Results 1 - 10
of
42
Cross-lingual annotation projection for semantic roles
- Journal of Artificial Intelligence Research
, 2009
"... This article considers the task of automatically inducing role-semantic annotations in the FrameNet paradigm for new languages. We propose a general framework that is based on annotation projection, phrased as a graph optimization problem. It is relatively inexpensive and has the potential to reduce ..."
Abstract
-
Cited by 38 (3 self)
- Add to MetaCart
(Show Context)
This article considers the task of automatically inducing role-semantic annotations in the FrameNet paradigm for new languages. We propose a general framework that is based on annotation projection, phrased as a graph optimization problem. It is relatively inexpensive and has the potential to reduce the human effort involved in creating role-semantic resources. Within this framework, we present projection models that exploit lexical and syntactic information. We provide an experimental evaluation on an English-German parallel corpus which demonstrates the feasibility of inducing high-precision German semantic role annotation both for manually and automatically annotated English data. 1.
End-to-End Relation Extraction Using Distant Supervision from External Semantic Repositories
"... In this paper, we extend distant supervision (DS) based on Wikipedia for Relation Extraction (RE) by considering (i) relations defined in external repositories, e.g. YAGO, and (ii) any subset of Wikipedia documents. We show that training data constituted by sentences containing pairs of named entiti ..."
Abstract
-
Cited by 27 (2 self)
- Add to MetaCart
(Show Context)
In this paper, we extend distant supervision (DS) based on Wikipedia for Relation Extraction (RE) by considering (i) relations defined in external repositories, e.g. YAGO, and (ii) any subset of Wikipedia documents. We show that training data constituted by sentences containing pairs of named entities in target relations is enough to produce reliable supervision. Our experiments with state-of-the-art relation extraction models, trained on the above data, show a meaningful F1 of 74.29 % on a manually annotated test set: this highly improves the state-of-art in RE using DS. Additionally, our end-to-end experiments demonstrated that our extractors can be applied to any general text document. 1
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
Structural relationships for large-scale learning of answer reranking
- 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
(Show Context)
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.
Embedding semantic similarity in tree kernels for domain adaptation of relation extraction
- In ACL
, 2013
"... Relation Extraction (RE) is the task of extracting semantic relationships between entities in text. Recent studies on rela-tion extraction are mostly supervised. The clear drawback of supervised methods is the need of training data: labeled data is expensive to obtain, and there is often a mismatch ..."
Abstract
-
Cited by 13 (4 self)
- Add to MetaCart
(Show Context)
Relation Extraction (RE) is the task of extracting semantic relationships between entities in text. Recent studies on rela-tion extraction are mostly supervised. The clear drawback of supervised methods is the need of training data: labeled data is expensive to obtain, and there is often a mismatch between the training data and the data the system will be applied to. This is the problem of domain adapta-tion. In this paper, we propose to combine (i) term generalization approaches such as word clustering and latent semantic anal-ysis (LSA) and (ii) structured kernels to improve the adaptability of relation ex-tractors to new text genres/domains. The empirical evaluation on ACE 2005 do-mains shows that a suitable combination of syntax and lexical generalization is very promising for domain adaptation. 1
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
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.
Joint Distant and Direct Supervision for Relation Extraction
"... Supervised approaches to Relation Extraction (RE) are characterized by higher accuracy than unsupervised models. Unfortunately, their applicability is limited by the need of training data for each relation type. Automatic creation of such data using Distant Supervision (DS) provides a promising solu ..."
Abstract
-
Cited by 10 (1 self)
- Add to MetaCart
(Show Context)
Supervised approaches to Relation Extraction (RE) are characterized by higher accuracy than unsupervised models. Unfortunately, their applicability is limited by the need of training data for each relation type. Automatic creation of such data using Distant Supervision (DS) provides a promising solution to the problem. In this paper, we study DS for designing endto-end systems of sentence-level RE. In particular, we propose a joint model between Web data derived with DS and manually annotated data from ACE. The results show (i) an improvement on the previous state-of-the-art in ACE, which provides important evidence of the benefit of DS; and (ii) a rather good accuracy on extracting 52 types of relations from Web data, which suggests the applicability of DS for general RE. 1
Learning Adaptable Patterns for Passage Reranking
"... This paper proposes passage reranking models that (i) do not require manual feature engineering and (ii) greatly preserve accuracy, when changing application domain. Their main characteristic is the use of relational semantic structures representing questions and their answer passages. The relations ..."
Abstract
-
Cited by 9 (5 self)
- Add to MetaCart
(Show Context)
This paper proposes passage reranking models that (i) do not require manual feature engineering and (ii) greatly preserve accuracy, when changing application domain. Their main characteristic is the use of relational semantic structures representing questions and their answer passages. The relations are established using information from automatic classifiers,
Discriminative Reranking for Spoken Language Understanding
- IEEE Transactions on Audio, Speech & Language Processing
, 2012
"... Abstract—Spoken Language Understanding (SLU) is con-cerned with the extraction of meaning structures from spo-ken utterances. Recent computational approaches to SLU, e.g. Conditional Random Fields (CRF), optimize local models by encoding several features, mainly based on simple n-grams. In contrast, ..."
Abstract
-
Cited by 8 (0 self)
- Add to MetaCart
(Show Context)
Abstract—Spoken Language Understanding (SLU) is con-cerned with the extraction of meaning structures from spo-ken utterances. Recent computational approaches to SLU, e.g. Conditional Random Fields (CRF), optimize local models by encoding several features, mainly based on simple n-grams. In contrast, recent works have shown that the accuracy of CRF can be significantly improved by modeling long-distance dependency features. In this paper, we propose novel approaches to encode all possible dependencies between features and most importantly among parts of the meaning structure, e.g. concepts and their combination. We rerank hypotheses generated by local models, e.g. Stochastic Finite State Transducers (SFSTs) or Conditional Random Fields (CRF), with a global model. The latter encodes a very large number of dependencies (in the form of trees or sequences) by applying kernel methods to the space of all meaning (sub) structures. We performed comparative experiments between SFST, CRF, Support Vector Machines (SVMs) and our proposed discriminative reranking models (DRMs) on representative conversational speech corpora in three different languages: the ATIS (English), the MEDIA (French) and the LUNA (Italian) corpora. These corpora have been collected within three different domain applications of increasing complexity: informational, transactional and problem-solving tasks, respectively. The results show that our DRMs consistently outperform the state-of-the-art models based on CRF.
Automatic Feature Engineering for Answer Selection and Extraction
"... This paper proposes a framework for automat-ically engineering features for two important tasks of question answering: answer sentence selection and answer extraction. We represent question and answer sentence pairs with lin-guistic structures enriched by semantic infor-mation, where the latter is p ..."
Abstract
-
Cited by 8 (4 self)
- Add to MetaCart
(Show Context)
This paper proposes a framework for automat-ically engineering features for two important tasks of question answering: answer sentence selection and answer extraction. We represent question and answer sentence pairs with lin-guistic structures enriched by semantic infor-mation, where the latter is produced by auto-matic classifiers, e.g., question classifier and Named Entity Recognizer. Tree kernels ap-plied to such structures enable a simple way to generate highly discriminative structural fea-tures that combine syntactic and semantic in-formation encoded in the input trees. We con-duct experiments on a public benchmark from TREC to compare with previous systems for answer sentence selection and answer extrac-tion. The results show that our models greatly improve on the state of the art, e.g., up to 22% on F1 (relative improvement) for answer ex-traction, while using no additional resources and no manual feature engineering. 1
