In this paper, we propose an Ontology-Style Relation (OSR) annotation approach. In conventional Relation Extraction (RE) datasets, relations are annotated as a link between two entity mentions. In contrast, in our OSR annotation, a relation is annotated as a relation mention (i.e., not a link but a node) and rdfs:domain and rdfs:range links are annotated from the relation mention to its argument entity mentions. This approach has the following benefits: (1) the relation annotations can be easily converted to Resource Description Framework (RDF) triples to populate an Ontology, (2) some part of conventional RE tasks can be tackled as Named Entity Recognition (NER) tasks, and the relation classes are limited to several RDF properties, and (3) OSR annotations can be used for clear documentations of Ontology contents. We conducted two kinds of evaluation to investigate effects of OSR annotation. We converted (1) an in-house corpus of Japanese Rules of the Road (RoR) in conventional annotations into the OSR annotations and built a novel OSR-RoR corpus and (2) SemEval-2010 Task 8 dataset into the OSR annotations (called OSR-SemEval corpus). We compared the NER and RE performance using neural NER/RE tool DyGIE++ on the conventional and OSR annotations. The experimental results show that the OSR annotations make the RE task easier while introducing slight complexity into the NER task.

MOTIVATION: Most of the conventional deep neural network-based methods for drug-drug interaction (DDI) extraction consider only context information around drug mentions in the text. However, human experts use heterogeneous background knowledge about drugs to comprehend pharmaceutical papers and extract relationships between drugs. Therefore, we propose a novel method that simultaneously considers various heterogeneous information for DDI extraction from the literature. RESULTS: We first construct drug representations by conducting the link prediction task on a heterogeneous pharmaceutical knowledge graph (KG) dataset. We then effectively combine the text information of input sentences in the corpus and the information on drugs in the heterogeneous KG (HKG) dataset. Finally, we evaluate our DDI extraction method on the DDIExtraction-2013 shared task dataset. In the experiment, integrating heterogeneous drug information significantly improves the DDI extraction performance, and we achieved an F-score of 85.40%, which results in state-of-the-art performance. We evaluated our method on the DrugProt dataset and improved the performance significantly, achieving an F-score of 77.9%. Further analysis showed that each type of node in the HKG contributes to the performance improvement of DDI extraction, indicating the importance of considering multiple pieces of information. AVAILABILITY AND IMPLEMENTATION: Our code is available at https://github.com/tticoin/HKG-DDIE.git.

MOTIVATION: Entity linking is the task of linking entity mentions to the database entries corresponding to the entity mentions. Entity linking enables the treatment of superficially different but semantically identical mentions as the same entity. Since millions of concepts are listed in biomedical databases, selecting the correct database entry for each targeted entity is challenging. Simple string matching between the word and each synonym in biomedical databases is insufficient to handle a wide variety of variants of biomedical entities appearing in the biomedical literature. Recent progress in neural approaches is promising for entity linking. Still, existing neural methods require sufficient data, which is difficult to prepare in biomedical entity linking that deals with millions of biomedical concepts. Therefore, we need to develop a new neural method to train entity-linking models over the sparse training data covering a very limited part of the biomedical concepts. RESULTS: We have devised a pure neural model that classifies biomedical entity mentions into millions of biomedical concepts. The classifier employs (1) the layer overwriting that breaks through the performance ceiling during training, (2) training data augmentation using database entries that compensate for the problem of insufficient training data, and (3) the cosine similarity-based loss function that helps distinguish the millions of biomedical concepts. Our system using the proposed classifier was ranked first in the official run of the National NLP Clinical Challenges (n2c2) 2019 Track 3, which targeted linking medical/clinical entity mentions to 434,056 Concept Unique Identifier (CUI) entries. We also applied our system to the MedMentions dataset, which has 3.2M candidate concepts. Experimental results confirmed the same advantages of our proposed method. We further evaluated our system on the NLM-CHEM corpus with 350K candidate concepts, and our system achieved a new state-of-the-art performance on the corpus. AVAILABILITY: https://github.com/tti-coin/bio-linking Contact:[email protected].

This paper describes contextualized medication event extraction for automatically identifying medication change events with their contexts from clinical notes. The striding named entity recognition (NER) model extracts medication name spans from an input text sequence using a sliding-window approach. Specifically, the striding NER model separates the input sequence into a set of overlapping subsequences of 512 tokens with 128 tokens of stride, processing each subsequence using a large pre-trained language model and aggregating the outputs from the subsequences. The event and context classification has been done with multi-turn question-answering (QA) and span-based models. The span-based model classifies the span of each medication name using the span representation of the language model. In the QA model, event classification is augmented with questions in classifying the change events of each medication name and the context of the change events, while the model architecture is a classification style that is the same as the span-based model. We evaluated our extraction system on the n2c2 2022 Track 1 dataset, which is annotated for medication extraction (ME), event classification (EC), and context classification (CC) from clinical notes. Our system is a pipeline of the striding NER model for ME and the ensemble of the span-based and QA-based models for EC and CC. Our system achieved a combined F-score of 66.47% for the end-to-end contextualized medication event extraction (Release 1), which is the highest score among the participants of the n2c2 2022 Track 1.

This paper describes a superconductivity corpus for materials informatics (SC-CoMIcs) tailored for the extraction of superconductive material information from the literature. Currently, few corpora exist for materials informatics in contrast to the situation for biomedical informatics. In particular, there is no sizable corpus that can be used to assist with the search for superconducting materials. The SC-CoMIcs consists of 1,000 abstracts with manually annotated named entities, main materials, and relations/events associated with superconductivity. In particular, the main material is a selling point of our corpus, which can be regarded as a hub that binds implicitly related physical entities and properties in abstracts. We conduct named entity recognition, main material identification, and relation/event extraction experiments to determine the effectiveness of the corpus. The experimental results show that we can obtain F1 scores of approximately 74%–95%, 84% and 73%–97% for named entity recognition, main material identification and relation extraction tasks, respectively. We also demonstrate that the extracted doping information is consistent with that of the well-known Hume–Rothery rules, which implies that the constructed corpus can provide an opportunity to revisit or find physical chemical rules from the literature.

MOTIVATION: Neural methods to extract drug-drug interactions (DDIs) from literature require a large number of annotations. In this study, we propose a novel method to effectively utilize external drug database information as well as information from large-scale plain text for DDI extraction. Specifically, we focus on drug description and molecular structure information as the drug database information. RESULTS: We evaluated our approach on the DDIExtraction 2013 shared task dataset. We obtained the following results. First, large-scale raw text information can greatly improve the performance of extracting DDIs when combined with the existing model and it shows the state-of-the-art performance. Second, each of drug description and molecular structure information is helpful to further improve the DDI performance for some specific DDI types. Finally, the simultaneous use of the drug description and molecular structure information can significantly improve the performance on all the DDI types. We showed that the plain text, the drug description information and molecular structure information are complementary and their effective combination is essential for the improvement. AVAILABILITY AND IMPLEMENTATION: Our code is available at https://github.com/tticoin/DESC_MOL-DDIE.

This paper proposes an Ontology-Style Relation (OSR) annotation approach. In conventional Relation Extraction (RE) datasets, relations are annotated as links between entity mentions. In contrast, in our OSR annotation, a relation is annotated as a relation mention (i.e., not a link but a node) and domain and range links are annotated from the relation mention to its argument entity mentions. We expect the following benefits: (1) the relation annotations can be easily converted to Resource Description Framework (RDF) triples to populate an Ontology, (2) some part of conventional RE tasks can be tackled as Named Entity Recognition (NER) tasks. The relation classes are limited to several RDF properties such as domain, range, and subClassOf, and (3) OSR annotations can be clear documentations of Ontology contents. As a case study, we converted an in-house corpus of Japanese traffic rules in conventional annotations into the OSR annotations and built a novel OSR-RoR (Rules of the Road) corpus. The inter-annotator agreements of the conversion were 85-87%. We evaluated the performance of neural NER and RE tools on the conventional and OSR annotations. The experimental results showed that the OSR annotations make the RE task easier while introducing slight complexity into the NER task.

This paper describes a novel corpus tailored for the text mining of superconducting materials in Materials Informatics (MI), named SuperConductivety Corpus for Materials Informatics (SC-CoMIcs). Different from biomedical informatics, there exist very few corpora targeting Materials Science and Engineering (MSE). Especially, there is no sizable corpus which can be used to assist the search of superconducting materials. A team of materials scientists and natural language processing experts jointly designed the annotation and constructed a corpus consisting of manually-annotated 1,000 MSE abstracts related to superconductivity. We conducted experiments on the corpus with a neural Named Entity Recognition (NER) tool. The experimental results show that NER performance over the corpus is around 77% in terms of micro-F1, which is comparable to human annotator agreement rates. Using the trained NER model, we automatically annotated 9,000 abstracts and created a term retrieval tool based on the term similarity. This tool can find superconductivity terms relevant to a query term within a specified Named Entity category, which demonstrates the power of our SC-CoMIcs, efficiently providing knowledge for Materials Informatics applications from rapidly expanding publications.

We propose a novel word embedding-based hypernym generation model that jointly learns clusters of hyponym-hypernym relations, i.e., hypernymy, and projections from hyponym to hypernym embeddings. Most of the recent hypernym detection models focus on a hypernymy classification problem that determines whether a pair of words is in hypernymy or not. These models do not directly deal with a hypernym generation problem in that a model generates hypernyms for a given word. Differently from previous studies, our model jointly learns the clusters and projections with adjusting the number of clusters so that the number of clusters can be determined depending on the learned projections and vice versa. Our model also boosts the performance by incorporating inner product-based similarity measures and negative examples, i.e., sampled non-hypernyms, into our objectives in learning. We evaluated our joint learning models on the task of Japanese and English hypernym generation and showed a significant improvement over an existing pipeline model. Our model also compared favorably to existing distributed hypernym detection models on the English hypernym classification task.

Making fast driving decisions at intersections is a challenging problem for improving safety of autonomous vehicles. Furthermore, representing sensor data in a machine understandable format is essential to enable vehicles to understand traffic situations. Ontologies are used to represent knowledge of sensor data for autonomous vehicles to aware traffic situations. In this paper, we introduce a fast decision making system, which utilizes only related part of the ontology-based knowledge base to make decisions at intersections. The decision making system performs real-time reasoning using traffic regulations and a part of the map information from the knowledge base.

Many Advanced Driver Assistance Systems (ADAS) have been developed to improve car safety. However, it is still a challenging problem to make autonomous vehicles to drive safely on urban streets such as uncontrolled intersections (without traffic lights) and narrow roads. In this paper, we introduce a decision making system that can assist autonomous vehicles at uncontrolled intersections and narrow roads. We constructed a machine understandable ontology-based Knowledge Base, which contains maps and traffic regulations. The system makes decisions in comply with traffic regulations such as Right-Of-Way rules when it receives a collision warning signal. The decisions are sent to a path planning system to change the route or stop to avoid collisions.

This paper proposes a novel approach to train word embeddings to capture antonyms. Word embeddings have shown to capture synonyms and analogies. Such word embeddings, however, cannot capture antonyms since they depend on the distributional hypothesis. Our approach utilizes supervised synonym and antonym information from thesauri, as well as distributional information from large-scale unlabelled text data. The evaluation results on the GRE antonym question task show that our model outperforms the state-of-the-art systems and it can answer the antonym questions in the F-score of 89%.

This paper proposes a history-based structured learning approach that jointly extracts entities and relations in a sentence.We introduce a novel simple and flexible table representation of entities and relations.We investigate several feature settings, search orders, and learning methods with inexact search on the table.The experimental results demonstrate that a joint learning approach significantly outperforms a pipeline approach by incorporating global features and by selecting appropriate learning methods and search orders.

So far, the disaster information has been offered based on a text and an image conventionally. With the substantiality of the recent information infrastructure, a disaster prevention system can offer disaster information on top of Web-GIS a lot. Because information of the stricken area is not considered as the form which takes care of temporal occasion in the existing system, the time change of the disaster cannot be adequately identified. In this paper, we established a domain called the seek bar which can make change disaster information in Web-GIS seamlessly with an axis in time and offered unified operations by chronological order. Thus, using seek bar operations, the disaster information combining with Web-GIS functions can be shown to observe in the temporal and special expressions to easily understand the tendency of disaster in elapsed time.

BACKGROUND: Due to the rapidly expanding body of biomedical literature, biologists require increasingly sophisticated and efficient systems to help them to search for relevant information. Such systems should account for the multiple written variants used to represent biomedical concepts, and allow the user to search for specific pieces of knowledge (or events) involving these concepts, e.g., protein-protein interactions. Such functionality requires access to detailed information about words used in the biomedical literature. Existing databases and ontologies often have a specific focus and are oriented towards human use. Consequently, biological knowledge is dispersed amongst many resources, which often do not attempt to account for the large and frequently changing set of variants that appear in the literature. Additionally, such resources typically do not provide information about how terms relate to each other in texts to describe events. RESULTS: This article provides an overview of the design, construction and evaluation of a large-scale lexical and conceptual resource for the biomedical domain, the BioLexicon. The resource can be exploited by text mining tools at several levels, e.g., part-of-speech tagging, recognition of biomedical entities, and the extraction of events in which they are involved. As such, the BioLexicon must account for real usage of words in biomedical texts. In particular, the BioLexicon gathers together different types of terms from several existing data resources into a single, unified repository, and augments them with new term variants automatically extracted from biomedical literature. Extraction of events is facilitated through the inclusion of biologically pertinent verbs (around which events are typically organized) together with information about typical patterns of grammatical and semantic behaviour, which are acquired from domain-specific texts. In order to foster interoperability, the BioLexicon is modelled using the Lexical Markup Framework, an ISO standard. CONCLUSIONS: The BioLexicon contains over 2.2 M lexical entries and over 1.8 M terminological variants, as well as over 3.3 M semantic relations, including over 2 M synonymy relations. Its exploitation can benefit both application developers and users. We demonstrate some such benefits by describing integration of the resource into a number of different tools, and evaluating improvements in performance that this can bring.

This paper describes our bio-event extraction system developed for the BioNLP 2009 Shared Task 2, with focus on its capability of extracting secondary biological event arguments from literature. Shared Task 2 is particularly interesting because when browsing literature, biologists often need to understand conditions surrounding biological events, which are usually expressed by secondary event arguments (e.g., binding sites). To achieve our goal, we take an approach that extracts n-ary relations from text using event extraction constraints automatically generated from a training corpus. Event constraints consist of sequences of trigger words and semantic roles which we automatically identify using Conditional Random Fields (CRFs). Unlike most other systems participating in this shared task, our system is light-weight and relies on neither external resources (e.g., Ontologies and dictionaries) nor natural language processing software (e.g., POS taggers and parsers). The official test results show that our approach performed well on extracting secondary arguments in Task 2, yielding the highest precision at 76.62% and the second highest F-measure at 43.22%.

The extraction of information from texts requires resources that contain both syntactic and semantic properties of lexical units. As the use of language in specialized domains, such as biology, can be very different to the general domain, there is a need for domain-specific resources to ensure that the information extracted is as accurate as possible. We are building a large-scale lexical resource for the biology domain, providing information about predicate-argument structure that has been bootstrapped from a biomedical corpus on the subject of E. Coli. The lexicon is currently focussed on verbs, and includes both automatically-extracted syntactic subcategorization frames, as well as semantic event frames that are based on annotation by domain experts. In addition, the lexicon contains manually-added explicit links between semantic and syntactic slots in corresponding frames. To our knowledge, this lexicon currently represents a unique resource within in the biomedical domain.

Kleio is an advanced information retrieval (IR) system developed at the UK National Centre for Text Mining (NaCTeM)1. The system offers textual and metadata searches across MEDLINE and provides enhanced searching functionality by leveraging terminology management technologies.

BACKGROUND: When term ambiguity and variability are very high, dictionary-based Named Entity Recognition (NER) is not an ideal solution even though large-scale terminological resources are available. Many researches on statistical NER have tried to cope with these problems. However, it is not straightforward how to exploit existing and additional Named Entity (NE) dictionaries in statistical NER. Presumably, addition of NEs to an NE dictionary leads to better performance. However, in reality, the retraining of NER models is required to achieve this. We chose protein name recognition as a case study because it most suffers the problems related to heavy term variation and ambiguity. METHODS: We have established a novel way to improve the NER performance by adding NEs to an NE dictionary without retraining. In our approach, first, known NEs are identified in parallel with Part-of-Speech (POS) tagging based on a general word dictionary and an NE dictionary. Then, statistical NER is trained on the POS/PROTEIN tagger outputs with correct NE labels attached. RESULTS: We evaluated performance of our NER on the standard JNLPBA-2004 data set. The F-score on the test set has been improved from 73.14 to 73.78 after adding protein names appearing in the training data to the POS tagger dictionary without any model retraining. The performance further increased to 78.72 after enriching the tagging dictionary with test set protein names. CONCLUSION: Our approach has demonstrated high performance in protein name recognition, which indicates how to make the most of known NEs in statistical NER.

This paper investigates multi-topic aspects in automatic classification of clinical free text. In many practical situ- ations, we need to deal with documents overlapping with multiple topics. Automatic assignment of multiple ICD-9- CM codes to clinical free text in medical records is a typi- cal multi-topic text classification problem. In this paper, we facilitate two different views on multi-topics. The Closed Topic Assumption (CTA) regards an absence of topics for a document as an explicit declaration that this document does not belong to those absent topics. In contrast, the Open Topic Assumption (OTA) considers the missing topics as neutral topics. This paper compares performances of vari- ous interpretations of a multi-topic Text Classification prob- lem into a Machine Learning problem. Experimental results show that the characteristics of multi-topic assignments in the Medical NLP Challenge data is OTA-oriented.

This paper describes a client-server speech translation platform designed for use at mobile terminals. Because terminals and servers are connected via a 3G public mobile phone networks, speech translation services are available at various places with thin client. This platform realizes hands-free communication and robustness for real use of speech translation in noisy environments. A microphone array and new noise suppression technique improves speech recognition performance, and a corpus-based approach enables wide coverage, robustness and portability to new languages and domains. The experimental result for evaluating the communicability of speakers of different languages shows that task completion rates using the speech translation system of 85% and 75% are achieved for Japanese- English and Japanese-Chinese, respectively. The system also has the ability to convey approximately one item of information per 2 utterances (one turn) on average for both Japanese-English and Japanese-Chinese in a task-oriented dialogue.

In this paper, we propose a new contextdependent SMT model that is tightly coupled with a language model.It is designed to decrease the translation ambiguities and efficiently search for an optimal hypothesis by reducing the hypothesis search space.It works through reciprocal incorporation between source and target context: a source word is determined by the context of previous and corresponding target words and the next target word is predicted by the pair consisting of the previous target word and its corresponding source word.In order to alleviate the data sparseness in chunk-based translation, we take a stepwise back-off translation strategy.Moreover, in order to obtain more semantically plausible translation results, we use bilingual verb-noun collocations; these are automatically extracted by using chunk alignment and a monolingual dependency parser.As a case study, we experimented on the language pair of Japanese and Korean.As a result, we could not only reduce the search space but also improve the performance.

This paper regards Question Answering (QA) as Question-Biased Term Extraction (QBTE). This new QBTE approach liberates QA systems from the heavy burden imposed by question types (or answer types). In conventional approaches, a QA system analyzes a given question and determines the question type, and then it selects answers from among answer candidates that match the question type. Consequently, the output of a QA system is restricted by the design of the question types. The QBTE directly extracts answers as terms biased by the question. To confirm the feasibility of our QBTE approach, we conducted experiments on the CRL QA Data based on 10-fold cross validation, using Maximum Entropy Models (MEMs) as an ML technique. Experimental results showed that the trained system achieved 0.36 in MRR and 0.47 in Top5 accuracy.

This paper proposes the "Hierarchical Directed Acyclic Graph (HDAG) Kernel" for structured natural language data. The HDAG Kernel directly accepts several levels of both chunks and their relations, and then efficiently computes the weighed sum of the number of common attribute sequences of the HDAGs. We applied the proposed method to question classification and sentence alignment tasks to evaluate its performance as a similarity measure and a kernel function. The results of the experiments demonstrate that the HDAG Kernel is superior to other kernel functions and baseline methods.

This paper devises a novel kernel function for structured natural language data. In the field of Natural Language Processing, feature extraction consists of the following two steps: (1) syntactically and semantically analyzing raw data, i.e., character strings, then representing the results as discrete structures, such as parse trees and dependency graphs with part-of-speech tags; (2) creating (possibly high-dimensional) numerical feature vectors from the discrete structures. The new kernels, called Hier- archical Directed Acyclic Graph (HDAG) kernels, directly accept DAGs whose nodes can contain DAGs. HDAG data structures are needed to fully reflect the syntactic and semantic structures that natural language data inherently have. In this paper, we define the kernel function and show how it permits efficient calculation. Experiments demonstrate that the proposed kernels are superior to existing kernel functions, e.g., se- quence kernels, tree kernels, and bag-of-words kernels.

The purpose of this study is to develop the basic theories and techniques for a plant inspection and diagnosis robot (IDR). The robot dealt with in this study will work in a large scale unmanned plant or a place with dangerous environment. It has the ability to monitor the condition of plant machinery with only few sensors, and quickly to discriminate machine failures, in order to guarantee both the quality and quantity of production against accident. The paper proposes a method for detecting a faulty part of a plant machine by the robot. A manipulator installed on the IDR is controlled by genetic algorithms (GA). A microphone installed on the manipulator tip is used to detect a failure signal. It is navigated to the nearby front of the faulty part by sound information and GA control. The method has been proved by practical applications.

Recent production system applications have been experiencing exceedingly difficult software maintenance problems. This is because the control of rule firings has been buried in the production rules themselves. To cope with this problem, we propose a meta-level control architecture for production systems, where procedural programming languages, such as Lisp and C, are employed to explicitly describe the control plans of production systems. The key idea of the architecture is to view production systems as a collection of independent rule processes, each of which monitors the global database and performs actions when its conditions are satisfied by the database. Procedural Control Macros (PCMs), which are based on C.A.R. Hoare's (1978) CSP, are then introduced into procedural programming languages to establish communication with the collection of rule processes. Although the PCMs are simple and easy to implement, the readability and maintainability of production system applications are greatly enhanced. Together with the original facilities of procedural languages, the PCMs enable users to efficiently specify the control plans for production systems. Furthermore, since control information is gathered into control plans, production rules can be declarative and thereby application-independent. This new feature makes it possible to develop large-scale shared rule bases.>

The authors demonstrate the enhancement in maintainability made possible by introducing meta-level control architectures to production systems. They assess the amount of effort expended in upgrading a rule base through the range referred to by maintenance staff for rule base upgrading. The rule base of an intelligent CAI system currently in operation that employs the meta-level control architecture and an identical one without the architecture have been upgraded so that they satisfy the same upgraded specifications. The measured range confirms that the meta-level control architecture curtails the effort expended in upgrading the rule base by 19%. In particular, the effort expended in upgrading control flow is reduced by 41%.

Polarization-maintaining optical fibers are developed for installation in a submarine optical repeater. These fibers preserve the polarization of light emitted from laser diodes (LD's) to a single-mode fiber through a light-switching coupler. Crosstalk of less than -30 dB in a l-m length of these optical fibers, called PANDA optical fibers, is achieved with a bending radius greater than 10 mm, twists of less than 60 turns, and tension of less than 3 kg, and ambient temperatures of -20-80°C. The mechanical strength of these fibers is the same as that of single-mode fibers.