confidence driven unsupervised semantic parsing

Tài liệu Báo cáo khoa học: "Transition-based parsing with Confidence-Weighted Classification" pdf

Tài liệu Báo cáo khoa học: "Transition-based parsing with Confidence-Weighted Classification" pdf

Ngày tải lên : 20/02/2014, 04:20
... kernel with the SVM. 3 Confidence- weighted classification Dredze et al. (2008) introduce confidence- weighted linear classifiers which are online- classifiers that maintain a confidence parameter for ... expected given their online-nature. We also see that parsing is much faster. SVM CW Training 75 min 8 min Parsing 29 min 1.5 min Table 1: Training and parsing time on Danish data. 5.3 Pruning features Because ... this by having a confidence- parameter for each weight, modeled by a Gaussian distribution, and this pa- rameter is used to make more aggressive updates on weights with lower confidence (Dredze...
  • 6
  • 493
  • 0
Tài liệu Báo cáo khoa học: "Semantic Parsing with Bayesian Tree Transducers" doc

Tài liệu Báo cáo khoa học: "Semantic Parsing with Bayesian Tree Transducers" doc

Ngày tải lên : 19/02/2014, 19:20
... transducers, producing state-of-the-art semantic parsing re- sults while remaining applicable to any do- main employing probabilistic tree transducers. 1 Introduction Semantic parsing is the task of mapping ... three-fold: we present a new state-of-the-art semantic parsing model, propose a broader theory for tree transforma- tion based semantic parsing, and present a general inference algorithm for ... decoding when we want to infer the input given the output. 4 A generative model of semantic parsing Like the hybrid tree semantic parser (Lu et al., 2008) and the synchronous grammar based WASP (Wong and...
  • 9
  • 475
  • 0
Tài liệu Báo cáo khoa học: "Unsupervised Semantic Role Induction with Global Role Ordering" doc

Tài liệu Báo cáo khoa học: "Unsupervised Semantic Role Induction with Global Role Ordering" doc

Ngày tải lên : 19/02/2014, 19:20
... ordering. 1 Introduction Unsupervised semantic role induction has gained significant interest recently (Lang and Lapata, 2011b) due to limited amounts of annotated corpora. A Semantic Role Labeling ... ] A1 (b.) [ The car ] A1 was driven by [ Mark ] A0 This simple example also shows that while certain local syntactic and semantic features could provide clues to the semantic role label of a constituent, ... 145–149, Jeju, Republic of Korea, 8-14 July 2012. c 2012 Association for Computational Linguistics Unsupervised Semantic Role Induction with Global Role Ordering Nikhil Garg University of Geneva Switzerland nikhil.garg@unige.ch James...
  • 5
  • 398
  • 0
Tài liệu Báo cáo khoa học: "A Method for Measuring Machine Translation Confidence" docx

Tài liệu Báo cáo khoa học: "A Method for Measuring Machine Translation Confidence" docx

Ngày tải lên : 20/02/2014, 04:20
... application of confidence score in the n- best list reranking task, we propose a method to visual- ize translation error using confidence scores. Our pur- pose is to visualize word and sentence-level confidence scores ... Section 4 indicate that the proposed confidence measure has a high correlation with HTER. However, it is not very clear if the core MT system can benefit from confidence measure by provid- ing better ... hypotheses and for each hypothesis we compute sentence-level confidence scores. The best candidate is the hypothesis with high- est confidence score. Table 3 shows the performance of reranking systems...
  • 9
  • 543
  • 0
Tài liệu Báo cáo khoa học: "Neutralizing Linguistically Problematic Annotations in Unsupervised Dependency Parsing Evaluation" doc

Tài liệu Báo cáo khoa học: "Neutralizing Linguistically Problematic Annotations in Unsupervised Dependency Parsing Evaluation" doc

Ngày tải lên : 20/02/2014, 04:20
... 2010. Unsupervised Induction of Tree Substitution Grammars for Depen- dency Parsing. In Proc. of EMNLP. Shay B. Cohen, Kevin Gimpel and Noah A. Smith, 2008. Logistic Normal Priors for Unsupervised ... HLT-NAACL. Michael J. Collins, 1999. Head -driven statistical models for natural language parsing. Ph.D. thesis, University of Pennsylvania, Philadelphia. Alexander Clark, 2001. Unsupervised language acquisi- tion: ... would like to have a proper evaluation of unsupervised parsing algo- rithms against a gold standard. The first way was to modify the parameters of the parsing algorithms so that in cases where...
  • 10
  • 411
  • 0
Tài liệu Báo cáo khoa học: "Fast Unsupervised Incremental Parsing" pdf

Tài liệu Báo cáo khoa học: "Fast Unsupervised Incremental Parsing" pdf

Ngày tải lên : 20/02/2014, 12:20
... be fast, parsing (on a 1.86GHz Centrino laptop) at a rate of around 4000 words/sec. and learning (including parsing) at a rate of 3200 – 3600 words/sec. The effect of sentence length on parsing ... paper. References Rens Bod. 2006a. An all-subtrees approach to unsuper- vised parsing. In Proceedings of COLING-ACL 2006. Rens Bod. 2006b. Unsupervised parsing with U-DOP. In Proceedings of CoNLL 10. Alexander Clark. ... re- mains, therefore, valid. Table 1 gives two baselines and the parsing re- sults for WSJ10, WSJ40, Negra10 and Negra40 for recent unsupervised parsing algorithms: CCM 2 I also tested the incremental...
  • 8
  • 343
  • 0
Tài liệu Báo cáo khoa học: "Performance Confidence Estimation for Automatic Summarization" ppt

Tài liệu Báo cáo khoa học: "Performance Confidence Estimation for Automatic Summarization" ppt

Ngày tải lên : 22/02/2014, 02:20
... Greece, 30 March – 3 April 2009. c 2009 Association for Computational Linguistics Performance Confidence Estimation for Automatic Summarization Annie Louis University of Pennsylvania lannie@seas.upenn.edu Ani ... properties of document clusters can be used to identify difficult inputs. The task of predicting the confidence in system performance for a given input is in fact relevant not only for summarization, ... question answering for example, a system may be configured not to answer questions for which the confidence of producing a correct answer is low, and in this way increase the overall accuracy of...
  • 8
  • 342
  • 0
Báo cáo khoa học: "Balancing User Effort and Translation Error in Interactive Machine Translation Via Confidence Measures" pot

Báo cáo khoa học: "Balancing User Effort and Translation Error in Interactive Machine Translation Via Confidence Measures" pot

Ngày tải lên : 07/03/2014, 22:20
... word is classified as correct if its confidence exceeds a word classification threshold τ w . c R (e I 1 ) = |{e i / c w (e i ) > τ w }| I (5) After computing the confidence value, each sen- tence ... and N. Ueffing. 2003. Confidence estimation for machine transla- tion. J. Blatz, E. Fitzgerald, G. Foster, S. Gandrabur, C. Goutte, A. Kuesza, A. Sanchis, and N. Ueffing. 2004. Confidence estimation ... Application of word- level confidence measures in interactive statistical machine translation. In Proc. EAMT, pages 262– 270. N. Ueffing and H. Ney. 2007. Word-level confidence estimation for machine...
  • 5
  • 385
  • 0
Báo cáo khoa học: "Mapping between Compositional Semantic Representations and Lexical Semantic Resources: Towards Accurate Deep Semantic Parsing" docx

Báo cáo khoa học: "Mapping between Compositional Semantic Representations and Lexical Semantic Resources: Towards Accurate Deep Semantic Parsing" docx

Ngày tải lên : 08/03/2014, 01:20
... Computational Linguistics Mapping between Compositional Semantic Representations and Lexical Semantic Resources: Towards Accurate Deep Semantic Parsing Sergio Roa†‡, Valia Kordoni† and Yi Zhang† Dept. ... representations and lexical semantic resources. A probabilistic model comprising Minimal Recursion Semantics (MRS) struc- tures and lexicalist oriented semantic features is acquired. Lexical semantic roles ... reliable and benefi- cial to deep parsing. 2 Minimal Recursion Semantics The semantic representation we are interested in in this paper is the Minimal Recursion Semantics (MRS). Because of its...
  • 4
  • 258
  • 0
Báo cáo khoa học: "A Study on Convolution Kernels for Shallow Semantic Parsing" pdf

Báo cáo khoa học: "A Study on Convolution Kernels for Shallow Semantic Parsing" pdf

Ngày tải lên : 08/03/2014, 04:22
... even if preliminary experiments on automatic seman- tic shallow parsing of PropBank have shown no important differences versus semantic parsing which adopts Gold Standard parse-trees. 5 Conclusions In ... features. The results have shown that: First, SVMs using the above kernels are ap- pealing for semantically parsing both corpora. Second, PAF and SCF can be used to improve automatic classification ... for parsing and tagging: Kernels over discrete structures, and the voted perceptron. In proceeding of ACL-02. Michael Collins. 1997. Three generative, lexicalized models for statistical parsing. ...
  • 8
  • 373
  • 0
Báo cáo khoa học: "FROM STRUCTURE-DRIVEN SEPARATE SEMANTIC GENERATION REPRESENTATIONS" ppt

Báo cáo khoa học: "FROM STRUCTURE-DRIVEN SEPARATE SEMANTIC GENERATION REPRESENTATIONS" ppt

Ngày tải lên : 09/03/2014, 01:20
... of these rulcs is to explicitly relate the semantic (sub)structures to possible syntactic counterparts. The rnappizJg pro- cess is driven by the semantic input structure that is traversed ... guided by semantic informa- tion in a top-down fashion. The benefits of integrated semantics are mani- fold. Elegant analyses of linguistic phenomena are possible that relate syntactic and semantic ... top-down genera- tots using an integrated semantics cannot occur in the separate-semantics approach. Expansion of grammar rules can be controlled by the semantic representation if each rule application...
  • 6
  • 256
  • 0
Báo cáo khoa học: "Head-driven Transition-based Parsing with Top-down Prediction" pdf

Báo cáo khoa học: "Head-driven Transition-based Parsing with Top-down Prediction" pdf

Ngày tải lên : 16/03/2014, 19:20
... Conclusion This paper presents a novel head -driven parsing al- gorithm and empirically shows that it is as practi- cal as other dependency parsing algorithms. Our head -driven parser has potential for handling ... proposed algo- rithm achieves comparable results with other data -driven dependency parsing algorithms. 1 Introduction Transition-based parsing algorithms, such as shift- reduce algorithms (Nivre, ... top-down head- driven transition-based parsing algorithm which can parse complex structures that are not trivial for shift- reduce parsers. The deductive system is very similar to Earley parsing (Earley,...
  • 9
  • 312
  • 0
Báo cáo khoa học: "Confidence-Weighted Learning of Factored Discriminative Language Models" pptx

Báo cáo khoa học: "Confidence-Weighted Learning of Factored Discriminative Language Models" pptx

Ngày tải lên : 17/03/2014, 00:20
... POS features, confidence- weighted learning is slightly better than perceptron, and confidence- weighted learning with soft margin is the best (9.08% and 5.04% better than perceptron and confidence- weighted ... language mod- els. (DLM 0) or factored features by standard percep- tron (DLM 1), confidence- weighted learning (DLM 2) and confidence- weighted learning with soft mar- gin (DLM 3). All discriminative language ... dataset, we trained dis- criminative language models by standard percep- tron, confidence- weighted learning and confidence- weighted learning with soft margin. We then trained the weights of a...
  • 6
  • 300
  • 0
Báo cáo khoa học: "Confidence Measure for Word Alignment" potx

Báo cáo khoa học: "Confidence Measure for Word Alignment" potx

Ngày tải lên : 17/03/2014, 01:20
... links from dif- ferent alignments. 3 Alignment Link Confidence Measure 3.1 Definition Similar to the sentence alignment confidence mea- sure, the confidence of an alignment link a ij in the sentence ... area, most research on confidence measure focus on the confidence of MT output: how accurate a translated sentence is. (Gandrabur and Foster, 2003) used neural-net to improve the confidence estimate ... for sentence and word confidence estimation. (Quirk, 2004) trained a sentence level confidence mea- sure using a human annotated corpus. (Bach et al., 2008) used the sentence-pair confidence scores estimated...
  • 9
  • 317
  • 0
Báo cáo khoa học: "Active Learning with Confidence" doc

Báo cáo khoa học: "Active Learning with Confidence" doc

Ngày tải lên : 17/03/2014, 02:20
... margin it has low confidence compared to the second. Both the margin value and confidence should be considered in choosing which example to label. We present active learning with confidence us- ing ... margin (Tong and Koller, 2001). Common intuition equates large margins with high prediction confidence. However, confidence and margin are two distinct properties. For example, an instance may receive a ... We present a method for in- corporating confidence into the margin by us- ing a newly introduced online learning algo- rithm and show empirically that confidence improves active learning. 1 Introduction Successful...
  • 4
  • 243
  • 0