Báo cáo khoa học: "Optimal Constituent Alignment with Edge Covers for Semantic Projection" potx
... pages 1161–1168, Sydney, July 2006. c 2006 Association for Computational Linguistics Optimal Constituent Alignment with Edge Covers for Semantic Projection Sebastian Padó Computational Linguistics Saarland ... drops by 8.3% for Forward and by almost 6% for Perf- Match and EdgeCover. Nevertheless, both Perf- Match and EdgeCover outperform the local For- ward model. PerfM...
Ngày tải lên: 31/03/2014, 01:20
... words for a particular tar- get alignment. This feature indicates whether a given alignment has the highest translation score of all the candidate alignments for a given tar- get word. For the ... many-to-one word alignments, where each source word is aligned with zero or one target words, and therefore each target word can be aligned with many source words. Each source word is l...
Ngày tải lên: 20/02/2014, 11:21
... Unfortunately, both approaches are problematic, but in different ways. In the case of discriminative alignment mod- els, manual alignment data is required for train- ing, which is problematic for ... such parsers. Third, the “correct” alignment annotation for differ- ent tasks may vary: for example, relatively denser or sparser alignments may be optimal for different ap- proac...
Ngày tải lên: 17/03/2014, 00:20
Báo cáo khoa học: "Automatic Syllabification with Structured SVMs for Letter-To-Phoneme Conversion" doc
... generate ONC tags for orthographic forms without at least a cursory knowledge of the language and its princi- ples. For English, tagging the syllabified training set with ONC tags is performed by the ... We report L2P performance without any syllabification infor- mation, with perfect dictionary syllabification, and with our small learned models of syllabification. L2P performance with...
Ngày tải lên: 17/03/2014, 02:20
Báo cáo khoa học: "Reducing Wrong Labels in Distant Supervision for Relation Extraction" potx
... lexico-syntactic forms. We use the entity pairs extracted by this rule. DS uses a knowledge base to create labeled data for relation extraction by heuristically matching en- tity pairs. A knowledge base ... LD end if end for return LD types to distinguish the sentences that express differ- ent relations with the same dependency path, such as “ABBA was formed in Stockholm.” and “ABBA was...
Ngày tải lên: 23/03/2014, 14:20
Báo cáo khoa học: "Generalizing over Lexical Features: Selectional Preferences for Semantic Role Classification" docx
... is specially relevant for out-of-domain data. Our findings suggest that selectional pref- erences have potential for improving a full system for Semantic Role Labeling. 1 Introduction Semantic Role Labeling ... preferences are able to generalize and perform better than lexical features in a large dataset for semantic role classifi- cation. The best results are obtained with a no...
Ngày tải lên: 23/03/2014, 17:20
Báo cáo khoa học: "A Grammar-driven Convolution Tree Kernel for Semantic Role Classification" doc
... either a semantic argu- ment or a non-argument while semantic role classi- fication involves classifying each semantic argument identified into a specific semantic role. This paper focuses on semantic ... target verbs or nouns and some constituents of the sentence. In particular, for each predicate (target verb or noun) all the constituents in the sentence which fill semanti...
Ngày tải lên: 23/03/2014, 18:20
Báo cáo khoa học: "A Framework of Feature Selection Methods for Text Categorization" potx
... categories, i.e., / i i A B . The terms with a high ratio are often referred to as the terms with high category information. These two measurements form the basis for all the measurements that are ... following formula (Yang and Pedersen, 1997) ( , ) log( ( | )) log( ( )) i i I t c P t c P t = − 694 Therefore, this method might perform badly when common terms are informative f...
Ngày tải lên: 30/03/2014, 23:20
Báo cáo khoa học: "Optimal rank reduction for Linear Context-Free Rewriting Systems with Fan-Out Two" pot
... (1) (without repeti- tions) along with some additional terminal sym- bols (with possible repetitions). For a mathematical definition of LCFRS we re- fer the reader to (Weir, 1992, p. 137). Informally, in ... = x 1 and r.right = x 2 . The set of backward edges for r is defined as B r = {(x, x ′ ) | (x, x ′ ) ∈ E r , x ≺ p r.left, x ′ ∈ r}. The set of for- ward edges for r is defined sy...
Ngày tải lên: 16/03/2014, 23:20
Báo cáo khoa học: "Coordinate Structure Analysis with Global Structural Constraints and Alignment-Based Local Features" pot
... whole sentence with no subsidiary information except for the parts-of-speech of words. As it assumes minimal information about syn- tactic constructs, our method provides a baseline for future work ... previ- ous studies on coordination, but these studies often dealt with a restricted form of coordination with apparently too much information provided from outside. Sometimes it was a...
Ngày tải lên: 23/03/2014, 16:21