We show teachability of a subclass of simple deterministic languages. The subclass we define is called stack uniform simple deterministic languages. Teachability is derived by showing the query learning algorithm for this language class. Our learning algorithm uses membership, equivalence and superset queries. Then, it terminates in polynomial time. It is already known that simple deterministic languages are polynomial time query learnable by context-free grammars. In contrast, our algorithm guesses a hypothesis by a stack uniform simple deterministic grammar, thus our result is strict teachability of the subclass of simple deterministic languages. In addition, we discuss parameters of the polynomial for teachability. The “thickness” is an important parameter for parsing and it should be one of parameters to evaluate the time complexity.

To understand human emotion, it is necessary to be aware of the surrounding situation and individual personalities. In most previous studies, however, these important aspects were not considered. Emotion recognition has been considered as a classification problem. In this paper, we attempt new approaches to utilize a person's situational information and personality for use in understanding emotion. We propose a method of extracting situational information and building a personalized emotion model for reflecting the personality of each character in the text. To extract and utilize situational information, we propose a situation model using lexical and syntactic information. In addition, to reflect the personality of an individual, we propose a personalized emotion model using KBANN (Knowledge-based Artificial Neural Network). Our proposed system has the advantage of using a traditional keyword-spotting algorithm. In addition, we also reflect the fact that the strength of emotion decreases over time. Experimental results show that the proposed system can more accurately and intelligently recognize a person's emotion than previous methods.

Morphemes, which are obtained from morphological parsing, and statistical sub-words, which are derived from data-driven splitting, are commonly used as the recognition units for speech recognition of agglutinative languages. In this letter, we propose a discriminative approach to select the splitting result, which is more likely to improve the recognizer's performance, for each distinct word type. An objective function which involves the unigram language model (LM) probability and the count of misrecognized phones on the acoustic training data is defined and minimized. After determining the splitting result for each word in the text corpus, we select the frequent units to build a hybrid vocabulary including morphemes and statistical sub-words. Compared to a statistical sub-word based system, the hybrid system achieves 0.8% letter error rates (LERs) reduction on the test set.

Automated or semi-automated annotation is a practical solution for large-scale corpus construction. However, the special characteristics of Thai language, such as lack of word-boundary and sentence-boundary markers, trigger several issues in automatic corpus annotation. This paper presents a multi-stage annotation framework, containing two stages of chunking and three stages of tagging. The two chunking stages are pattern matching-based named entity (NE) extraction and dictionary-based word segmentation while the three succeeding tagging stages are dictionary-, pattern- and statist09812490981249ical-based tagging. Applying heuristics of ambiguity priority, NE extraction is performed first on an original text using a set of patterns, in the order of pattern ambiguity. Next, the remaining text is segmented into words with a dictionary. The obtained chunks are then tagged with types of named entities or parts-of-speech (PoS) using dictionaries, patterns and statistics. Focusing on the reduction of human intervention in corpus construction, our experimental results show that the dictionary-based tagging process can assign unique tags to 64.92% of the words, with the remaining of 24.14% unknown words and 10.94% ambiguously tagged words. Later, the pattern-based tagging can reduce unknown words to only 13.34% while the statistical-based tagging can solve the ambiguously tagged words to only 3.01%.

Comparable Corpora are valuable resources for many NLP applications, and extensive research has been done on information mining based on comparable corpora in recent years. While there are not enough large-scale available public comparable corpora at present, this paper presents a bi-directional CLIR-based method for creating comparable corpora from two independent news collections in different languages. The original Chinese document collections and English documents collections are crawled from XinHuaNet respectively and formatted in a consistent manner. For each document from the two collections, the best query keywords are extracted to represent the essential content of the document, and then the keywords are translated into the language of the other collection. The translated queries are run against the collection in the same language to pick up the candidate documents in the other language and candidates are aligned based on their publication dates and the similarity scores. Results show that our approach significantly outperforms previous approaches to the construction of Chinese-English comparable corpora.

Semantic concept in an utterance is obtained by a fuzzy matching methods to solve problems such as words' variation induced by automatic speech recognition (ASR), or missing field of key information by users in the process of spoken language understanding (SLU). A two-stage method is proposed: first, we adopt conditional random field (CRF) for building probabilistic models to segment and label entity names from an input sentence. Second, fuzzy matching based on similarity function is conducted between the named entities labeled by a CRF model and the reference characters of a dictionary. The experiments compare the performances in terms of accuracy and processing speed. Dice similarity and cosine similarity based on TF score can achieve better accuracy performance among four similarity measures, which equal to and greater than 93% in F1-measure. Especially the latter one improved by 8.8% and 9% respectively compared to q-gram and improved edit-distance, which are two conventional methods for string fuzzy matching.

Event extraction is vital to social media monitoring and social event prediction. In this paper, we propose a method for social event extraction from web documents by identifying binary relations between named entities. There have been many studies on relation extraction, but their aims were mostly academic. For practical application, we try to identify 130 relation types that comprise 31 predefined event types, which address business and public issues. We use structured Support Vector Machine, the state of the art classifier to capture relations. We apply our method on news, blogs and tweets collected from the Internet and discuss the results.

The globalization of commerce has increased the importance of retrieving and updating complex and distributed information efficiently. Web services currently show that the most promise for building distributed application systems and model-driven architecture is a new approach to developing such applications. The expanding scale and complexity of enterprise information systems (EISs) under distributed computing environments has made sharing and exchanging data particularly challenging. Data services are applications tailored specifically for information oriented tasks to deal with business service requirements, and are heavily dependent on the distributed architecture of consumer data processing. The implementation of a data service can eliminate inconsistency among various application systems in the exchange of data. This paper proposes a data-oriented model-driven developmental framework to deal with these issues, in which a platform independent model (PIM) is divided into a service model, a logic data model, and a service composition model. We also divide a platform specific model (PSM) into a physical data model and a data service model. In this development method, we define five meta-models and outline a set of rules governing the transformation from PIMs into PSMs. A code generator is also included to transform each PSM into the application code. We include a case study to demonstrate the feasibility and merits of the proposed development framework with a case study.

To acquire a second language, one must develop an ear and tongue for the correct stress and intonation patterns of that language. In English language teaching, there is an effective method called Jazz Chants for working on the sound system. In this paper, we propose a method for predicting stressed words, which play a crucial role in Jazz Chants. The proposed method is specially designed for stress prediction in Jazz chants. It exploits several sources of information including words, POSs, sentence types, and the constraint on the number of stressed words in a chant text. Experiments show that the proposed method achieves an F-measure of 0.939 and outperforms the other methods implemented for comparison. The proposed method is expected to be useful in supporting non-native teachers of English when they teach chants to students and create chant texts with stress marks from arbitrary texts.

This paper describes a new method for semi-supervised discriminative language modeling, which is designed to improve the robustness of a discriminative language model (LM) obtained from manually transcribed (labeled) data. The discriminative LM is implemented as a log-linear model, which employs a set of linguistic features derived from word or phoneme sequences. The proposed semi-supervised discriminative modeling is formulated as a multi-objective optimization programming problem (MOP), which consists of two objective functions defined on both labeled lattices and automatic speech recognition (ASR) lattices as unlabeled data. The objectives are coherently designed based on the expected risks that reflect information about word errors for the training data. The model is trained in a discriminative manner and acquired as a solution to the MOP problem. In transcribing Japanese broadcast programs, the proposed method reduced relatively a word error rate by 6.3% compared with that achieved by a conventional trigram LM.

In this paper we study the ploblem whether the language D(1) of all d-primitive words can be generated by a contextual grammar. It is proved that D(1) can be generated neither by an external contextual grammar nor by an internal contextual grammar, and that it can be generated by a total contextual grammar with choice.

Out-of-vocabulary (OOV) words create serious problems for automatic speech recognition (ASR) systems. Not only are they miss-recognized as in-vocabulary (IV) words with similar phonetics, but the error also causes further errors in nearby words. Language models (LMs) for most open vocabulary ASR systems treat OOV words as a single entity, ignoring the linguistic information. In this paper we present a class-based n-gram LM that is able to deal with OOV words by treating each of them individually without retraining all the LM parameters. OOV words are assigned to IV classes consisting of similar semantic meanings for IV words. The World Wide Web is used to acquire additional data for finding the relation between the OOV and IV words. An evaluation based on adjusted perplexity and word-error-rate was carried out on the Wall Street Journal corpus. The result suggests the preference of the use of multiple classes for OOV words, instead of one unknown class.

The optimal way to build speech understanding modules depends on the amount of training data available. When only a small amount of training data is available, effective allocation of the data is crucial to preventing overfitting of statistical methods. We have developed a method for allocating a limited amount of training data in accordance with the amount available. Our method exploits rule-based methods for when the amount of data is small, which are included in our speech understanding framework based on multiple model combinations, i.e., multiple automatic speech recognition (ASR) modules and multiple language understanding (LU) modules, and then allocates training data preferentially to the modules that dominate the overall performance of speech understanding. Experimental evaluation showed that our allocation method consistently outperforms baseline methods that use a single ASR module and a single LU module while the amount of training data increases.

Although there have been enormous investments into English education all around the world, not many differences have been made to change the English instruction style. Considering the shortcomings for the current teaching-learning methodology, we have been investigating advanced computer-assisted language learning (CALL) systems. This paper aims at summarizing a set of POSTECH approaches including theories, technologies, systems, and field studies and providing relevant pointers. On top of the state-of-the-art technologies of spoken dialog system, a variety of adaptations have been applied to overcome some problems caused by numerous errors and variations naturally produced by non-native speakers. Furthermore, a number of methods have been developed for generating educational feedback that help learners develop to be proficient. Integrating these efforts resulted in intelligent educational robots – Mero and Engkey – and virtual 3D language learning games, Pomy. To verify the effects of our approaches on students' communicative abilities, we have conducted a field study at an elementary school in Korea. The results showed that our CALL approaches can be enjoyable and fruitful activities for students. Although the results of this study bring us a step closer to understanding computer-based education, more studies are needed to consolidate the findings.

This paper presents our recent work in regard to building Large Vocabulary Continuous Speech Recognition (LVCSR) systems for the Thai, Indonesian, and Chinese languages. For Thai, since there is no word boundary in the written form, we have proposed a new method for automatically creating word-like units from a text corpus, and applied topic and speaking style adaptation to the language model to recognize spoken-style utterances. For Indonesian, we have applied proper noun-specific adaptation to acoustic modeling, and rule-based English-to-Indonesian phoneme mapping to solve the problem of large variation in proper noun and English word pronunciation in a spoken-query information retrieval system. In spoken Chinese, long organization names are frequently abbreviated, and abbreviated utterances cannot be recognized if the abbreviations are not included in the dictionary. We have proposed a new method for automatically generating Chinese abbreviations, and by expanding the vocabulary using the generated abbreviations, we have significantly improved the performance of spoken query-based search.

This paper describes a technique for overcoming the model shrinkage problem in automatic speech recognition (ASR), which allows application developers and users to control the model size with less degradation of accuracy. Recently, models for ASR systems tend to be large and this can constitute a bottleneck for developers and users without special knowledge of ASR with respect to introducing the ASR function. Specifically, discriminative language models (DLMs) are usually designed in a high-dimensional parameter space, although DLMs have gained increasing attention as an approach for improving recognition accuracy. Our proposed method can be applied to linear models including DLMs, in which the score of an input sample is given by the inner product of its features and the model parameters, but our proposed method can shrink models in an easy computation by obtaining simple statistics, which are square sums of feature values appearing in a data set. Our experimental results show that our proposed method can shrink a DLM with little degradation in accuracy and perform properly whether or not the data for obtaining the statistics are the same as the data for training the model.

A method of generating scenarios using differential scenaro information is presented. Behaviors of normal scenarios of similar purpose are quite similar each other, while actors and data in scenarios are different among these scenarios. We derive the differential information between them and apply the differential information to generate new alternative/exceptional scenarios. Our method will be illustrated with examples. This paper describes (1) a language for describing scenarios based on a simple case grammar of actions, (2) introduction of the differential scenario, and (3) method and examples of scenario generation using the differential scenario.

Large-scale adoption of electronic healthcare applications requires semantic interoperability. The new proposals propose an advanced (multi-level) DBMS architecture for repository services for health records of patients. These also require query interfaces at multiple levels and at the level of semi-skilled users. In this regard, a high-level user interface for querying the new form of standardized Electronic Health Records system has been examined in this study. It proposes a step-by-step graphical query interface to allow semi-skilled users to write queries. Its aim is to decrease user effort and communication ambiguities, and increase user friendliness.

We propose a novel scheme to learn a language model (LM) for automatic speech recognition (ASR) directly from continuous speech. In the proposed method, we first generate phoneme lattices using an acoustic model with no linguistic constraints, then perform training over these phoneme lattices, simultaneously learning both lexical units and an LM. As a statistical framework for this learning problem, we use non-parametric Bayesian statistics, which make it possible to balance the learned model's complexity (such as the size of the learned vocabulary) and expressive power, and provide a principled learning algorithm through the use of Gibbs sampling. Implementation is performed using weighted finite state transducers (WFSTs), which allow for the simple handling of lattice input. Experimental results on natural, adult-directed speech demonstrate that LMs built using only continuous speech are able to significantly reduce ASR phoneme error rates. The proposed technique of joint Bayesian learning of lexical units and an LM over lattices is shown to significantly contribute to this improvement.

This paper investigates a new method for fusion of scores generated by multiple classification sub-systems that help to further reduce the classification error rate in Spoken Language Recognition (SLR). In recent studies, a variety of effective classification algorithms have been developed for SLR. Hence, it has been a common practice in the National Institute of Standards and Technology (NIST) Language Recognition Evaluations (LREs) to fuse the results from several classification sub-systems to boost the performance of the SLR systems. In this work, we introduce a discriminative performance measure to optimize the performance of the fusion of 7 language classifiers developed as IIR's submission to the 2009 NIST LRE. We present an Error Corrective Fusion (ECF) method in which we iteratively learn the fusion weights to minimize error rate of the fusion system. Experiments conducted on the 2009 NIST LRE corpus demonstrate a significant improvement compared to individual sub-systems. Comparison study is also conducted to show the effectiveness of the ECF method.