Juntae Yoon

Two-phase biomedical named entity recognition using a hybrid method

Biomedical named entity recognition (NER) is a difficult problem in biomedical information processing due to the widespread ambiguity of terms out of context and extensive lexical variations. This paper presents a two-phase biomedical NER consisting of term boundary detection and semantic labeling. By dividing the problem, we can adopt an effective model for each process. In our study, we use two exponential models, conditional random fields and maximum entropy, at each phase. Moreover, results by this machine learning based model are refined by rule-based postprocessing implemented using a finite state method. Experiments show it achieves the performance of F-score 71.19% on the JNLPBA 2004 shared task of identifying 5 classes of biomedical NEs.

Link-topic model for biomedical abbreviation disambiguation

INTRODUCTION The ambiguity of biomedical abbreviations is one of the challenges in biomedical text mining systems. In particular, the handling of term variants and abbreviations without nearby definitions is a critical issue. In this study, we adopt the concepts of topic of document and word link to disambiguate biomedical abbreviations. METHODS We newly suggest the link topic model inspired by the latent Dirichlet allocation model, in which each document is perceived as a random mixture of topics, where each topic is characterized by a distribution over words. Thus, the most probable expansions with respect to abbreviations of a given abstract are determined by word-topic, document-topic, and word-link distributions estimated from a document collection through the link topic model. The model allows two distinct modes of word generation to incorporate semantic dependencies among words, particularly long form words of abbreviations and their sentential co-occurring words; a word can be generated either dependently on the long form of the abbreviation or independently. The semantic dependency between two words is defined as a link and a new random parameter for the link is assigned to each word as well as a topic parameter. Because the link status indicates whether the word constitutes a link with a given specific long form, it has the effect of determining whether a word forms a unigram or a skipping/consecutive bigram with respect to the long form. Furthermore, we place a constraint on the model so that a word has the same topic as a specific long form if it is generated in reference to the long form. Consequently, documents are generated from the two hidden parameters, i.e. topic and link, and the most probable expansion of a specific abbreviation is estimated from the parameters. RESULTS Our model relaxes the bag-of-words assumption of the standard topic model in which the word order is neglected, and it captures a richer structure of text than does the standard topic model by considering unigrams and semantically associated bigrams simultaneously. The addition of semantic links improves the disambiguation accuracy without removing irrelevant contextual words and reduces the parameter space of massive skipping or consecutive bigrams. The link topic model achieves 98.42% disambiguation accuracy on 73,505 MEDLINE abstracts with respect to 21 three letter abbreviations and their 139 distinct long forms.

A corpus-based approach for Korean nominal compound analysis based on linguistic and statistical information

The syntactic structure of a nominal compound must be analyzed first for its semantic interpretation. In addition, the syntactic analysis of nominal compounds is very useful for NLP application such as information extraction, since a nominal compound often has a similar linguistic structure with a simple sentence, as well as representing concrete and compound meaning of an object with several nouns combined. In this paper, we present a novel model for structural analysis of nominal compounds using linguistic and statistical knowledge which is coupled based on lexical information. That is, the syntactic relations defined between nouns (complement-predicate and modifier-head relation) are obtained from large corpora and again used to analyze the structures of nominal compounds and identify the underlying relations between nouns. Experiments show that the model gives good results, and can be effectively used for application systems which do not require deep semantic information.

Experimental Study on a Two Phase Method for Biomedical Named Entity Recognition

In this paper, we describe a two-phase method for biomedical named entity recognition consisting of term boundary detection and biomedical category labeling. The term boundary detection can be defined as a task to assign label sequences to a given sentence, and biomedical category labeling can be viewed as a local classification problem which does not need knowledge of the labels of other named entities in a sentence. The advantage of dividing the recognition process into two phases is that we can measure the effectiveness of models at each phase and select separately the appropriate model for each subtask. In order to obtain a better performance in biomedical named entity recognition, we conducted comparative experiments using several learning methods at each phase. Moreover, results by these machine learning based models are refined by rule-based postprocessing. We tested our methods on the JNLPBA 2004 shared task and the GENIA corpus.

Semantic Dependency Link Topic Model for Biomedical Acronym Disambiguation

Many important terminologies in biomedical text are expressed as abbreviations or acronyms. We newly suggest a semantic link topic model based on the concepts of topic and dependency link to disambiguate biomedical abbreviations and cluster long form variants of abbreviations which refer to the same senses. This model is a generative model inspired by the latent Dirichlet allocation (LDA) topic model, in which each document is viewed as a mixture of topics, with each topic characterized by a distribution over words. Thus, words of a document are generated from a hidden topic structure of a document and the topic structure is inferred from observable word sequences of document collections. In this study, we allow two distinct word generation to incorporate semantic dependencies between words, particularly between expansions (long forms) of abbreviations and their sentential co-occurring words. Besides topic information, the semantic dependency between words is defined as a link and a new random parameter for the link presence is assigned to each word. As a result, the most probable expansions with respect to abbreviations of a given abstract are decided by word-topic distribution, document-topic distribution, and word-link distribution estimated from document collection though the semantic dependency link topic model. The abstracts retrieved from the MEDLINE Entrez interface by the query relating 22 abbreviations and their 186 expansions were used as a data set. The link topic model correctly predicted expansions of abbreviations with the accuracy of 98.30%.

Improving Korean verb-verb morphological disambiguation using lexical knowledge from unambiguous unlabeled data and selective web counts

This paper deals with verb-verb morphological disambiguation of two different verbs that have the same inflected form. The verb-verb morphological ambiguity (VVMA) is one of the critical Korean parts of speech (POS) tagging issues. The recognition of verb base forms related to ambiguous words highly depends on the lexical information in their surrounding contexts and the domains they occur in. However, current probabilistic morpheme-based POS tagging systems cannot handle VVMA adequately since most of them have a limitation to reflect a broad context of word level, and they are trained on too small amount of labeled training data to represent sufficient lexical information required for VVMA disambiguation. In this study, we suggest a classifier based on a large pool of raw text that contains sufficient lexical information to handle the VVMA. The underlying idea is that we automatically generate the annotated training set applicable to the ambiguity problem such as VVMA resolution via unlabeled unambiguous instances which belong to the same class. This enables to label ambiguous instances with the knowledge that can be induced from unambiguous instances. Since the unambiguous instances have only one label, the automatic generation of their annotated corpus are possible with unlabeled data. In our problem, since all conjugations of irregular verbs do not lead to the spelling changes that cause the VVMA, a training data for the VVMA disambiguation are generated via the instances of unambiguous conjugations related to each possible verb base form of ambiguous words. This approach does not require an additional annotation process for an initial training data set or a selection process for good seeds to iteratively augment a labeling set which are important issues in bootstrapping methods using unlabeled data. Thus, this can be strength against previous related works using unlabeled data. Furthermore, a plenty of confident seeds that are unambiguous and can show enough coverage for learning process are assured as well. We also suggest a strategy to extend the context information incrementally with web counts only to selected test examples that are difficult to predict using the current classifier or that are highly different from the pre-trained data set. As a result, automatic data generation and knowledge acquisition from unlabeled text for the VVMA resolution improved the overall tagging accuracy (token-level) by 0.04%. In practice, 9-10% out of verb-related tagging errors are fixed by the VVMA resolution whose accuracy was about 98% by using the Naive Bayes classifier coupled with selective web counts.

Two-Level Alignment by Words and Phrases Based on Syntactic Information

As a part of work on alignment of the English and Korean parallel corpus, this paper presents a statistical translation model incorporating linguistic knowledge of syntactic and phrasal information for better translations. For this, we propose three models: First, we incorporate syntactic information such as part of speech into the word-based lexical alignment. Based on this model, we propose the second model which finds phrasal correspondence in the parallel corpus. Phrasal mapping through chunk-based shallow parsing enables to settle mismatch of meaningful units in the two languages. Lastly, we develop a two-level alignment model by combining these two models in order to construct both the word and phrase-based translation model. Model parameters are automatically estimated from a set of bilingual sentence pairs by applying the EM algorithm. Experiments show that the structural relationship helps construct a better translation model for structurally different languages like Korean and English.