Báo cáo khoa học: "Learning Script Knowledge with Web Experiments" doc

... Sweden, 11-16 July 2010. c 2010 Association for Computational Linguistics Learning Script Knowledge with Web Experiments Michaela Regneri Alexander Koller Department of Computational Linguistics ... unsuper- vised learning of the events that make up a script, along with constraints on their temporal ordering. We collect natural- language descriptions of script- specific event sequ...

Ngày tải lên: 07/03/2014, 22:20

... of translation edit rate with targeted human annotation. In AMTA. Valentin I. Spitkovsky, Hiyan Alshawi, and Daniel Juraf- sky. 2011. Lateen em: Unsupervised training with multiple objectives, ... different metrics M k (h) for evaluating the quality of h. Without loss of gen- erality, we assume metric scores are bounded be- tween 0 and 1, with 1 being perfect. Each hypoth- esis h can be...

Ngày tải lên: 19/02/2014, 19:20

... e(D, T) be the coverage rate of the feature set T with respect to a set of con- texts D, i.e., the ratio of the number of the occur- rences with at least one feature in their local con- texts ... helps to avoid the bias to- ward the selection of fewer features, since with fewer features, there are more occurrences without features in contexts, and their context vectors will be zero valu...

Ngày tải lên: 20/02/2014, 16:20

... bijec- tively with those of α. • The terminal-labeled frontier nodes of γ are aligned (many-to-many) with those of α. In the substitution operation, an aligned pair of substitution nodes is rewritten with ... previous work (Chiang, 2007), with differences shown in Table 2. Rules with non- terminals were extracted from a subset of the data (labeled “Core” in Table 2), and rules witho...

Ngày tải lên: 07/03/2014, 22:20

... experimented on a document clustering task. 1 Introduction In natural language processing (NLP) and text min- ing, clustering methods are crucial for various tasks such as document clustering. ... authors also justified their method by showing that with feature hashing, dot- product is unbiased, and the length of each vector is well-preserved with high probability under some conditions. Pl...

Ngày tải lên: 20/02/2014, 05:20

... again SVM with 67.9% test precision. Compared with the baseline (51.5%) and human agreement (79.8%), this again is a very promising result, especially for a multi-classification task with such ... annotations would be consistent with this distribution. Thus, the baseline will be an annotator who knows the global distribution and annotates in accordance with it, but does not re...

Ngày tải lên: 20/02/2014, 12:20

... manually created document ontology to model the content of an underlying document col- lection. While the primary usage of ontologies is as a means of organizing and navigating document collections, ... Fixed hLDA (Reisinger and Pa¸sca, 2009) where the set of topics associated with a document is known a priori. In both cases, document labels are mapped to constraints on the set of topics on...

Ngày tải lên: 07/03/2014, 22:20

... the baseline at the 95% confidence level are labelled with a single star, at the 99% level with two. with a 3-gram language model smoothed with modi- fied Knesser-Ney discounting (Chen and Goodman, 1998), ... phrase-pair spans filled with source- language linguistically motivated labels. We show how we can employ this crucial input to extract and train a hierarchical translation struct...

Ngày tải lên: 20/02/2014, 04:20

... words within a document as a context. To extract contexts from a document, we use sliding window techniques (Maarek et al., 1991). The window is a slide from the first word of the document ... title word with the maximum similarity score with a word W, c max is the category of the title word T max , and T secondmax is other title word with the second high similarity score with...

Ngày tải lên: 20/02/2014, 16:20

... the complexity of parse grammars with hand-coded rules turned out to be much more difficult than expected, if not impos- sible. Newer statistical approaches with often only very limited context ... trained on very large corpora. To cope with the complexity of unrestricted text, parse rules in any kind of formalism will have to consider a complex context with many different mor...

Ngày tải lên: 22/02/2014, 03:20