Search results

The field of natural language processing (NLP) demonstrates rapid changes in the design of information retrieval systems and human‐computer interaction. While natural language is being looked on as the most effective tool for information retrieval in a contemporary information environment, the systems using it are only beginning to emerge. This study attempts to evaluate the current state of NLP IR systems from the user’s point of view: what techniques are used by these systems to guide their users through the search process? The analysis focused on the structure and components of the systems’ help mechanisms. Results of the study demonstrated that systems which claimed to be using natural language searching in fact used a wide range of information retrieval techniques from real natural language processing to Boolean searching. As a result, the user assistance mechanisms of these systems also varied. While pseudo‐NLP systems would suit a more traditional method of instruction, real NLP systems primarily utilised the methods of explanation and user‐system “dialogue”.

There is a huge amount of information and data stored in publicly available online databases that consist of large text files accessed by Boolean search techniques. It is widely held that less use is made of these databases than could or should be the case, and that one reason for this is that potential users find it difficult to identify which databases to search, to use the various command languages of the hosts and to construct the Boolean search statements required. This reasoning has stimulated a considerable amount of exploration and development work on the construction of search interfaces, to aid the inexperienced user to gain effective access to these databases. The aim of our paper is to review aspects of the design of such interfaces: to indicate the requirements that must be met if maximum aid is to be offered to the inexperienced searcher; to spell out the knowledge that must be incorporated in an interface if such aid is to be given; to describe some of the solutions that have been implemented in experimental and operational interfaces; and to discuss some of the problems encountered. The paper closes with an extensive bibliography of references relevant to online search aids, going well beyond the items explicitly mentioned in the text. An index to software appears after the bibliography at the end of the paper.

Experimental evidence suggests that enhancing the subject content of OPAC records can improve retrieval performance. This is based on the use of natural language index terms derived from the table of contents and back‐of‐the‐book index of documents. The research reported here investigates the alternative approach of translating these natural language terms into controlled vocabulary. Subject queries were collected by interview at the catalogue, and indexing of the queries demonstrated the impressive ability of PRECIS, and to a lesser extent LCSH, to represent users' information needs. DDC performed poorly in this respect. The assumption was made that an index language adequately specific to represent users' queries should be adequate to represent document contents. Searches were carried out on three test databases, and both natural language and PRECIS enhancement of MARC records increased the number of relevant documents found, with PRECIS showing the better performance. However, with weak stemming the advantage of PRECIS was lost. Consideration must also be given to the potential advantages of controlled vocabulary, over and above basic retrieval performance measures.

Some research has indicated that interacting with a computer through a natural language is not easier, more effective, or even preferred by new users of a system, when compared with menu and command interfaces. However, command‐driven searches would be facilitated, as users move from system to system, if there existed a common command language. Proposed standards for a “Common Command Language for Online, Interactive Information Retrieval” have been developed by NISO Committee G, and are now being reviewed for adoption.

Text mining, natural language processing, and natural language understanding continually help businesses and organizations extract valuable insights from unstructured data. As the business environment changes, companies must integrate data from many sources to remain competitive. Text is yet another rich data source collected by an organization both internally from employees and externally from customers. The chapter begins by distinguishing and defining text mining, natural language processing, and natural language understanding. Then two case studies are presented to understand how these technologies are applied in practice, namely on human resources and customer service applications of natural language. The chapter closes with defining steps to mitigate project risk as well as exploring the many industries employing this emerging technology.

A review is made of research in the design and use of languages for computer programming, with emphasis on one of its specialized applications, information retrieval, and on the end‐user directly interacting with the computer. It is shown that we lack the criteria for determining what is the best fit of a language to a particular user, although some research has suggested that there is a means by which this can be done, offering the users a wide range of language choice and using the computer as a means of helping him learn and adapt to the language.

The rapid rise of large language models (LLMs) has propelled them to the forefront of applications in natural language processing (NLP). This paper aims to present a comprehensive examination of the research landscape in LLMs, providing an overview of the prevailing themes and topics within this dynamic domain.

Drawing from an extensive corpus of 198 records published between 1996 to 2023 from the relevant academic database encompassing journal articles, books, book chapters, conference papers and selected working papers, this study delves deep into the multifaceted world of LLM research. In this study, the authors employed the BERTopic algorithm, a recent advancement in topic modeling, to conduct a comprehensive analysis of the data after it had been meticulously cleaned and preprocessed. BERTopic leverages the power of transformer-based language models like bidirectional encoder representations from transformers (BERT) to generate more meaningful and coherent topics. This approach facilitates the identification of hidden patterns within the data, enabling authors to uncover valuable insights that might otherwise have remained obscure. The analysis revealed four distinct clusters of topics in LLM research: “language and NLP”, “education and teaching”, “clinical and medical applications” and “speech and recognition techniques”. Each cluster embodies a unique aspect of LLM application and showcases the breadth of possibilities that LLM technology has to offer. In addition to presenting the research findings, this paper identifies key challenges and opportunities in the realm of LLMs. It underscores the necessity for further investigation in specific areas, including the paramount importance of addressing potential biases, transparency and explainability, data privacy and security, and responsible deployment of LLM technology.

The analysis revealed four distinct clusters of topics in LLM research: “language and NLP”, “education and teaching”, “clinical and medical applications” and “speech and recognition techniques”. Each cluster embodies a unique aspect of LLM application and showcases the breadth of possibilities that LLM technology has to offer. In addition to presenting the research findings, this paper identifies key challenges and opportunities in the realm of LLMs. It underscores the necessity for further investigation in specific areas, including the paramount importance of addressing potential biases, transparency and explainability, data privacy and security, and responsible deployment of LLM technology.

This classification offers practical guidance for researchers, developers, educators, and policymakers to focus efforts and resources. The study underscores the importance of addressing challenges in LLMs, including potential biases, transparency, data privacy, and responsible deployment. Policymakers can utilize this information to shape regulations, while developers can tailor technology development based on the diverse applications identified. The findings also emphasize the need for interdisciplinary collaboration and highlight ethical considerations, providing a roadmap for navigating the complex landscape of LLM research and applications.

This study stands out as the first to examine the evolution of LLMs across such a long time frame and across such diversified disciplines. It provides a unique perspective on the key areas of LLM research, highlighting the breadth and depth of LLM’s evolution.

In a university/district collaboration, three college professors and authors of this chapter co-taught with four teachers over a period of seven years. This study explores the perceived changes in thought and practice of both groups as a result of providing three-week summer school programs for fifth and eighth grade emergent bilinguals. This research is grounded in qualitative methodologies of self-study and case study. We present our joint story as a self-study. Data were collected in the form of lesson plan notes, yearly journals, personal notes, audiotapes of meetings, and in-depth interviews/discussions of those involved in the bounded context. Resulting themes were situated meaning, hybrid language, and a 5R Instructional Model. A case study design is used to present the data from the four in-service teachers. Data were collected from field notes and interviews. Several themes emerged from the teacher data, all of which are components of situated meaning: professional development as side-by-side teaching and learning, recognition of and interest in curriculum integration, and change in classroom practice. Findings indicate that the summer program was a meaningful avenue for professional development (PD) for both groups. However, within group similarities were stronger than across group. The experience changed the way we teach and how we develop PD for teachers. The implications for professors and K-12 teachers are discussed and suggestions for further study and PD are given.