Efficiently extracting data from tables in the scientific literature is pivotal for building large-scale databases. However, the tables reported in materials science papers exist in highly diverse forms; thus, rule-based extractions are an ineffective approach. To overcome this challenge, the study presents MaTableGPT, which is a GPT-based table data extractor from the materials science literature. MaTableGPT features key strategies of table data representation and table splitting for better GPT comprehension and filtering hallucinated information through follow-up questions. When applied to a vast volume of water splitting catalysis literature, MaTableGPT achieves an extraction accuracy (total F1 score) of up to 96.8%. Through comprehensive evaluations of the GPT usage cost, labeling cost, and extraction accuracy for the learning methods of zero-shot, few-shot, and fine-tuning, the study presents a Pareto-front mapping where the few-shot learning method is found to be the most balanced solution owing to both its high extraction accuracy (total F1 score >95%) and low cost (GPT usage cost of 5.97 US dollars and labeling cost of 10 I/O paired examples). The statistical analyses conducted on the database generated by MaTableGPT revealed valuable insights into the distribution of the overpotential and elemental utilization across the reported catalysts in the water splitting literature.

This paper describes a machine learning and data science pipeline for structured information extraction from documents, implemented as a suite of open-source tools and extensions to existing tools. It centers around a methodology for extracting procedural information in the form of recipes, stepwise procedures for creating an artifact (in this case synthesizing a nanomaterial), from published scientific literature. From our overall goal of producing recipes from free text, we derive the technical objectives of a system consisting of pipeline stages: document acquisition and filtering, payload extraction, recipe step extraction as a relationship extraction task, recipe assembly, and presentation through an information retrieval interface with question answering (QA) functionality. This system meets computational information and knowledge management (CIKM) requirements of metadata-driven payload extraction, named entity extraction, and relationship extraction from text. Functional contributions described in this paper include semi-supervised machine learning methods for PDF filtering and payload extraction tasks, followed by structured extraction and data transformation tasks beginning with section extraction, recipe steps as information tuples, and finally assembled recipes. Measurable objective criteria for extraction quality include precision and recall of recipe steps, ordering constraints, and QA accuracy, precision, and recall. Results, key novel contributions, and significant open problems derived from this work center around the attribution of these holistic quality measures to specific machine learning and inference stages of the pipeline, each with their performance measures. The desired recipes contain identified preconditions, material inputs, and operations, and constitute the overall output generated by our computational information and knowledge management (CIKM) system. Within the overall pipeline, we have applied machine learning approaches to step classification and, in continuing work, are applying these approaches to the subtasks of feature extraction, document filtering and classification, text payload extraction, recipe step identification, and multi-step assembly.

ISO/IEC-11179 is an international standard that documents the standardization and registration of metadata to make data understandable and shareable. This standardization and registration allows for easier locating, retrieving, and transmitting data from disparate databases. The standard defines the how metadata are conceptually modeled and how they are shared among parties, but does not define how data is physically represented as bits and bytes. The standard consists of six parts. Part 1 provides a high-level overview of the standard and defines the basic element of a metadata registry - a data element. Part 2 defines the procedures for registering classification schemes and classifying administered items in a metadata registry (MDR). Part 3 specifies the structure of an MDR. Part 4 specifies requirements and recommendations for constructing definitions for data and metadata. Part 5 defines how administered items are named and identified. Part 6 defines how administered items are registered and assigned an identifier.

The Java Metadata Facility is introduced by Java Specification Request (JSR) 175 [1], and incorporated into the Java language specification [2] in version 1.5 of the language. The specification allows annotations on Java program elements: classes, interfaces, methods, and fields. Annotations give programmers a uniform way to add metadata to program elements that can be used by code checkers, code generators, or other compile-time or runtime components. Annotations are defined by annotation types. These are defined the same way as interfaces, but with the symbol {at} preceding the interface keyword. There are additional restrictions on defining annotation types: (1) They cannot be generic; (2) They cannot extend other annotation types or interfaces; (3) Methods cannot have any parameters; (4) Methods cannot have type parameters; (5) Methods cannot throw exceptions; and (6) The return type of methods of an annotation type must be a primitive, a String, a Class, an annotation type, or an array, where the type of the array is restricted to one of the four allowed types. See [2] for additional restrictions and syntax. The methods of an annotation type define the elements that may be used to parameterize the annotation in code. Annotation types may have defaultmore » values for any of its elements. For example, an annotation that specifies a defect report could initialize an element defining the defect outcome submitted. Annotations may also have zero elements. This could be used to indicate serializability for a class (as opposed to the current Serializability interface).« less

Event detection from text data is an active area of research. While the emphasis in the literature has been on event identification and labeling using a single data source, this work considers event and story line detection when using a large number of data sources. In this setting, it is natural for different events in the same domain, e.g., violence, sports, politics, to occur at the same time and for different story lines about the same event to emerge. To capture events in this setting, we propose an Offline algorithm that detects events and story lines about events for a target domain given a news article collection. Our algorithm leverages a multi-relational sentence-level semantic graph and well-known graph properties to identify overlapping events and story lines within the events. We then extend this algorithm for an Online setting. Both the Offline and Online approaches are evaluated using two large data sets containing millions of news articles from a large number of sources. Our empirical analysis shows that methods using the proposed semantic graph beat the state of the art in terms of precision and recall while providing more complete event summaries.

Event detection from text data is an active area of research. While the emphasis has been on event identification and labeling using a single data source, this work considers event and story line detection when using a large number of data sources. In this setting, it is natural for different events in the same domain, e.g. violence, sports, politics, to occur at the same time and for different story lines about the same event to emerge. To capture events in this setting, we propose an algorithm that detects events and story lines about events for a target domain. Our algorithm leverages a multi-relational sentence level semantic graph and well known graph properties to identify overlapping events and story lines within the events. We evaluate our approach on two large data sets containing millions of news articles from a large number of sources. Our empirical analysis shows that our approach improves the detection precision and recall by 10% to 25%, while providing complete event summaries.

Meta paths are good mechanisms to improve the quality of graph analysis on heterogeneous information networks. This paper presents a meta path graph clustering framework, VEPATHCLUSTER, that combines meta path vertex-centric clustering with meta path edge-centric clustering for improving the clustering quality of heterogeneous networks. First, we propose an edge-centric path graph model to capture the meta-path dependencies between pairwise path edges. We model a heterogeneous network containing M types of meta paths as M vertex-centric path graphs and M edge-centric path graphs. Second, we propose a clustering-based multigraph model to capture the fine-grained clustering-based relationships between pairwise vertices and between pairwise path edges. We perform clustering analysis on both a unified vertex-centric path graph and each edge-centric path graph to generate vertex clustering and edge clusterings of the original heterogeneous network respectively. Third, a reinforcement algorithm is provided to tightly integrate vertex-centric clustering and edge-centric clustering by mutually enhancing each other. Finally, an iterative learning strategy is presented to dynamically refine both vertex-centric clustering and edge-centric clustering by continuously learning the contributions and adjusting the weights of different path graphs.

I am pleased to bring you Web Services Research and Practices. Web services technology has been widely admitted as the future technology for Internet computing and distributed computing. As the second volume in the IGI Advanced Book Series, this book provides researchers, practitioners, and educators with the most current research results in the field in 10 chapters. The chapter discusses the overhead of network bandwidth using SOAP for service integration. The authors explore compression strategies through a detailed survey and evaluation of state-of-the-art binary encoding techniques for SOAP. The chapter also introduces an experimental concept for SOAP compression based on differential encoding, which makes use of the commonly available WSDL description of a SOAP Web service. The chapter presents a network adaptable middleware that strikes a compromise between the encoding/decoding and associated overhead of data compression to enhance response time of Web services. Chapter III is titled " Realizability Analysis of Top-Down Web Service Composition Specifications " by Xiang Fu, Tevfik Bultan, and Jianwen Su. The chapter presents " conversation protocol, " a top-down specification approach to study the realizability problem of conversation protocols.

The authors investigated the use of microblogs—or weibos—and related censorship practices using 111 million microblogs collected between 1 January and 30 June 2012. Using a matched case-control study design helped researchers determine a list of Chinese terms that discriminate censored and uncensored posts written by the same microbloggers. This list includes homophones and puns created by Chinese microbloggers to circumvent the censors successfully. The study's design also allowed for evaluating the new real-name registration system's impact on microbloggers' posting activities. Findings suggest that this policy might have stopped some microbloggers from writing about social and political subjects.

We apply two new automated semantic evaluations to three distinct latent topic models. Both metrics have been shown to align with human evaluations and provide a balance between internal measures of information gain and comparisons to human ratings of coherent topics. We improve upon the measures by introducing new aggregate measures that allows for comparing complete topic models. We further compare the automated measures to other metrics for topic models, comparison to manually crafted semantic tests and document classification. Our experiments reveal that LDA and LSA each have different strengths; LDA best learns descriptive topics while LSA is best at creating a compact semantic representation of documents and words in a corpus.

Analysts are overwhelmed with information. They have large archives of historical data, both structured and unstructured, and continuous streams of relevant messages and documents that they need to match to current tasks, digest, and incorporate into their analysis. The purpose of the READ project is to develop technologies to make it easier to catalog, classify, and locate relevant information. We approached this task from multiple angles. First, we tackle the issue of processing large quantities of information in reasonable time. Second, we provide mechanisms that allow users to customize their queries based on latent topics exposed from corpus statistics. Third, we assist users in organizing query results, adding localized expert structure over results. Forth, we use word sense disambiguation techniques to increase the precision of matching user generated keyword lists with terms and concepts in the corpus. Fifth, we enhance co-occurrence statistics with latent topic attribution, to aid entity relationship discovery. Finally we quantitatively analyze the quality of three popular latent modeling techniques to examine under which circumstances each is useful.

An explosive growth of online news has taken place. Users are inundated with thousands of news articles, only some of which are interesting. A system to filter out uninteresting articles would aid users that need to read and analyze many articles daily, such as financial analysts and government officials. The most obvious approach for reducing the amount of information overload is to learn keywords of interest for a user (Carreira et al., 2004). Although filtering articles based on keywords removes many irrelevant articles, there are still many uninteresting articles that are highly relevant to keyword searches. A relevant article may not be interesting for various reasons, such as the article’s age or if it discusses an event that the user has already read about in other articles. Although it has been shown that collaborative filtering can aid in personalized recommendation systems (Wang et al., 2006), a large number of users is needed. In a limited user environment, such as a small group of analysts monitoring news events, collaborative filtering would be ineffective. The definition of what makes an article interesting – or its “interestingness” – varies from user to user and is continually evolving, calling for adaptable user personalization. Furthermore, due to the nature of news, most articles are uninteresting since many are similar or report events outside the scope of an individual’s concerns. There has been much work in news recommendation systems, but none have yet addressed the question of what makes an article interesting.

We consider the problem of a user navigating an unfamiliar corpus of text documents where document metadata is limited or unavailable, the domain is specialized, and the user base is small. These challenging conditions may hold, for example, within an organization such as a business or government agency. We propose to augment standard keyword search with user feedback on latent topics. These topics are automatically learned from the corpus in an unsupervised manner and presented alongside search results. User feedback is then used to reformulate the original query, resulting in improved information retrieval performance in our experiments.

How to organize and present search results plays a critical role in the utility of search engines. Due to the unprecedented scale of the Web and diversity of search results, the common strategy of ranked lists has become increasingly inadequate, and clustering has been considered as a promising alternative. Clustering divides a long list of disparate search results into a few topic-coherent clusters, allowing the user to quickly locate relevant results by topic navigation. While many clustering algorithms have been proposed that innovate on the automatic clustering procedure, we introduce ClusteringWiki, the first prototype and framework for personalized clustering that allows direct user editing of clustering results. Through a Wiki interface, the user can edit and annotate the membership, structure and labels of clusters for a personalized presentation. In addition, the edits and annotations can be shared among users as a mass collaborative way of improving search result organization and search engine utility.

How to organize and present search results plays a critical role in the utility of search engines. Due to the unprecedented scale of the Web and diversity of search results, the common strategy of ranked lists has become increasingly inadequate, and clustering has been considered as a promising alternative. Clustering divides a long list of disparate search results into a few topic-coherent clusters, allowing the user to quickly locate relevant results by topic navigation. While many clustering algorithms have been proposed that innovate on the automatic clustering procedure, we introduce ClusteringWiki, the first prototype and framework for personalized clustering that allows direct user editing of the clustering results. Through a Wiki interface, the user can edit and annotate the membership, structure and labels of clusters for a personalized presentation. In addition, the edits and annotations can be shared among users as a mass-collaborative way of improving search result organization and search engine utility.

Despite the existence of several noun phrase coreference resolution data sets as well as several formal evaluations on the task, it remains frustratingly difficult to compare results across different coreference resolution systems. This is due to the high cost of implementing a complete end-to-end coreference resolution system, which often forces researchers to substitute available gold-standard information in lieu of implementing a module that would compute that information. Unfortunately, this leads to inconsistent and often unrealistic evaluation scenarios. With the aim to facilitate consistent and realistic experimental evaluations in coreference resolution, we present Reconcile, an infrastructure for the development of learning-based noun phrase (NP) coreference resolution systems. Reconcile is designed to facilitate the rapid creation of coreference resolution systems, easy implementation of new feature sets and approaches to coreference resolution, and empirical evaluation of coreference resolvers across a variety of benchmark data sets and standard scoring metrics. We describe Reconcile and present experimental results showing that Reconcile can be used to create a coreference resolver that achieves performance comparable to state-of-the-art systems on six benchmark data sets.

Multivariate analysis deals with the statistical analysis of observations where there are multiple responses on each observational unit. Let X be ann ́ p data matrix where the rows represent observations and the columns, variables. We will denote the variables by X1, X2, ..., Xp. In most cases, it is necessary to sphere the data by subtracting out the means and dividing by the standard deviations. If outliers are a possibility, then a robust sphering method such as that discussed by Venables and Ripley [44, p. 266] should also be tried. Important special cases are p = 1, 2, 3 which correspond to univariate, bivariate and trivariate data.

Despite the availability of standard data sets and metrics, approaches to the problem of noun phrase coreference resolution are hard to compare empirically due to the different evaluation setting stemming, in part, from the lack of comprehensive coreference resolution research platforms. In this tech report we present Reconcile, a coreference resolution research platform that aims to facilitate the implementation of new approaches to coreference resolution as well as the comparison of existing approaches. We discuss Reconcile's architecture and give results of running Reconcile on six data sets using four evaluation metrics, showing that Reconcile's performance is comparable to state-of-the-art systems in coreference resolution.