Báo cáo khoa học: "Rich bitext projection features for parse

Báo cáo khoa học: "Rich bitext projection features for parse reranking" potx

... 0.04. For the two parses of the full sentences contain- ing the NPs in ﬁgure 1 and ﬁgure 2, we sum over 7 POSParents and get a value of 0.27 for parse 1 and 0.11 for parse 2. The lower value for parse 2 ... 3 April 2009. c 2009 Association for Computational Linguistics Rich bitext projection features for parse reranking Alexander Fraser Renjing Wang Institute for...

Ngày tải lên : 17/03/2014, 22:20

9
336
0

Báo cáo khoa học: "Data-Deﬁned Kernels for Parse Reranking Derived from Probabilistic Models" docx

... its usefulness for reranking. We performed experiments on parse reranking using a neural network based statistical parser as both the probabilistic model and the source of the list of candidate parses. ... model of parsing. For this we use a statistical parser which has previously been shown to achieve state-of-the-art performance, namely that proposed in (Henderson, 2003). This parse...

Ngày tải lên : 08/03/2014, 04:22

8
466
0

Tài liệu Báo cáo khoa học: "Exploring Syntactic Structural Features for Sub-Tree Alignment using Bilingual Tree Kernels" docx

... pairs are further parsed by Stanford parser (Klein and Manning, 2003) on both the English and Chinese sides. We manually annotate the sub-tree alignment for the automatically parsed tree pairs ... sub-tree alignment along with some plain features. Our study reveals that the structural features embedded in a bilingual parse tree pair are very effective for sub-tree alignment...

Ngày tải lên : 20/02/2014, 04:20

10
467
0

Tài liệu Báo cáo khoa học: "Exploiting Non-local Features for Spoken Language Understanding" pptx

... linguis- tic features are located within ﬁve tokens. For comparison, we exploit the two groups of non- local syntax parser-based features; we use Collins parser and extract this type of features ... with word features and iteratively add them one-by-one so that we achieve the best performance. Table 1 shows the empirical results of local features, syntactic parser-based features,...

Ngày tải lên : 20/02/2014, 12:20

8
396
0

Báo cáo khoa học: "Semi-supervised Convex Training for Dependency Parsing" potx

... and all words respectively. Features For simplicity, in current work, we only used two sets of features word-pair and tag-pair indicator features, which are a subset of features used by other researchers ... unlabeled data resource. Our goal is to obtain better performance than a purely supervised approach without unreasonable computational effort. Unfortunately, although signiﬁcant...

Ngày tải lên : 08/03/2014, 01:20

9
304
0

Báo cáo khoa học: "A Generative Lexicon Perspective for Adjectival Modification" potx

... into on- tological domains for modelling some forms of metaphors. • Types are not sufficiently 'constrained' to ac- count for the constraints holding, for each predicate, on the ... in particular for the Telic role, (explored e.g. in the EuroWordNet project, the European WordNet). Qualias are well-designed and useful for nouns, but look more artificial for other...

Ngày tải lên : 23/03/2014, 19:20

7
217
0

Báo cáo khoa học: "A Probabilistic Modeling Framework for Lexical Entailment" potx

... Association for Computational Linguistics:shortpapers, pages 558–563, Portland, Oregon, June 19-24, 2011. c 2011 Association for Computational Linguistics A Probabilistic Modeling Framework for Lexical ... (e.g. parsing) aiming at high performance. Nevertheless, simple entailment methods, per- forming at the lexical level, provide strong baselines which most systems did not outperform...

Ngày tải lên : 30/03/2014, 21:20

6
376
0

Tài liệu Báo cáo khoa học: "Part-of-Speech Tagging for Twitter: Annotation, Features, and Experiments" pdf

... ar- bitrary local features in a log-linear model. Our base features include: a feature for each word type, a set of features that check whether the word con- tains digits or hyphens, sufﬁx features up ... weight. 7 We compute features for membership in the top N items by this metric, for N ∈ {1000, 2000, 3000, 5000, 10000, 20000}. TAGDICT: Traditional tag dictionary. We add f...

Ngày tải lên : 20/02/2014, 04:20

6
669
0

Tài liệu Báo cáo khoa học: "Identifying Noun Product Features that Imply Opinions" pdf

... features which have implied opinions and normal features which have no opinions, e.g., “voice quality” and “battery life.” For normal features, people often can have different opinions. For ... 1541 4308 2306 # Noun features 326 38 173 222 Table 1. Experimental datasets An issue for judging noun features implying opinions is that it can be subjective. So for the gold...

Ngày tải lên : 20/02/2014, 05:20

6
361
0

Tài liệu Báo cáo khoa học: "Learning with Unlabeled Data for Text Categorization Using Bootstrapping and Feature Projection Techniques" doc

... the voting scores of all features. First of all, we must calculate the voting ratio of each category for all features. Since elements with a high TF-IDF value in projections of a feature must ... readily available and plentiful. Therefore, this paper advocates using a bootstrapping framework and a feature projection technique with just unlabeled data for text categorization. T...

Ngày tải lên : 20/02/2014, 16:20

8
443
0