Báo cáo khoa học: "Hierarchical Sequential Learning for Extracting Opinions and their Attributes" ppt

... 11-16 July 2010. c 2010 Association for Computational Linguistics Hierarchical Sequential Learning for Extracting Opinions and their Attributes Yejin Choi and Claire Cardie Department of Computer ... (e.g. Kim and Hovy (2005), Popescu and Etzioni (2005), Breck et al. (2007)), determining their polarity (e.g. Hu and Liu (2004), Kim and Hovy (2004), Wilson et al. (2...

Ngày tải lên: 17/03/2014, 00:20

... part-of-speech (POS) tagger for Chinese, and Toutanova and Cherry (2009) learned a joint model of lemmatization and POS tagging which outperformed a pipelined model. Adler and Elhadad (2006) presented ... where there exists labeled training data for all domains and the goal is to improve performance on all of them. Ando and Zhang (2005) utilized a multi- task learner within t...

Ngày tải lên: 30/03/2014, 21:20

... well-formed text and learner text? We recreate a state-of-the-art preposition usage system (Tetreault and Chodorow (2008), hence- forth T&C08) originally trained with lexical fea- tures and ... tree and dependency triples returned by the Stanford parser for this phrase. 3.1 Baseline System The work of Chodorow et al. (2007) and T&C08 treat the tasks of preposition selectio...

Ngày tải lên: 30/03/2014, 21:20

... consis- tency (Halliday and Hasan, 1976), and variation, which influence people’s assessment of discourse (Levelt and Kelter, 1982) and generated output (Belz and Reiter, 2006; Foster and Oberlander, 2006). Also, ... Halliday and Hasan, 1976) on the one hand, and variation (to improve text quality and readability) on the other hand (Belz and Reiter, 2006; Foster and Oberl...

Ngày tải lên: 07/03/2014, 22:20

... al., 2007; Arnold et al., 2007; Chan and Ng, 2007; Daume, 2007; Jiang and Zhai, 2007; Reichart and Rappoport, 2007; Andreevskaia and Bergler, 2008), multi-task learning (Caruana, 1997; Re- ichart ... cross-feature-space learning. Wu and Oard (2008) proposed to handle the cross- language learning problem by translating the data into a same language and applying kNN on the late...

Ngày tải lên: 08/03/2014, 00:20

Ngày tải lên: 08/03/2014, 01:20

Ngày tải lên: 08/03/2014, 01:20

... ingredient for SCL, and they should align well with the NLP task. For PoS tagging and Sentiment Analysis, features on the word level are intuitively well-related to the problem at hand. For the ... the datasets (Dredze et al., 2007) and a bug in their system (Shimizu and Nakagawa, 2007), their re- sults are inconclusive. 1 Thus, the effectiveness of SCL is rather unexplored...

Ngày tải lên: 08/03/2014, 21:20

... decision trees, combined with a bigram model of accent and boundary patterns. Their method achieved an accuracy of 84% for accent, 71% for IPB, and 84% for break index detection at the syllable level. ... sam- ples added for the first 20 iterations, and the av- erage labeling error rate of those samples for the self-labeled positive and negative classes for two methods. T...

Ngày tải lên: 23/03/2014, 16:21

... and Cohen’s Kappa (κ) were then used to quantify the level of agreement. For brevity we refer the reader to (Artstein and Poesio, 2005) and (Hripc- sak and Rothschild, 2004) for formulation and ... single-view, where the former generate multiple redundant (or semi-redundant) ‘views’ of a data sample and per- form mutual bootstrapping. This idea was for- malised by Blum and...

Ngày tải lên: 23/03/2014, 18:20