Pattern Matching Rules Research Articles

The Value of Numbers in Clinical Text Classification

Clinical text often includes numbers of various types and formats. However, most current text classification approaches do not take advantage of these numbers. This study aims to demonstrate that using numbers as features can significantly improve the performance of text classification models. This study also demonstrates the feasibility of extracting such features from clinical text. Unsupervised learning was used to identify patterns of number usage in clinical text. These patterns were analyzed manually and converted into pattern-matching rules. Information extraction was used to incorporate numbers as features into a document representation model. We evaluated text classification models trained on such representation. Our experiments were performed with two document representation models (vector space model and word embedding model) and two classification models (support vector machines and neural networks). The results showed that even a handful of numerical features can significantly improve text classification performance. We conclude that commonly used document representations do not represent numbers in a way that machine learning algorithms can effectively utilize them as features. Although we demonstrated that traditional information extraction can be effective in converting numbers into features, further community-wide research is required to systematically incorporate number representation into the word embedding process.

Predicate Pushdown for Data Science Pipelines

Predicate pushdown is a widely adopted query optimization. Existing systems and prior work mostly use pattern-matching rules to decide when a predicate can be pushed through certain operators like join or groupby. However, challenges arise in optimizing for data science pipelines due to the widely used non-relational operators and user-defined functions (UDF) that existing rules would fail to cover. In this paper, we present MagicPush, which decides predicate pushdown using a search-verification approach.MagicPush searches for candidate predicates on pipeline input, which is often not the same as the predicate to be pushed down, and verifies that the pushdown does not change pipeline output with full correctness guarantees. Our evaluation on TPC-H queries and 200 real-world pipelines sampled from GitHub Notebooks shows that MagicPush substantially outperforms a strong baseline that uses a union of rules from prior work - it is able to discover new pushdown opportunities and better optimize 42 real-world pipelines with up to 99% reduction in running time, while discovering all pushdown opportunities found by the existing baseline on remaining cases.

Unsupervised Numerical Information Extraction via Exploiting Syntactic Structures

Numerical information plays an important role in various fields such as scientific, financial, social, statistics, and news. Most prior studies adopt unsupervised methods by designing complex handcrafted pattern-matching rules to extract numerical information, which can be difficult to scale to the open domain. Other supervised methods require extra time, cost, and knowledge to design, understand, and annotate the training data. To address these limitations, we propose QuantityIE, a novel approach to extracting numerical information as structured representations by exploiting syntactic features of both constituency parsing (CP) and dependency parsing (DP). The extraction results may also serve as distant supervision for zero-shot model training. Our approach outperforms existing methods from two perspectives: (1) the rules are simple yet effective, and (2) the results are more self-contained. We further propose a numerical information retrieval approach based on QuantityIE to answer analytical queries. Experimental results on information extraction and retrieval demonstrate the effectiveness of QuantityIE in extracting numerical information with high fidelity.

An evaluation of existing text de-identification tools for use with patient progress notes from Australian general practice

IntroductionDigitized patient progress notes from general practice represent a significant resource for clinical and public health research but cannot feasibly and ethically be used for these purposes without automated de-identification. Internationally, several open-source natural language processing tools have been developed, however, given wide variations in clinical documentation practices, these cannot be utilized without appropriate review. We evaluated the performance of four de-identification tools and assessed their suitability for customization to Australian general practice progress notes. MethodsFour tools were selected: three rule-based (HMS Scrubber, MIT De-id, Philter) and one machine learning (MIST). 300 patient progress notes from three general practice clinics were manually annotated with personally identifying information. We conducted a pairwise comparison between the manual annotations and patient identifiers automatically detected by each tool, measuring recall (sensitivity), precision (positive predictive value), f1-score (harmonic mean of precision and recall), and f2-score (weighs recall 2x higher than precision). Error analysis was also conducted to better understand each tool’s structure and performance. ResultsManual annotation detected 701 identifiers in seven categories. The rule-based tools detected identifiers in six categories and MIST in three. Philter achieved the highest aggregate recall (67%) and the highest recall for NAME (87%). HMS Scrubber achieved the highest recall for DATE (94%) and all tools performed poorly on LOCATION. MIST achieved the highest precision for NAME and DATE while also achieving similar recall to the rule-based tools for DATE and highest recall for LOCATION. Philter had the lowest aggregate precision (37%), however preliminary adjustments of its rules and dictionaries showed a substantial reduction in false positives. ConclusionExisting off-the-shelf solutions for automated de-identification of clinical text are not immediately suitable for our context without modification. Philter is the most promising candidate due to its high recall and flexibility however will require extensive revising of its pattern matching rules and dictionaries.

Medical Image Analysis Using Deep Learning and Distribution Pattern Matching Algorithm

Artificial intelligence plays an essential role in the medical and health industries. Deep convolution networks offer valuable services and help create automated systems to perform medical image analysis. However, convolution networks examine medical images effectively; such systems require high computational complexity when recognizing the same disease-affected region. Therefore, an optimized deep convolution network is utilized for analyzing disease-affected regions in this work. Different disease-related medical images are selected and examined pixel by pixel; this analysis uses the gray wolf optimized deep learning network. This method identifies affected pixels by the gray wolf hunting process. The convolution network uses an automatic learning function that predicts the disease affected by previous imaging analysis. The optimized algorithm-based selected regions are further examined using the distribution pattern-matching rule. The pattern-matching process recognizes the disease effectively, and the system's efficiency is evaluated using the MATLAB implementation process. This process ensures high accuracy of up to 99.02% to 99.37% and reduces computational complexity.

Instance-Based Zero-Shot learning for semi-Automatic MeSH indexing

• Propose an instance-based Zero-shot learning method for facilitating the semi-automatic indexing of biomedical articles. • Novel labels of complex ontologies are ranked through exploiting similarity functions on an arbitrary semantic space. • We design a hybrid criterion based on underlying label dependencies, semantic similarities and pattern matching rules. • Robust ranking performance of the novel labels is obtained for ideal, artificially noisy and realistic oracles. • We obtain promising multi-label ranking performance regarding the novel labels on the last version of the PubMed dataset. Zero-shot learning constitutes a variant of the broader category of weakly supervised learning algorithms. Its main asset is the possibility of identifying entities for which no training data are provided in advance. Under this extreme scenario, conventional supervised learning methods cannot operate properly, while consumption of human resources for obtaining even limited instances may be highly restricted, especially when the label space is quite complex because of its cardinality and the underlying semantic dependencies. However, removing the human factor from the learning loop under complicated tasks cannot guarantee robust performance. Thus, semi-automated solutions are widely accepted by both the research and industrial communities, favoring cooperation of human and machine, mainly for alleviating the spent effort of the former, and for acquiring safer predictions. In contrast with the majority of existing Zero-shot learning approaches, we propose a generalized instance-based method oriented towards tackling the Multi-label classification task without performing any transductive operations over the test instances. Instead, we aim to provide a label ranking of the unseen classes exploiting sentence-based semantic embeddings and label similarities, through a dedicated fine-tuned language representational model. We also use a pattern matching rule to further boost the ranking of our method. Some realistic assumptions are made in order for our approach to work correctly and provide said ranking. Results on a biomedical database with a semantically rich fine-grained label space are really promising, rendering its utilization as a helpful and computationally inexpensive tool for facilitating semi-automated indexing.

Ontology and rule-based natural language processing approach for interpreting textual regulations on underground utility infrastructure

The nation’s massive underground utility infrastructure must comply with a multitude of regulations. The regulatory compliance checking of underground utilities requires an objective and consistent interpretation of the regulations. However, utility regulations contain a variety of domain-specific terms and numerous spatial constraints regarding the location and clearance of underground utilities. It is challenging for the interpreters to understand both the domain and spatial semantics in utility regulations. To address the challenge, this paper adopts an ontology and rule-based Natural Language Processing (NLP) framework to automate the interpretation of utility regulations – the extraction of regulatory information and the subsequent transformation into logic clauses. Two new ontologies have been developed. The urban product ontology (UPO) is domain-specific to model domain concepts and capture domain semantics on top of heterogeneous terminologies in utility regulations. The spatial ontology (SO) consists of two layers of semantics – linguistic spatial expressions and formal spatial relations – for better understanding the spatial language in utility regulations. Pattern-matching rules defined on syntactic features (captured using common NLP techniques) and semantic features (captured using ontologies) were encoded for information extraction. The extracted information elements were then mapped to their semantic correspondences via ontologies and finally transformed into deontic logic (DL) clauses to achieve the semantic and logical formalization. The approach was tested on the spatial configuration-related requirements in utility accommodation policies. Results show it achieves a 98.2% precision and a 94.7% recall in information extraction, a 94.4% precision and a 90.1% recall in semantic formalization, and an 83% accuracy in logical formalization.

IMPLEMENTING INDONESIAN LANGUAGE CHATBOT FOR ECOMMERCE SITE USING ARTIFICIAL INTELLIGENCE MARKUP LANGUAGE (AIML)

E-Commerce becomes one of the hits in the online world nowadays. Peopleare tending to buy things online. Some e-commerce sites providechatting withtheir contact person to get in touch with their customers every time. However,there is another alternative to get in touch with the customers, which is usingChatbot. It can be used for 24 hours every day as long as the server is on. It canhelp customers to know more about the products. Furthermore, customers getinformation that being asked. This Chatbot is built using Artificial IntelligenceMarkup Language (AIML) and Pandorabots as the interpreter. This researchaims to found right AIML interpreter which can be used in Indonesianlanguage E-Commerce website. By holding experiment with respondent, itsaccuracy is measured. The result shows that the Chatbot still needsimprovement. Chatbot knowledge pattern matching rules should be enrichedbased on the questions that customers input in order to construct rules.

Automatically Tagging Constructions of Causation and Their Slot-Fillers

This paper explores extending shallow semantic parsing beyond lexical-unit triggers, using causal relations as a test case. Semantic parsing becomes difficult in the face of the wide variety of linguistic realizations that causation can take on. We therefore base our approach on the concept of constructions from the linguistic paradigm known as Construction Grammar (CxG). In CxG, a construction is a form/function pairing that can rely on arbitrary linguistic and semantic features. Rather than codifying all aspects of each construction’s form, as some attempts to employ CxG in NLP have done, we propose methods that offload that problem to machine learning. We describe two supervised approaches for tagging causal constructions and their arguments. Both approaches combine automatically induced pattern-matching rules with statistical classifiers that learn the subtler parameters of the constructions. Our results show that these approaches are promising: they significantly outperform naïve baselines for both construction recognition and cause and effect head matches.

MPTM: A tool for mining protein post-translational modifications from literature.

Due to the importance of post-translational modifications (PTMs) in human health and diseases, PTMs are regularly reported in the biomedical literature. However, the continuing and rapid pace of expansion of this literature brings a huge challenge for researchers and database curators. Therefore, there is a pressing need to aid them in identifying relevant PTM information more efficiently by using a text mining system. So far, only a few web servers are available for mining information of a very limited number of PTMs, which are based on simple pattern matching or pre-defined rules. In our work, in order to help researchers and database curators easily find and retrieve PTM information from available text, we have developed a text mining tool called MPTM, which extracts and organizes valuable knowledge about 11 common PTMs from abstracts in PubMed by using relations extracted from dependency parse trees and a heuristic algorithm. It is the first web server that provides literature mining service for hydroxylation, myristoylation and GPI-anchor. The tool is also used to find new publications on PTMs from PubMed and uncovers potential PTM information by large-scale text analysis. MPTM analyzes text sentences to identify protein names including substrates and protein-interacting enzymes, and automatically associates them with the UniProtKB protein entry. To facilitate further investigation, it also retrieves PTM-related information, such as human diseases, Gene Ontology terms and organisms from the input text and related databases. In addition, an online database (MPTMDB) with extracted PTM information and a local MPTM Lite package are provided on the MPTM website. MPTM is freely available online at http://bioinformatics.ustc.edu.cn/mptm/ and the source codes are hosted on GitHub: https://github.com/USTC-HILAB/MPTM .

Tumour Classification and Analysis from Breast Cancer Pathology Reports using Natural Language Processing

Breast Cancer is the prime cause of death in Indian women. Hospitals in India use electronic means of collection and reporting of data. One such report is the Pathology report which has natural language narrations of the conditions of patients. This work aims to extract the details on Tumour (T) in the breast using pattern-matching rules and derive the pathological classification of T by applying the PTNM classification protocol by American Joint Committee on Cancer (AJCC). Information Retrieval (IR), Natural Language Processing (NLP) tasks and Information Extraction (IE) techniques are applied to develop an automated system to accomplish the task. The system analyzes the extracted and the classified values of T against the Gold Standard Values, which are derived by manual scrutiny of the reports. The evaluation of the performance of the automated system performed using three sets of Pathology reports, resulted in an average Precision of 86%, Recall of 82.7%, Specificity of 75.1% and Accuracy of 79.53%.

MeSHLabeler: improving the accuracy of large-scale MeSH indexing by integrating diverse evidence.

Motivation: Medical Subject Headings (MeSHs) are used by National Library of Medicine (NLM) to index almost all citations in MEDLINE, which greatly facilitates the applications of biomedical information retrieval and text mining. To reduce the time and financial cost of manual annotation, NLM has developed a software package, Medical Text Indexer (MTI), for assisting MeSH annotation, which uses k-nearest neighbors (KNN), pattern matching and indexing rules. Other types of information, such as prediction by MeSH classifiers (trained separately), can also be used for automatic MeSH annotation. However, existing methods cannot effectively integrate multiple evidence for MeSH annotation.Methods: We propose a novel framework, MeSHLabeler, to integrate multiple evidence for accurate MeSH annotation by using ‘learning to rank’. Evidence includes numerous predictions from MeSH classifiers, KNN, pattern matching, MTI and the correlation between different MeSH terms, etc. Each MeSH classifier is trained independently, and thus prediction scores from different classifiers are incomparable. To address this issue, we have developed an effective score normalization procedure to improve the prediction accuracy.Results: MeSHLabeler won the first place in Task 2A of 2014 BioASQ challenge, achieving the Micro F-measure of 0.6248 for 9,040 citations provided by the BioASQ challenge. Note that this accuracy is around 9.15% higher than 0.5724, obtained by MTI.Availability and implementation: The software is available upon request.Contact: zhusf@fudan.edu.cn

Semantic cache replacement strategy for XML algebra-based query optimization

Aiming at the fact that traditional cache replacement strategy lacks pertinence to the semantic cache in the process of extensible markup language (XML) algebra query, a replacement strategy based on the semantic cache contribution value is proposed. First, pattern matching rules for XML algebra query and semantic caches are given. Second, the method of calculating the semantic cache contribution value is proposed. In XML documents with four different sizes, the experimental results of time efficiency show that this strategy supports environment of the XML algebra query and it has better time efficiency than both least frequency used (LFU) and least recently used (LRU).

Who tweets? Deriving the demographic characteristics of age, occupation and social class from twitter user meta-data.

This paper specifies, designs and critically evaluates two tools for the automated identification of demographic data (age, occupation and social class) from the profile descriptions of Twitter users in the United Kingdom (UK). Meta-data data routinely collected through the Collaborative Social Media Observatory (COSMOS: http://www.cosmosproject.net/) relating to UK Twitter users is matched with the occupational lookup tables between job and social class provided by the Office for National Statistics (ONS) using SOC2010. Using expert human validation, the validity and reliability of the automated matching process is critically assessed and a prospective class distribution of UK Twitter users is offered with 2011 Census baseline comparisons. The pattern matching rules for identifying age are explained and enacted following a discussion on how to minimise false positives. The age distribution of Twitter users, as identified using the tool, is presented alongside the age distribution of the UK population from the 2011 Census. The automated occupation detection tool reliably identifies certain occupational groups, such as professionals, for which job titles cannot be confused with hobbies or are used in common parlance within alternative contexts. An alternative explanation on the prevalence of hobbies is that the creative sector is overrepresented on Twitter compared to 2011 Census data. The age detection tool illustrates the youthfulness of Twitter users compared to the general UK population as of the 2011 Census according to proportions, but projections demonstrate that there is still potentially a large number of older platform users. It is possible to detect “signatures” of both occupation and age from Twitter meta-data with varying degrees of accuracy (particularly dependent on occupational groups) but further confirmatory work is needed.

Using Tabled Logic Programming to Solve the Petrobras Planning Problem

AbstractTabling has been used for some time to improve efficiency of Prolog programs by memorizing answered queries. The same idea can be naturally used to memorize visited states during search for planning. In this paper we present a planner developed in the Picat language to solve the Petrobras planning problem. Picat is a novel Prolog-like language that provides pattern matching, deterministic and non-deterministic rules, and tabling as its core modelling and solving features. We demonstrate these capabilities using the Petrobras problem, where the goal is to plan transport of cargo items from ports to platforms using vessels with limited capacity. Monte Carlo Tree Search has been so far the best technique to tackle this problem and we will show that by using tabling we can achieve much better runtime efficiency and better plan quality.

A Naïve Bayes Approach to Classifying Topics in Suicide Notes

The authors present a system developed for the 2011 i2b2 Challenge on Sentiment Classification, whose aim was to automatically classify sentences in suicide notes using a scheme of 15 topics, mostly emotions. The system combines machine learning with a rule-based methodology. The features used to represent a problem were based on lexico–semantic properties of individual words in addition to regular expressions used to represent patterns of word usage across different topics. A naïve Bayes classifier was trained using the features extracted from the training data consisting of 600 manually annotated suicide notes. Classification was then performed using the naïve Bayes classifier as well as a set of pattern–matching rules. The classification performance was evaluated against a manually prepared gold standard consisting of 300 suicide notes, in which 1,091 out of a total of 2,037 sentences were associated with a total of 1,272 annotations. The competing systems were ranked using the micro-averaged F-measure as the primary evaluation metric. Our system achieved the F-measure of 53% (with 55% precision and 52% recall), which was significantly better than the average performance of 48.75% achieved by the 26 participating teams.

A Hybrid Approach to Sentiment Sentence Classification in Suicide Notes

This paper describes the sentiment classification system developed by the Mayo Clinic team for the 2011 I2B2/VA/Cincinnati Natural Language Processing (NLP) Challenge. The sentiment classification task is to assign any pertinent emotion to each sentence in suicide notes. We have implemented three systems that have been trained on suicide notes provided by the I2B2 challenge organizer—a machine learning system, a rule-based system, and a system consisting of a combination of both. Our machine learning system was trained on re-annotated data in which apparently inconsistent emotion assignment was adjusted. Then, the machine learning methods by RIPPER and multinomial Naïve Bayes classifiers, manual pattern matching rules, and the combination of the two systems were tested to determine the emotions within sentences. The combination of the machine learning and rule-based system performed best and produced a micro-average F-score of 0.5640.

Drug side effect extraction from clinical narratives of psychiatry and psychology patients

To extract physician-asserted drug side effects from electronic medical record clinical narratives. Pattern matching rules were manually developed through examining keywords and expression patterns of side effects to discover an individual side effect and causative drug relationship. A combination of machine learning (C4.5) using side effect keyword features and pattern matching rules was used to extract sentences that contain side effect and causative drug pairs, enabling the system to discover most side effect occurrences. Our system was implemented as a module within the clinical Text Analysis and Knowledge Extraction System. The system was tested in the domain of psychiatry and psychology. The rule-based system extracting side effects and causative drugs produced an F score of 0.80 (0.55 excluding allergy section). The hybrid system identifying side effect sentences had an F score of 0.75 (0.56 excluding allergy section) but covered more side effect and causative drug pairs than individual side effect extraction. The rule-based system was able to identify most side effects expressed by clear indication words. More sophisticated semantic processing is required to handle complex side effect descriptions in the narrative. We demonstrated that our system can be trained to identify sentences with complex side effect descriptions that can be submitted to a human expert for further abstraction. Our system was able to extract most physician-asserted drug side effects. It can be used in either an automated mode for side effect extraction or semi-automated mode to identify side effect sentences that can significantly simplify abstraction by a human expert.

Verifying higher-order functional programs with pattern-matching algebraic data types

Type-based model checking algorithms for higher-order recursion schemes have recently emerged as a promising approach to the verification of functional programs. We introduce pattern-matching recursion schemes (PMRS) as an accurate model of computation for functional programs that manipulate algebraic data-types. PMRS are a natural extension of higher-order recursion schemes that incorporate pattern-matching in the defining rules. This paper is concerned with the following (undecidable) verification problem: given a correctness property φ, a functional program ℘ ( qua PMRS) and a regular input set ℑ, does every term that is reachable from ℑ under rewriting by ℘ satisfy φ? To solve the PMRS verification problem, we present a sound semi-algorithm which is based on model-checking and counterexample guided abstraction refinement. Given a no-instance of the verification problem, the method is guaranteed to terminate. From an order- n PMRS and an input set generated by a regular tree grammar, our method constructs an order- n weak PMRS which over-approximates only the first-order pattern-matching behaviour, whilst remaining completely faithful to the higher-order control flow. Using a variation of Kobayashi's type-based approach, we show that the (trivial automaton) model-checking problem for weak PMRS is decidable. When a violation of the property is detected in the abstraction which does not correspond to a violation in the model, the abstraction is automatically refined by `unfolding' the pattern-matching rules in the program to give successively more and more accurate weak PMRS models.

Method for Extracting Product Information from TV Commercial

Television (TV) Commercial program contains important product information that displayed only in seconds. People who need that information has no insufficient time for noted it, even just for reading that information. This research work focus on automatically detect text and extract important information from a TV commercial to provide information in real time and for video indexing. We propose method for product information extraction from TV commercial using knowledge based system with pattern matching rule based method. Implementation and experiments on 50 commercial screenshot images achieved a high accuracy result on text extraction and information recognition.