Muhammad Abdul-Mageed, AbdelRahim Elmadany, El Moatez Billah Nagoudi, Dinesh Pabbi, Kunal Verma, Rannie Lin. Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume. 2021.

In this paper, we share our experiences creating NLP based AI platform for finance - Appzen (http://www.appzen.com). AppZen's auditing technology is being utilized by over 500 enterprise customers including multiple Fortune 500 companies for auditing employee expenses. AppZen's technology can process, analyze and identify relationships between various kinds of transaction documents such as - receipts, invoices, contracts and purchase orders. Each type of transaction document requires custom processing and analysis due to the diversity in language and structure of the document. Contracts typically require deep understanding of the content such as identifying sentence structures, identifying entities and relationships between them compared to receipts and invoices, which are somewhat semi-structured and require a different kind of processing. We elaborate on the challenges we have experienced and use of NLP in conjunction with a lightweight semantic layer to alleviate these challenges.

In this paper, we present an approach that jointly infers the boundaries of tokens and their labels to construct dictionaries for Information Extraction. Our approach for joint-inference is based on graph propagation, and extends it in two novel ways. First, we extend the graph representation to capture ambiguities that occur during the token extraction phase. Second, we modify the labeling phase (i.e., label propagation) to utilize this new representation, allowing evidence from labeling to be used for token extraction. Our evaluation shows these extensions (and hence our approach) significantly improve the performance of the outcome dictionaries over pipeline-based approaches by preventing aggressive commitment. Our evaluation also shows that our extensions over a base graph-propagation framework improve the precision without hurting the recall.

For large scale enterprise implementations, a key problem, that has not been tackled much, is the ability to automatically map users’ requirements to reference process models. We present a tool called Process Model Requirements Gap Analyzer (ProcGap), which uses a combination of natural language processing, information retrieval and semantic reasoning to automatically match and map textual requirements to industry-specific process models. We present the results of mapping requirements from an industry project to an existing process model. We compare our approach to two previously implemented approaches and show that our approach outperforms them. In a case study, we also found that a user group with ProcGap had better performance than a user group that performed the same task manually.

Practitioners spend significant amounts of time creating high-level design from requirements. Though there exist methodologies to describe and manage requirements and design artifacts, there is not yet an automated way to faithfully translate a requirement into a high-level design. While it is extremely difficult to generate design elements from free-form natural language due to its inherent ambiguity, it is possible to significantly improve the accuracy of the design from relatively structured and constrained natural language. In this paper we propose a technique to generate high-level class diagrams from a set of requirements, using a set of requirement-specific heuristics. In this approach, we leverage work we had previously done to first process a requirement statement to classify it into a requirement type, and then break it into various constituents. Depending on the requirement type and its constituents, our heuristics then discover a functional design comprising of coarse-grained modules, their relationships and responsibilities. We express the design as a UML class diagram in IBM rational software architect (RSA) format. Our preliminary investigation shows that the resulting class diagram is rich, and can be used by practitioners as a basis for further design.

Web application hybrids, popularly known as mashups, are created by integrating services on the Web using their APIs. Support for finding an API is currently provided by generic search engines or domain specific solutions such as Google and ProgrammableWeb. Shortcomings of both these solutions in terms of and reliance on user tags make the task of identifying an API challenging. Since these APIs are described in HTML documents, it is essential to look beyond the boundaries of current approaches to Web service discovery that rely on formal descriptions. In this work, we present a faceted approach to searching and ranking Web APIs that takes into consideration attributes or facets of the APIs as found in their HTML descriptions. Our method adopts current research in document classification and faceted search and introduces the serviut score to rank APIs based on their utilization and popularity. We evaluate classification, search accuracy and ranking effectiveness using available APIs while contrasting our solution with existing ones.

We propose a semantic framework for automatically identifying events as a step towards developing an adaptive middleware for Service Oriented Architecture (SOA). Current related research focuses on adapting to events that violate certain non-functional objectives of the service requestor. Given the large of number of events that can happen during the execution of a service, identifying events that can impact the non-functional objectives of a service request is a key challenge. To address this problem we propose an approach that allows service requestors to create semantically rich service requirement descriptions, called semantic templates. We propose a formal model for expressing semantic templates and for measuring the relevance of an event to both the action being performed and the nonfunctional objectives. This model is extended to adjust the relevance of the events based on feedback from the underlying adaptation framework. We present an algorithm that utilizes multiple ontologies for identifying relevant events and present our evaluations that measure the efficiency of both the event identification and the subsequent adaptation scheme.

With the rising popularity of Web services, both academia and industry have invested considerably in Web service description standards, discovery, and composition techniques. The standards based approach utilized by Web services has supported interoperability at the syntax level. However, issues of structural and semantic heterogeneity between messages exchanged by Web services are far more complex and crucial to interoperability. It is for these reasons that we recognize the value that schema/data mappings bring to Web service descriptions. In this paper, we examine challenges to interoperability; classify the types of heterogeneities that can occur between interacting services and present a possible solution for data mediation using the mapping support provided by WSDL-S, the extensibility features of WSDL and the popular SOAP engine, Axis 2

We present methods for optimally adapting Web processes to exogenous events while preserving inter-service constraints that necessitate coordination. For example, in a supply chain process, orders placed by a manufacturer may get delayed in arriving. In response to this event, the manufacturer has the choice of either waiting out the delay or changing the supplier. Additionally, there may be compatibility constraints between the different orders, thereby introducing the problem of coordination between them if the manufacturer chooses to change the suppliers. We focus on formulating the decision making models of the managers, who must adapt to external events while satisfying the coordination constraints, using Markov decision processes. Our methods range from being centralized and globally optimal in their adaptation but not scalable, to decentralized that is suboptimal but scalable to multiple managers. We also develop a hybrid approach that improves on the performance of the decentralized approach with a minimal loss of optimality

(Under the direction of Amit P. Sheth) In a dynamic service oriented environment it is desirable for service consumers and providers to offer and obtain guarantees regarding their capabilities and requirements. WS-Agreement defines a language and protocol for establishing agreements between two parties. The agreements are complex and expressive to the extent that the manual matching of these agreements would be expensive both in time and resources. It is essential to develop a method for matching agreements automatically. This work presents the framework and implementation of an innovative tool for the matching providers and consumers based on WS-Agreements. The approach utilizes Semantic Web technologies to achieve rich and accurate matches. A key feature is the novel and flexible approach for achieving user personalized matches.

The growing popularity of service oriented computing based on Web services standards is creating a need for paradigms to represent and design business processes. Significant work has been done in the representation aspects with regards to WSBPEL. However, design and modeling of business processes is still an open issue. In this paper, we present a novel designer for business processes, which allows for intuitive modeling of Web processes, as well as using a template based approach for semi-automatically integrating partners either at design time or at deployment time. This work has been done as part of the METEOR-S project, which concentrates on adding semantics to the entire Web process lifecycle.

The advent of Web services has made automated workflow composition relevant to Web based applications. One technique, that has received some attention, for automatically composing workflows is AI-based classical planning. However, classical planning suffers from the paradox of first assuming deterministic behavior of Web services, then requiring the additional overhead of execution monitoring to recover from unexpected behavior of services. To address these concerns, we propose using Markov decision processes (MDPs), to model workflow composition. Our method models both, the inherent stochastic nature of Web services, and the dynamic nature of the environment. The resulting workflows are robust to nondeterministic behaviors of Web services and adaptive to a changing environment. Using an example scenario, we demonstrate our method and provide empirical results in its support.

The potential of a large scale growth of private and semi-private registries is creating the need for an infrastructure which can support discovery and publication over a group of autonomous registries. Recent versions of UDDI have made changes to accommodate interactions between distributed registries. In this paper, we discuss METEOR-S Web service Discovery Infrastructure, which provides an ontology-based infrastructure to access a group of registries that are divided based on business domains and grouped into federations. We also discuss how Web service discovery is carried out within a federation.

The World Wide Web is emerging not only as an infrastructure for data, but also for a broader variety of resources that are increasingly being made available as Web services. Relevant current standards like UDDI, WSDL, and SOAP are in their fledgling years and form the basis of making Web services a workable and broadly adopted technology. However, realizing the fuller scope of the promise of Web services and associated service oriented architecture will requite further technological advances in the areas of service interoperation, service discovery, service composition, and process orchestration. Semantics, especially as supported by the use of ontologies, and related Semantic Web technologies, are likely to provide better qualitative and scalable solutions to these requirements. Just as semantic annotation of data in the Semantic Web is the first critical step to better search, integration and analytics over heterogeneous data, semantic annotation of Web services is an equally critical first step to achieving the above promise. Our approach is to work with existing Web services technologies and combine them with ideas from the Semantic Web to create a better framework for Web service discovery and composition. In this paper we present MWSAF (METEOR-S Web Service Annotation Framework), a framework for semi-automatically marking up Web service descriptions with ontologies. We have developed algorithms to match and annotate WSDL files with relevant ontologies. We use domain ontologies to categorize Web services into domains. An empirical study of our approach is presented to help evaluate its performance.

The design and implementation of a computer vision system called DNAScan for the automated analysis of DNA hybridization images is presented. The hybridization of a DNA clone with a radioactively tagged probe manifests itself as a spot on the hybridization membrane. A recursive segmentation procedure is designed and implemented to extract spot-like features in the hybridization images in the presence of a highly inhomogeneous background. Positive hybridization signals (hits) are extracted from the spot-like features using grouping and decomposition algorithms based on computational geometry. A mathematical model for the positive hybridization patterns and a pattern classifier based on shape-based moments are proposed and implemented to distinguish between the clone-probe hybridization signals.