... 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 c i . 4 Experiment Setup and Evaluation Several experiments have been designed to evalu- ate the proposed learning approaches and to reveal the impact of...
Ngày tải lên: 31/03/2014, 03:20
... expensive and time-consuming to create. 2 Throughout we will use relation instance to refer to a fact (e.g. ORGHasEmployee(Apple, Steve Jobs)), while we will use relation text to refer a ... predicate-argument structure and em- ploy coreference. Section 3 describes our particular approach to pattern and relation instance scoring and selection. Another research strand...
Ngày tải lên: 20/02/2014, 04:20
Tài liệu Báo cáo khoa học: " Applying Co-Training to Reference Resolution" ppt
... manual labeling work and still produce a classifier with an ac- ceptable performance. 1 Introduction A major obstacle for natural language processing systems which analyze natural language texts or utterances ... began to experiment with weakly supervised machine learning algorithms such as Co-Training (Blum and Mitchell, 1998). Among others Co-Training was applied to documen...
Ngày tải lên: 20/02/2014, 21:20
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 use three machine -learning ... context means greater susceptibility to parse errors. Another factor to consider is the fact that we trained and adjusted parameters on gold- standard trees, and the model lea...
Ngày tải lên: 08/03/2014, 02:21
Báo cáo khoa học: "Using Machine Learning to Explore Human Multimodal Clarification Strategies" ppt
... distribu- tions into account and help to avoid sparse data. Second, most of our features are highly positively skewed. Some ML methods (such as the standard extension of the Na ¨ ıve Bayes classifier to handle numeric ... lead to repetitive action, i.e. if a screen output was once shown to this user, and the user has previously used or referred to the screen, the screen will be u...
Ngày tải lên: 23/03/2014, 18:20
Báo cáo khoa học: "Using Machine Learning to Maintain Rule-based Named-Entity Recognition and Classification Systems" pdf
... 1998). ThesystemdevelopedforItalianinECRAN (Cuchiarelli et al., 1998), uses unsupervised learning to expand a manually constructed sys- tem and improve its performance. The learning algorithm tries to supplement the manually con- structed ... labelled examples are used to train the classifiers and then, unlabelled examples are presented to the classifiers. Examples that cause...
Ngày tải lên: 23/03/2014, 19:20
Báo cáo khoa học: "Using Reinforcement Learning to Build a Better Model of Dialogue State" pdf
... student state and what are the best actions for a tutor to consider, one must have a flexible system that allows one to easily test dif- ferent configurations of states and actions. To ac- complish ... collapsing functions allow the user to easily constrain the trajectory space. To further reduce the search space for the MDP, our tool allows the user to specify a threshold to...
Ngày tải lên: 24/03/2014, 03:20
Báo cáo khoa học: "A Uniform Approach to Underspecification and Parallelism" doc
... unification, and present some results about its formal proper- ties and its relation to other formalisms. Section 3 demonstrates the application to scope underspeci- fication, to ellipsis, and to the ... source and the target clause (i.e., the first and the second clause of a parallel construction; the termi- nology is taken over from the ellipsis literature), and X...
Ngày tải lên: 31/03/2014, 21:20
Tài liệu Báo cáo khoa học: "The Use of Ooject-Special Knowledge in Natural Language Processing" doc
... by adding the new state information to the token in the ACTOR slot of the state description. Thus the bottle token is updated to include the gtven CONNECTOR description. For the purposes ... ta important to understand how OPUS differs from previous inference strateKies in natural language processing. To emphasize the original contributions of OPUS we will compare it to R...
Ngày tải lên: 21/02/2014, 20:20
Tài liệu Báo cáo khoa học: "TOWARDS A CORE VOCABULARY FOR SYSTEM A NATURAL LANGUAGE" potx
... take into account tile research goals pursued. For a natural language system which is sup- posed to analyze and generate texts, to engage in dialogues with users, and which is to acquire ... Motiva!ion Rcasearch on natural language processing sys- tems today strives for the construction of robust and portable systems) A system is robust, if it can handle a large...
Ngày tải lên: 22/02/2014, 10:20