Homa B. Hashemi

Stock market value prediction using neural networks

Neural networks, as an intelligent data mining method, have been used in many different challenging pattern recognition problems such as stock market prediction. However, there is no formal method to determine the optimal neural network for prediction purpose in the literature. In this paper, two kinds of neural networks, a feed forward multi layer Perceptron (MLP) and an Elman recurrent network, are used to predict a companys stock value based on its stock share value history. The experimental results show that the application of MLP neural network is more promising in predicting stock value changes rather than Elman recurrent network and linear regression method. However, based on the standard measures that will be presented in the paper we find that the Elman recurrent network and linear regression can predict the direction of the changes of the stock value better than the MLP.

Protein Fold Pattern Recognition Using Bayesian Ensemble of RBF Neural Networks

Protein fold pattern recognition has been one of the most challenging problems in biology during the last 40 years. Recently due to the vast improvement in machine learning and pattern recognition methods many computer scientists have applied these methods to solve this problem. However, protein folding problem is much more complicated than ordinary machine learning problems because of its natural complexity imposed by the high dimensionality of feature space and diversity of different protein fold classes. To deal with such a challenging problem, we use an ensemble classifier model by applying MLP and RBF Neural Networks and Bayesian ensemble method. Also we have used the Laplace estimation method in order to smooth confusion matrices of the base classifiers. Experimental results imply that RBF Neural Network holds better Correct Classification Rate (CCR) compared to other common classification methods such as MLP networks. Our experiments also show that the Bayesian fusion method can improve the correct classification rate of proteins up to 20% with the final CCR of 59% by reducing both bias and variance error of the RBF classifiers, on a benchmark dataset containing 27 SCOP folds.

Mining a Persian-English comparable corpus for cross-language information retrieval

Knowledge acquisition and bilingual terminology extraction from multilingual corpora are challenging tasks for cross-language information retrieval. In this study, we propose a novel method for mining high quality translation knowledge from our constructed Persian-English comparable corpus, University of Tehran Persian-English Comparable Corpus (UTPECC). We extract translation knowledge based on Term Association Network (TAN) constructed from term co-occurrences in same language as well as term associations in different languages. We further propose a post-processing step to do term translation validity check by detecting the mistranslated terms as outliers. Evaluation results on two different data sets show that translating queries using UTPECC and using the proposed methods significantly outperform simple dictionary-based methods. Moreover, the experimental results show that our methods are especially effective in translating Out-Of-Vocabulary terms and also expanding query words based on their associated terms.

Application of ensemble models in web ranking

One of the most important parts of search engines is the ranking unit. Many different classical ranking algorithms based on content (such as TF-IDF and BM25) and connectivity (such as HITS and PageRank) have been used in web search engines to find pages in response to a user query. Although these algorithms have been developed to improve retrieval results, none of them can take advantage of power of contents as well as useful link structures. Thus, it remains a challenging research question how to effectively combine these available information to maximize search accuracy. In this study, we investigate the application of different ensemble models in ranking algorithms. Some of them are simple such as Sum, Product and Borda rule, and the others are more complicated methods. We present three complex ensemble approaches. The first one is OWA operator to merge the results of various ranking algorithms. In the second approach, a state-of-the-art method, simulated click-through data, is used to learn how to combine many content and connectivity features of web pages. Moreover, we present a modified version of SVM classifier customized for ranking problems as the third complex fusion approach. The proposed methods are evaluated using the LETOR and dotIR benchmark data sets. The experimental results show that in most of the cases ensemble methods give better results and the improvements are very encouraging. These results also show that the OWA and SVM fusion methods are promising respect to other ensemble models.

Creating a Persian-English comparable corpus

Multilingual corpora are valuable resources for cross-language information retrieval and are available in many language pairs. However the Persian language does not have rich multilingual resources due to some of its special features and difficulties in constructing the corpora. In this study, we build a Persian-English comparable corpus from two independent news collections: BBC News in English and Hamshahri news in Persian. We use the similarity of the document topics and their publication dates to align the documents in these sets. We tried several alternatives for constructing the comparable corpora and assessed the quality of the corpora using different criteria. Evaluation results show the high quality of the aligned documents and using the Persian-English comparable corpus for extracting translation knowledge seems promising.

ArgRewrite: A Web-based Revision Assistant for Argumentative Writings

While intelligent writing assistants have become more common, they typically have little support for revision behavior. We present ArgRewrite, a novel web-based revision assistant that focus on rewriting analysis. The system supports two major functionalities: 1) to assist students as they revise, the system automatically extracts and analyzes revisions; 2) to assist teachers, the system provides an overview of students’ revisions and allows teachers to correct the automatically analyzed results, ensuring that students get the correct feedback.

A Corpus of Annotated Revisions for Studying Argumentative Writing.

This paper presents ArgRewrite, a corpus of between-draft revisions of argumentative essays. Drafts are manually aligned at the sentence level, and the writer’s purpose for each revision is annotated with categories analogous to those used in argument mining and discourse analysis. The corpus should enable advanced research in writing comparison and revision analysis, as demonstrated via our own studies of student revision behavior and of automatic revision purpose prediction.

An Evaluation of Parser Robustness for Ungrammatical Sentences.

For many NLP applications that require a parser, the sentences of interest may not be well-formed. If the parser can overlook problems such as grammar mistakes and produce a parse tree that closely resembles the correct analysis for the intended sentence, we say that the parser is robust. This paper compares the performances of eight state-of-the-art dependency parsers on two domains of ungrammatical sentences: learner English and machine translation outputs. We have developed an evaluation metric and conducted a suite of experiments. Our analyses may help practitioners to choose an appropriate parser for their tasks, and help developers to improve parser robustness against ungrammatical sentences.

A Tool for Summarizing Students’ Changes across Drafts

In the context of popular peer review educational approaches, teachers wish to know whether the students are benefiting from peer reviews and applying the changes in their second drafts. This paper presents a tool for teachers that compares information about students first and second drafts of papers focusing on the extent and type of changes in the papers.

Turn-Taking Behavior in a Human Tutoring Corpus.

Analysis of turn-taking in tutoring dialogues can be helpful to understand the procedure of tutoring and also the influence with regard to demographics between students and the tutor. In this research, we analyze turn-taking behavior between students in a human-human spoken tutoring system. Our approach is to learn turn-taking models using dialog activity state sequences and then we measure the association of these models with students’ demographic features (gender and education). The experimental results show that female students speak simultaneously longer with the tutor than male students, female activities are less than male activities and also the tutor speaks longer with students who have lower pre-test score.