Richard Tzong-Han Tsai

Overview of BioCreative II gene mention recognition

Nineteen teams presented results for the Gene Mention Task at the BioCreative II Workshop. In this task participants designed systems to identify substrings in sentences corresponding to gene name mentions. A variety of different methods were used and the results varied with a highest achieved F1 score of 0.8721. Here we present brief descriptions of all the methods used and a statistical analysis of the results. We also demonstrate that, by combining the results from all submissions, an F score of 0.9066 is feasible, and furthermore that the best result makes use of the lowest scoring submissions.

The gene normalization task in BioCreative III

BackgroundWe report the Gene Normalization (GN) challenge in BioCreative III where participating teams were asked to return a ranked list of identifiers of the genes detected in full-text articles. For training, 32 fully and 500 partially annotated articles were prepared. A total of 507 articles were selected as the test set. Due to the high annotation cost, it was not feasible to obtain gold-standard human annotations for all test articles. Instead, we developed an Expectation Maximization (EM) algorithm approach for choosing a small number of test articles for manual annotation that were most capable of differentiating team performance. Moreover, the same algorithm was subsequently used for inferring ground truth based solely on team submissions. We report team performance on both gold standard and inferred ground truth using a newly proposed metric called Threshold Average Precision (TAP-k).ResultsWe received a total of 37 runs from 14 different teams for the task. When evaluated using the gold-standard annotations of the 50 articles, the highest TAP-k scores were 0.3297 (k=5), 0.3538 (k=10), and 0.3535 (k=20), respectively. Higher TAP-k scores of 0.4916 (k=5, 10, 20) were observed when evaluated using the inferred ground truth over the full test set. When combining team results using machine learning, the best composite system achieved TAP-k scores of 0.3707 (k=5), 0.4311 (k=10), and 0.4477 (k=20) on the gold standard, representing improvements of 12.4%, 21.8%, and 26.6% over the best team results, respectively.ConclusionsBy using full text and being species non-specific, the GN task in BioCreative III has moved closer to a real literature curation task than similar tasks in the past and presents additional challenges for the text mining community, as revealed in the overall team results. By evaluating teams using the gold standard, we show that the EM algorithm allows team submissions to be differentiated while keeping the manual annotation effort feasible. Using the inferred ground truth we show measures of comparative performance between teams. Finally, by comparing team rankings on gold standard vs. inferred ground truth, we further demonstrate that the inferred ground truth is as effective as the gold standard for detecting good team performance.

The CHEMDNER corpus of chemicals and drugs and its annotation principles

The automatic extraction of chemical information from text requires the recognition of chemical entity mentions as one of its key steps. When developing supervised named entity recognition (NER) systems, the availability of a large, manually annotated text corpus is desirable. Furthermore, large corpora permit the robust evaluation and comparison of different approaches that detect chemicals in documents. We present the CHEMDNER corpus, a collection of 10,000 PubMed abstracts that contain a total of 84,355 chemical entity mentions labeled manually by expert chemistry literature curators, following annotation guidelines specifically defined for this task. The abstracts of the CHEMDNER corpus were selected to be representative for all major chemical disciplines. Each of the chemical entity mentions was manually labeled according to its structure-associated chemical entity mention (SACEM) class: abbreviation, family, formula, identifier, multiple, systematic and trivial. The difficulty and consistency of tagging chemicals in text was measured using an agreement study between annotators, obtaining a percentage agreement of 91. For a subset of the CHEMDNER corpus (the test set of 3,000 abstracts) we provide not only the Gold Standard manual annotations, but also mentions automatically detected by the 26 teams that participated in the BioCreative IV CHEMDNER chemical mention recognition task. In addition, we release the CHEMDNER silver standard corpus of automatically extracted mentions from 17,000 randomly selected PubMed abstracts. A version of the CHEMDNER corpus in the BioC format has been generated as well. We propose a standard for required minimum information about entity annotations for the construction of domain specific corpora on chemical and drug entities. The CHEMDNER corpus and annotation guidelines are available at: http://www.biocreative.org/resources/biocreative-iv/chemdner-corpus/

Various criteria in the evaluation of biomedical named entity recognition

BackgroundText mining in the biomedical domain is receiving increasing attention. A key component of this process is named entity recognition (NER). Generally speaking, two annotated corpora, GENIA and GENETAG, are most frequently used for training and testing biomedical named entity recognition (Bio-NER) systems. JNLPBA and BioCreAtIvE are two major Bio-NER tasks using these corpora. Both tasks take different approaches to corpus annotation and use different matching criteria to evaluate system performance. This paper details these differences and describes alternative criteria. We then examine the impact of different criteria and annotation schemes on system performance by retesting systems participated in the above two tasks.ResultsTo analyze the difference between JNLPBAs and BioCreAtIvEs evaluation, we conduct Experiment 1 to evaluate the top four JNLPBA systems using BioCreAtIvEs classification scheme. We then compare them with the top four BioCreAtIvE systems. Among them, three systems participated in both tasks, and each has an F-score lower on JNLPBA than on BioCreAtIvE. In Experiment 2, we apply hypothesis testing and correlation coefficient to find alternatives to BioCreAtIvEs evaluation scheme. It shows that right-match and left-match criteria have no significant difference with BioCreAtIvE. In Experiment 3, we propose a customized relaxed-match criterion that uses right match and merges JNLPBAs five NE classes into two, which achieves an F-score of 81.5%. In Experiment 4, we evaluate a range of five matching criteria from loose to strict on the top JNLPBA system and examine the percentage of false negatives. Our experiment gives the relative change in precision, recall and F-score as matching criteria are relaxed.ConclusionIn many applications, biomedical NEs could have several acceptable tags, which might just differ in their left or right boundaries. However, most corpora annotate only one of them. In our experiment, we found that right match and left match can be appropriate alternatives to JNLPBA and BioCreAtIvEs matching criteria. In addition, our relaxed-match criterion demonstrates that users can define their own relaxed criteria that correspond more realistically to their application requirements.

Reference metadata extraction using a hierarchical knowledge representation framework

The integration of bibliographical information on scholarly publications available on the Internet is an important task in the academic community. Accurate reference metadata extraction from such publications is essential for the integration of metadata from heterogeneous reference sources. In this paper, we propose a hierarchical template-based reference metadata extraction method for scholarly publications. We adopt a hierarchical knowledge representation framework called INFOMAP, which automatically extracts metadata. The experimental results show that, by using INFOMAP, we can extract author, title, journal, volume, number (issue), year, and page information from different kinds of reference styles with a high degree of precision. The overall average accuracy is 92.39% for the six major reference styles compared in this study.

BIOSMILE: A semantic role labeling system for biomedical verbs using a maximum-entropy model with automatically generated template features

BackgroundBioinformatics tools for automatic processing of biomedical literature are invaluable for both the design and interpretation of large-scale experiments. Many information extraction (IE) systems that incorporate natural language processing (NLP) techniques have thus been developed for use in the biomedical field. A key IE task in this field is the extraction of biomedical relations, such as protein-protein and gene-disease interactions. However, most biomedical relation extraction systems usually ignore adverbial and prepositional phrases and words identifying location, manner, timing, and condition, which are essential for describing biomedical relations. Semantic role labeling (SRL) is a natural language processing technique that identifies the semantic roles of these words or phrases in sentences and expresses them as predicate-argument structures. We construct a biomedical SRL system called BIOSMILE that uses a maximum entropy (ME) machine-learning model to extract biomedical relations. BIOSMILE is trained on BioProp, our semi-automatic, annotated biomedical proposition bank. Currently, we are focusing on 30 biomedical verbs that are frequently used or considered important for describing molecular events.ResultsTo evaluate the performance of BIOSMILE, we conducted two experiments to (1) compare the performance of SRL systems trained on newswire and biomedical corpora; and (2) examine the effects of using biomedical-specific features. The experimental results show that using BioProp improves the F-score of the SRL system by 21.45% over an SRL system that uses a newswire corpus. It is noteworthy that adding automatically generated template features improves the overall F-score by a further 0.52%. Specifically, ArgM-LOC, ArgM-MNR, and Arg2 achieve statistically significant performance improvements of 3.33%, 2.27%, and 1.44%, respectively.ConclusionWe demonstrate the necessity of using a biomedical proposition bank for training SRL systems in the biomedical domain. Besides the different characteristics of biomedical and newswire sentences, factors such as cross-domain framesets and verb usage variations also influence the performance of SRL systems. For argument classification, we find that NE (named entity) features indicating if the target node matches with NEs are not effective, since NEs may match with a node of the parsing tree that does not have semantic role labels in the training set. We therefore incorporate templates composed of specific words, NE types, and POS tags into the SRL system. As a result, the classification accuracy for adjunct arguments, which is especially important for biomedical SRL, is improved significantly.

New Challenges for Biological Text-Mining in the Next Decade

The massive flow of scholarly publications from traditional paper journals to online outlets has benefited biologists because of its ease to access. However, due to the sheer volume of available biological literature, researchers are finding it increasingly difficult to locate needed information. As a result, recent biology contests, notably JNLPBA and BioCreAtIvE, have focused on evaluating various methods in which the literature may be navigated. Among these methods, text-mining technology has shown the most promise. With recent advances in text-mining technology and the fact that publishers are now making the full texts of articles available in XML format, TMSs can be adapted to accelerate literature curation, maintain the integrity of information, and ensure proper linkage of data to other resources. Even so, several new challenges have emerged in relation to full text analysis, life-science terminology, complex relation extraction, and information fusion. These challenges must be overcome in order for text-mining to be more effective. In this paper, we identify the challenges, discuss how they might be overcome, and consider the resources that may be helpful in achieving that goal.

A Semi-Automatic Method for Annotating a Biomedical Proposition Bank

In this paper, we present a semiautomatic approach for annotating semantic information in biomedical texts. The information is used to construct a biomedical proposition bank called BioProp. Like PropBank in the newswire domain, BioProp contains annotations of predicate argument structures and semantic roles in a treebank schema. To construct BioProp, a semantic role labeling (SRL) system trained on PropBank is used to annotate BioProp. Incorrect tagging results are then corrected by human annotators. To suit the needs in the biomedical domain, we modify the PropBank annotation guidelines and characterize semantic roles as components of biological events. The method can substantially reduce annotation efforts, and we introduce a measure of an upper bound for the saving of annotation efforts. Thus far, the method has been applied experimentally to a 4,389-sentence tree-bank corpus for the construction of BioProp. Inter-annotator agreement measured by kappa statistic reaches .95 for combined decision of role identification and classification when all argument labels are considered. In addition, we show that, when trained on BioProp, our biomedical SRL system called BIOSMILE achieves an F-score of 87%.

Multistage Gene Normalization and SVM-Based Ranking for Protein Interactor Extraction in Full-Text Articles

The interactor normalization task (INT) is to identify genes that play the interactor role in protein-protein interactions (PPIs), to map these genes to unique IDs, and to rank them according to their normalized confidence. INT has two subtasks: gene normalization (GN) and interactor ranking. The main difficulties of INT GN are identifying genes across species and using full papers instead of abstracts. To tackle these problems, we developed a multistage GN algorithm and a ranking method, which exploit information in different parts of a paper. Our system achieved a promising AUC of 0.43471. Using the multistage GN algorithm, we have been able to improve system performance (AUC) by 1.719 percent compared to a one-stage GN algorithm. Our experimental results also show that with full text, versus abstract only, INT AUC performance was 22.6 percent higher.

TEMPTING system: A hybrid method of rule and machine learning for temporal relation extraction in patient discharge summaries

Patient discharge summaries provide detailed medical information about individuals who have been hospitalized. To make a precise and legitimate assessment of the abundant data, a proper time layout of the sequence of relevant events should be compiled and used to drive a patient-specific timeline, which could further assist medical personnel in making clinical decisions. The process of identifying the chronological order of entities is called temporal relation extraction. In this paper, we propose a hybrid method to identify appropriate temporal links between a pair of entities. The method combines two approaches: one is rule-based and the other is based on the maximum entropy model. We develop an integration algorithm to fuse the results of the two approaches. All rules and the integration algorithm are formally stated so that one can easily reproduce the system and results. To optimize the systems configuration, we used the 2012 i2b2 challenge TLINK track dataset and applied threefold cross validation to the training set. Then, we evaluated its performance on the training and test datasets. The experiment results show that the proposed TEMPTING (TEMPoral relaTion extractING) system (ranked seventh) achieved an F-score of 0.563, which was at least 30% better than that of the baseline system, which randomly selects TLINK candidates from all pairs and assigns the TLINK types. The TEMPTING system using the hybrid method also outperformed the stage-based TEMPTING system. Its F-scores were 3.51% and 0.97% better than those of the stage-based system on the training set and test set, respectively.