Báo cáo khoa học: "Using Machine Learning to Maintain Rule-based Named-Entity Recognition and Classification Systems" pdf

... Using Machine Learning to Maintain Rule-based Named-Entity Recognition and Classification SystemsGeorgios Petasis †, Frantz Vichot §, Francis ... alternativeuse of machine learning in named-entity recog-nition and classification. Instead of constructingan autonomous NERC system, the system con-structed with the use of machine learning assistsin ... regard-ing mainly the classification grammar. In fact,some of our classification rules were found to betoo general, leading to wrong classifications.For example, according to one of the rules,...

Báo cáo khoa học: "Using Machine-Learning to Assign Function Labels to Parser Output for Spanish" ppt

... success-fully to other languages and treebank re-sources. In addition to tag assignment ac-curacy and f-scores we also present re-sults of a task-based evaluation. We usethree machine- learning ... context means greater susceptibility to parse errors. Another factor to consider is the factthat we trained and adjusted parameters on gold-standard trees, and the model learned may rely onfeatures ... attributed to two main factors. Firstly,the mapping from Cast3LB tags to LFG grammat-ical functions is not one -to- one. For example threeCast3LB tags (CC, MOD and ET) are all mapped to LFG ADJUNCT....

Báo cáo khoa học: "Using Machine Learning to Explore Human Multimodal Clariﬁcation Strategies" ppt

... generation and input leads to more robust interaction (Oviatt, 2002) and re-duced cognitive load (Oviatt et al., 2004). In thispaper we investigate the use of machine learning (ML) to explore ... distribu-tions into account and help to avoid sparse data.Second, most of our features are highly positivelyskewed. Some ML methods (such as the standardextension of the Na¨ıve Bayes classiﬁer to handlenumeric ... discussRule Induction and Decision Trees since they arethe easiest to interpret (and to implement in stan-dard rule-based dialogue systems). For both weexplain the results obtained by MDL and selectiveBayes,...

Báo cáo khoa học: "Using Reinforcement Learning to Build a Better Model of Dialogue State" pdf

... student state and what are the bestactions for a tutor to consider, one must have aflexible system that allows one to easily test dif-ferent configurations of states and actions. To ac-complish ... collapsing functions allowthe user to easily constrain the trajectory space. To further reduce the search space for the MDP, ourtool allows the user to specify a threshold to com-bine states that occur ... way to approximate their learning gain in the middle ofa session.The output of the tool is a probability matrixover the user-specified states and actions. Thismatrix is then passed to an MDP toolkit...

Báo cáo khoa học: "Using Machine Learning Techniques to Build a Comma Checker for Basque" pdf

... chunks to the beginning and to the end of the sentence  number of nominal chunks to the begin-ning and to the end of the sentence number of subordinate-clause marks to the beginning and to ... the style and the punctuation of the texts. To be precise, we have experimented using machine learning techniques for the special case of the comma, to evaluate their performance and to analyse ... Related work Machine learning techniques have been applied in many fields and for many purposes, but we have found only one reference in the literature related to the use of machine learning techniques...

Báo cáo khoa học: "Using Machine Learning Techniques to Interpret WH-questions" potx

... 69/6 Topic Itself clues Initial component, Attribute cluesTopic 193/9 Total NOUNs Total ADJs, Total AJPs, Total PRONOUNsFocus 226/10 Initial component Topic Itself clues, Total NOUNs, Total ... technologies.Heckerman and Horvitz (1998) and Horvitz etal. (1998) used hand-crafted models and super-vised learning to construct Bayesian models thatpredict users’ goals and needs for assistance ... methods (Salton and McGill,1983) with “shallow” NLP techniques. One ap-proach to the QA task consists of applying the IRmethods to retrieve documents relevant to a user’squestion, and then using...

Báo cáo khoa học: "Applying Machine Learning to Chinese Temporal Relation Resolution" pptx

... have incorporated machine learning methods to coordinate multiple linguistic features for example in accent restoration (Yarowsky, 1994) and event classification (Siegel and McKeown, 1998), ... of the indicators BEFORE and AFTER respectively. Consider the most extreme case where an event consists of at most 4 temporal indicators before and 2 after. We set m and n to 4 and 2 initially. ... be-longing to ci. 4 Experiment Setup and Evaluation Several experiments have been designed to evalu-ate the proposed learning approaches and to reveal the impact of linguistic features on learning...

Báo cáo khoa học: "Using Mutual Information to Resolve Query Translation Ambiguities and Query Term Weighting" doc

... scheme is to give a large weight to the best candidate and divide the remaining quantity to assign equal weights to the rest of the candidates. In other words, the weight for the best candidate, ... pair candidate between wl and w2 are (motorcar, air), (automobile, air), and (car, air). Here because the weight of the word pairs (automobile, air) is W, = 0.83, the word "automobile" ... from the morphological analyzer will have to be entered into the translation process, which in and of itself will generate extraneous words, due to one -to- many mapping in the bilingual dictionary....

Báo cáo khoa học: "A Machine Learning Approach to German Pronoun Resolution" docx

... German, we were able to obtain thesystem submitted by (Curran and Clark, 2003) to the 2003 CoNLL competition. In order to run therecogniser, the data needs to be tokenised, tagged and lemmatised, ... pa-per.(McCarthy and Lehnert, 1995) were amongthe ﬁrst to use machine learning for coreferenceresolution. RESOLVE was trained on data fromMUC-5 English Joint Venture (EJV) corpus and used the ... million tokens.The reported F-measure for pronoun resolution is81.5. However, (Morton, 2000) only attempts to resolve singular pronouns, and there is no mentionof what percentage of total pronouns...

Báo cáo khoa học: " Improving Machine Learning Approaches to Coreference Resolution" potx

... extensions to the Soon etal. corpus-based approach. First, we propose and evaluate three extra-linguistic modiﬁcations to the machine learning framework, which together pro-vide substantial and statistically ... Insections 2 and 3, we present the baseline corefer-ence system and explore extra-linguistic modiﬁca-tions to the machine learning framework. Section 4describes and evaluates the expanded feature ... work of Soon etal. (2001) and, to our knowledge, pro-duces the best results to date on the MUC-6 and MUC-7 coreference resolution datasets — F-measures of 70.4 and 63.4, re-spectively. Improvements...

Xem thêm