
Cited by 11 (6 self)
- Add to MetaCart
(Show Context)
This paper presents an improved formally syntax-based SMT model, which is enriched by linguistically syntactic knowledge obtained from statistical constituent parsers. We propose a linguistically-motivated prior derivation model to score hypothesis derivations on top of the baseline model during the translation decoding. Moreover, we devise a fast training algorithm to achieve such improved models based on tree kernel methods. Experiments on an English-to-Chinese task demonstrate that our proposed models outperformed the baseline formally syntaxbased models, while both of them achieved
Large-scale support vector learning with structural kernels
- In ECML/PKDD
, 2010
"... Abstract. In this paper, we present an extensive study of the cutting-plane algorithm (CPA) applied to structural kernels for advanced text classification on large datasets. In particular, we carry out a compre-hensive experimentation on two interesting natural language tasks, e.g. predicate argumen ..."
Abstract
-
Cited by 11 (4 self)
- Add to MetaCart
(Show Context)
Abstract. In this paper, we present an extensive study of the cutting-plane algorithm (CPA) applied to structural kernels for advanced text classification on large datasets. In particular, we carry out a compre-hensive experimentation on two interesting natural language tasks, e.g. predicate argument extraction and question answering. Our results show that (i) CPA applied to train a non-linear model with different tree kernels fully matches the accuracy of the conventional SVM algorithm while being ten times faster; (ii) by using smaller sampling sizes to ap-proximate subgradients in CPA we can trade off accuracy for speed, yet the optimal parameters and kernels found remain optimal for the exact SVM. These results open numerous research perspectives, e.g. in natural language processing, as they show that complex structural kernels can be efficiently used in real-world applications. For example, for the first time, we could carry out extensive tests of several tree kernels on mil-lions of training instances. As a direct benefit, we could experiment with a variant of the partial tree kernel, which we also propose in this paper.
Syntactic and semantic kernels for short text pair categorization
- In EACL
, 2009
"... Automatic detection of general relations between short texts is a complex task that cannot be carried out only relying on language models and bag-of-words. Therefore, learning methods to exploit syntax and semantics are required. In this paper, we present a new kernel for the representation of shall ..."
Abstract
-
Cited by 11 (4 self)
- Add to MetaCart
(Show Context)
Automatic detection of general relations between short texts is a complex task that cannot be carried out only relying on language models and bag-of-words. Therefore, learning methods to exploit syntax and semantics are required. In this paper, we present a new kernel for the representation of shallow semantic information along with a comprehensive study on kernel methods for the exploitation of syntactic/semantic structures for short text pair categorization. Our experiments with Support Vector Machines on question/answer classification show that our kernels can be used to greatly improve system accuracy. 1
Linguistic kernels for answer re-ranking in question answering systems
- Information Processing & Management
, 2010
"... Abstract Answer selection is the most complex phase of a Question Answering (QA) system. To solve this task, typical approaches use unsupervised methods such as computing the similarity between query and answer, optionally exploiting advanced syntactic, semantic or logic representations. In this pa ..."
Abstract
-
Cited by 10 (4 self)
- Add to MetaCart
(Show Context)
Abstract Answer selection is the most complex phase of a Question Answering (QA) system. To solve this task, typical approaches use unsupervised methods such as computing the similarity between query and answer, optionally exploiting advanced syntactic, semantic or logic representations. In this paper, we study supervised discriminative models that learn to select (rank) answers using examples of question and answer pairs. The pair representation is implicitly provided by kernel combinations applied to each of its members. To reduce the burden of large amounts of manual annotation, we represent question and answer pairs by means of powerful generalization methods, exploiting the application of structural kernels to syntactic/semantic structures. We experiment with Support Vector Machines and string kernels, syntactic and shallow semantic tree kernels applied to part-of-speech tag sequences, syntactic parse trees and predicate argument structures on two datasets which we have compiled and made available. Our results on classification of correct and incorrect pairs show that our best model improves the bag-of-words model by 63% on a TREC dataset. Moreover, such a binary classifier, used as a re-ranker, improves the Mean Reciprocal Rank of our baseline QA system by 13%. These findings demonstrate that our method automatically selects an appropriate representation of question-answer relations.
