Search

Judicial decisions are an important part of modern democratic societies. In this paper, I present results of multi-label classification of Chinese judicial documents. The experiments employ the same corpus that was used in Chinese AI & Law Challenge(CAIL) 2018.

Real data with privacy and confidentiality concerns are not often available or are too expensive to afford in respect of both time and money. In this situation, it is a good alternative to use synthetic data. The objective of this research is to generate realistic synthetic data so that people can use it freely. We propose a synthetic data generation model based on boundary-seeking generative adversarial networks (BGANs)–designated as medical BGAN or medBGAN and compare its performances with an existing method medical GAN (medGAN). We aim to perform the investigation on several datasets in two different domains: electronic health records (EHRs) in the medical domain and a crime dataset in the City of Los Angeles Police Department. Firstly, we train the models and generate synthetic data by using these trained models. We then analyze and compare the models' performance by applying some statistical methods (dimension-wise average and Kolmogorov-Smirnov test) and two machine learning tasks (association rule mining and prediction). The comprehensive analysis of this study shows that the proposed model is more efficient in generating realistic synthetic data than those generated using medGAN.

Item difficulty is a key parameter for test items. Learning this parameter in an IRT-based context with statistical methods or machine learning-based approaches is a typical research topic in the field of educational assessment. This paper reports an exploration of using a betting mechanism to assess test takers' intrinsic uncertainty about the answers to a special type of Chinese cloze tests. Uncertainty about the answers influences test takers' behavior in betting on the candidate answers, so statistics of betting behavior serve as a conceivable incarnation of item difficulties. The proposed approach is innovative in that there is no known previous work that employed economics-based methods for this educational data mining problem. The proposed method was evaluated with more than a thousand realistic test items and with 48 native speakers of Chinese. Experimental results show encouraging connections between betting behavior and item difficulty. More specifically, we observed that participants may even lose money in very difficult tests, and they spent longer time in more challenging tests.

In this paper, we demonstrate and discuss results of our mining the abstracts of the publications in Harvard Business Review between 1922 and 2012. Techniques for computing n-grams, collocations, basic sentiment analysis, and named-entity recognition were employed to uncover trends hidden in the abstracts. We present findings about international relationships, sentiment in HBR's abstracts, important international companies, influential technological inventions, renown researchers in management theories, US presidents via chronological analyses., 6 pages, 14 figures, Proceedings of 2012 International Conference on Technologies and Applications of Artificial Intelligence

Subjective statements provide qualitative evaluation of the financial status of the reporting corporations, in addition to the quantitative information released in US 10-K filings. Both qualitative and quantitative appraisals are crucial for quality financial decisions. To extract such opinioned statements from the reports, we built tagging models based on the conditional random field (CRF) techniques, considering a variety of combinations of linguistic factors including morphology, orthography, predicate-argument structure, syntax and simple semantics. The CRF models showed reasonable effectiveness to find opinion holders in experiments when we adopted the popular MPQA corpus for training and testing. We also identified opinion patterns in the form of multi-word expressions (MWEs), which is a major contribution of our work. In a recent article published in a prestigious journal in Finance, single words, rather than MWEs, were reported to indicate positive and negative judgments in financial statements.

Subjective assertions in financial statements influence the judgments of market participants when they assess the value and profitability of the reporting corporations. Hence, the managements of corporations may attempt to conceal the negative and to accentuate the positive with "prudent" wording. To excavate this accounting phenomenon hidden behind financial statements, we designed an artificial intelligence based strategy to investigate the linkage between financial status measured by annual earnings and subjective multi-word expressions (MWEs). We applied the conditional random field (CRF) models to identify opinion patterns in the form of MWEs, and our approach outperformed previous work employing unigram models. Moreover, our novel algorithms take the lead to discover the evidences that support the common belief that there are inconsistencies between the implications of the written statements and the reality indicated by the figures in the financial statements. Unexpected negative earnings are often accompanied by ambiguous and mild statements and sometimes by promises of glorious future.

We collected the locations of eye fixations of Chinese native speakers when they read four Chinese articles, and attempted to analyze how the contextual linguistic and personal information influence the landing positions within the landing sites. In addition, we employed machine learning techniques to build models for the prediction of the landing positions. The models performed well for the closed tests, achieving 78% in accuracy in predicting whether a reader’s eyes landed on the first or the second character within a word that contained two characters. Unfortunately, the accuracy for the same task in the 10-fold cross validations dropped to 60%, indicating the necessity of more future work.

Student modeling is a key ingredient for intelligent interaction with students, and understanding how students learn composite concepts can help us build models of higher quality. An interesting question is how machines can help us infer about students' learning processes of composite concepts from students' external performance. Since Bayesian networks have been used in student modeling in many research projects, we employ them for simulating students' performance in taking tests, and seek methods for learning the original networks based on the simulated students' performance. The problem is not easy because the data we can observe have only indirect and uncertain relationship with the variables for mastery levels, and we would like to know the relationships among these hidden variables. We applied mutual information and artificial neural networks for this learning problem, and we achieved 75% in accuracy even when the item responses have really uncertain relationships with the actual mastery levels.

Financial distresses in corporations harm both individual investors and financial institutions, and can cause social problems due to the cascading effects. Government agencies, fund managers, and even small investors need to arm themselves with devices for predicting financial distresses in corporations, even when the financial problems are shadowed by malignant window dressing. In previous work, we explored the effectiveness of making predictions based on both financial ratios, including those proposed by Altman for the Z-score models and those used in the common-size analysis, and qualitative indicators, such as corporate governance. In this paper, we report results of our attempt to select the best features from the previously proposed features with genetic algorithms and gain ratio-based methods. Experimental results indicate that the selected features outperform the features used in the Z-score models. Not surprisingly, the genetic algorithms surpass the gain ratio-based methods in the task of feature selection.

Students need to integrate multiple basic concepts to become competent in the activities that require the knowledge of the composite concept. Traditionally, we rely on experts’ judgments to build models for this integration process. In this paper, we explore computational methods for unveiling how students learn composite concepts, and compare effects of applying mutual information-based and hierarchical search-based techniques for guessing the unobservable processes, which were simulated by Bayesian networks. Experimental results show that computational methods can be useful in assisting this student modelling task.

As the steps of globalization accelerate, learning foreign languages has become a modern challenge for everyone. Obtaining a broad range of learning and practice material will boost the efficiency of language learning, and the Web serves as a rich source of text material. We offer methods for algorithmically creating test items that may meet needs of individual learners and instructors of English. At the current stage, we explore the generation of test items for students' practicing listening cloze in English, using text material obtained from the Web. Relying on the text corpus, a voice-synthesizer software, and linguistics-based criteria, our system identifies candidate sentences and selects distractors for composing test items for listening cloze. Teachers can select and compose the machine-generated items as they wish, and allow students to practice the composed items. In addition, the current system records histories of the performance of individual student, so the resulting system paves our way to adoptively supporting students' activities for polishing their competence in listening English.

When we have an item bank available for assessing students, we would like to select the test items that can reveal students' knowledge levels as effectively and accurately as possible. This may not be a trivial task when we consider the fact that students' item-response patterns may not reflect their competence exactly. Theoretical and experimental results reported in this paper indicate that mutual information between test items and educational targets provides a principled and instrumental basis for adaptively selecting test items for student assessments.

The author examines methods for a special class of path planning problems in which the routes are constrained. General search algorithms assume that we can move around in the traffic network freely, so they extend the partial paths from the very last location to each of its neighbors to form more partial paths. The best partial paths are then selected to expand, unless die selected partial path happens to he a solution. Without proper guidance, this strategy way lead to inefficient planning algorithms when the way one can move around in the networks Is constrained. This scenario could happen in public transportation system where passengers cannot order drivers to change the routes of public buses to meet individual travel needs. A few recently proposed path-planning algorithms for public transportation systems capture the route constraints by matrices. Although they work for some applications, they are not perfect for cooperating with traditional algorithms; for best-path planning. Applying special properties of matrix multiplication, the author also employs matrices for capturing the route constraints. The author improves previous designs, and comes up with the so-called Q matrices that serve well in the A* algorithm for best-path planning under route constraints.

We consider stochastic networks in which link travel times are dependent, discrete random variables. We present methods for computing bounds on path travel times using stochastic dominance relationships among link travel times, and discuss techniques for controlling tightness of the bounds. We apply these methods to shortest-path problems, show that the proposed algorithm can provide bounds on the recommended path, and elaborate on extensions of the algorithm for demonstrating the anytime property.

Computing travel plans for desired trips in public transportation systems is not exactly the same as finding a shortest driving path in a given area. Path planning in the context of public transportation systems must consider the route constraint that public vehicles serve on particular paths and that passengers cannot order the drivers to change the bus routes. Explicit representation of the route constraint helps us to design efficient algorithms that focus on viable routes for computing travel plans of interest. This paper presents two strategies for capturing the route constraint. The first strategy employs connectivity matrices, and applies special properties of matrices for quickly identifying feasible travel plans for the desired trips. The second strategy uses hubs where many service routes concentrate for computing travel plans. Our algorithms perform very well in field tests.