Cognitive diagnosis is very useful to teachers and students, but its application is limited at present. This is largely because identifying the cognitive attributes of items currently is labor intensive and time-consu...
详细信息
ISBN:
(纸本)9781450376235
Cognitive diagnosis is very useful to teachers and students, but its application is limited at present. This is largely because identifying the cognitive attributes of items currently is labor intensive and time-consuming. In this study, we used text classification techniques to automatically identify cognitive attributes. Specifically, two popular deep learning classification models, long-short term memory and bi-directional long-short term memory, were employed in conjunction with word embeddings. As the baseline, support vector machine with feature selection using information gain was also adopted. Experiments based on a sample of 805 third grade math items showed that both the deep learning models performed better than support vector machine, and bi-directional long-short term memory achieved the best performance, yielding the accuracy of 82% and the F1 measure of 80%. Our result indicated that text classification methods, especially deep learning models, have great potential in identifying cognitive attributes efficiently, and in turn, make cognitive diagnostic more feasible to practitioners.
MULLE is a tool for language learning that focuses on teaching Latin as a foreign language. It is aimed for easy integration into the traditional classroom setting and syllabus, which makes it distinct from other lang...
ISBN:
(纸本)9781948087353
MULLE is a tool for language learning that focuses on teaching Latin as a foreign language. It is aimed for easy integration into the traditional classroom setting and syllabus, which makes it distinct from other language learning tools that provide standalone learning experience. It uses grammar-based lessons and embraces methods of gamification to improve the learner motivation. The main type of exercise provided by our application is to practice translation, but it is also possible to shift the focus to vocabulary or morphology training.
A place graph is an abstract representation of human place knowledge, which models spatial references. A place graph can be used for various tasks that rely on reasoning and querying of the stored knowledge. In relate...
详细信息
A place graph is an abstract representation of human place knowledge, which models spatial references. A place graph can be used for various tasks that rely on reasoning and querying of the stored knowledge. In related work, place graphs were constructed from parsing naturallanguage place descriptions using languageprocessing techniques. In this research, we present an innovative approach to derive place graphs from information stored in spatial databases, with a demonstration using OpenStreetMap data. The approach provides a complementary way to generating place graphs from naturallanguage descriptions.
The proceedings contain 13 papers. The topics discussed include: span-based constituency parsing with a structure-label system and provably optimal dynamic oracles;rule extraction for tree-to-tree transducers by cost ...
ISBN:
(纸本)9781945626326
The proceedings contain 13 papers. The topics discussed include: span-based constituency parsing with a structure-label system and provably optimal dynamic oracles;rule extraction for tree-to-tree transducers by cost minimization;a neural network for coordination boundary prediction;using left-corner parsing to encode universal structural constraints in grammar induction;distinguishing past, on-going, and future events: the EventStatus corpus;a position encoding convolutional neural network based on dependency tree for relation classification;and comparing computational cognitive models of generalization in a language acquisition task.
With the recent growth of Internet, mobile and social networks the spread of fake news and click-baits increases drastically. Today, the fact retrieval system is one of the most effective tools for identifying the inf...
详细信息
With the recent growth of Internet, mobile and social networks the spread of fake news and click-baits increases drastically. Today, the fact retrieval system is one of the most effective tools for identifying the information for decision-making. We propose the approach based on factual information systematization. Different interpretations of the same phenomenon, as well as the inconsistency, inaccuracy or mismatch in information coming from different sources, lead to the task of factual information extraction. In this work, we explore how can naturallanguageprocessingmethods help to check contradictions and mismatches in facts automatically. The reference model of the fact-based analytical system is proposed. It consists of such basic components as Document Search component, Fact retrieval component, Fact Analysis component, Visualization component, and Control component.
graph-theoretical methods are being increasingly used in areas of interest within the IEEE and beyond. graphs are mathematical abstractions that can be used to represent networks of various types: physical (e.g., the ...
详细信息
graph-theoretical methods are being increasingly used in areas of interest within the IEEE and beyond. graphs are mathematical abstractions that can be used to represent networks of various types: physical (e.g., the internet or electrical networks), biological (e.g., brain networks), or social (e.g., online social networks). Furthermore, graphs can provide tools for flexible representation of data sets in which data points have irregular positions with respect to each other. Common examples of this include data sets acquired by a sensor network, where uniform sensor placement may not be possible, or machine learning data sets, where training samples are not uniformly distributed in feature space. In some instances, a graph representation arises as a natural way to describe the problem, while in other areas, e.g., image processing, they are being used to develop powerful, content-dependent alternatives to conventional processing tools.
One of the main tasks of applied linguistics is the solution of the problem of high-quality automated processing of naturallanguage. The most popular methods for processingnatural-language text responses for the pur...
详细信息
The application of naturallanguageprocessing (NLP) methods and resources to clinical and biomedical text has received growing attention over the past years, but progress has been limited by difficulties to access sh...
详细信息
ISBN:
(纸本)9781450357944
The application of naturallanguageprocessing (NLP) methods and resources to clinical and biomedical text has received growing attention over the past years, but progress has been limited by difficulties to access shared tools and resources, partially caused by patient privacy and data confidentiality constraints. Efforts to increase sharing and interoperability of the few existing resources are needed to facilitate the progress observed in the general NLP domain. Leveraging our research in corpus analysis and de-identification research, we have created multiple synthetic data sets for a couple of NLP tasks based on real clinical sentences. We are organizing a challenge workshop to promote community efforts towards the advancement in clinical NLP. The challenge workshop will have two tasks: 1) Family History Information Extraction;and 2) Clinical Semantic Textual Similarity.
In this description, we report the experimental results of Machine Translation models conducted by a team from University of Computer Studies, Yangon (UCSY) for the translation tasks of WAT 2018. Generally, our models...
详细信息
In this description, we report the experimental results of Machine Translation models conducted by a team from University of Computer Studies, Yangon (UCSY) for the translation tasks of WAT 2018. Generally, our models are based on neural methods and statistical methods for both Myanmar-English and English-Myanmar direction of languages pair. For the neural method experiments, attention-based neural machine translation (NMT) that uses word level segmentation and Transformer that uses sub-word level segmentation have been carried out. In the portion of statistical machine translation (SMT), we used three different statistical approaches: phrase-based, hierarchical phrasebased, and the operation sequence model (OSM). Different Machine Translations are conducted on the ALT and UCSY datasets and the best scores from the experiments are described in this system description. Copyright 2018 by the authors.
The proceedings contain 56 papers. The topics discussed include: when does deep multi-task learning work for loosely related document classification tasks?;analyzing learned representations of a deep ASR performance p...
ISBN:
(纸本)9781948087711
The proceedings contain 56 papers. The topics discussed include: when does deep multi-task learning work for loosely related document classification tasks?;analyzing learned representations of a deep ASR performance prediction model;explaining non-linear classifier decisions within kernel-based deep architectures;nightmare at test time: how punctuation prevents parsers from generalizing;evaluating textual representations through image generation;on the role of text preprocessing in neural network architectures: an evaluation study on text categorization and sentiment analysis;jump to better conclusions: SCAN both left and right;understanding convolutional neural networks for text classification;and linguistic representations in multi-task neural networks for ellipsis resolution.
暂无评论