Search

This special issue features the selected works of authors who have presented papers at the 2022 iteration of the Joint Conference on Digital Libraries (JCDL) in Cologne, Germany. The motto of the conference was "Bridging Worlds" and was run as a fully hybrid event. Ten papers covering all aspects of Digital Libraries, namely Natural Language Processing, Information Retrieval, User Behavior, Scholarly Communication, Classification, Information Extraction are included in this issue. [ABSTRACT FROM AUTHOR]

Clinical abbreviation disambiguation is a crucial task in the biomedical domain, as the accurate identification of the intended meanings or expansions of abbreviations in clinical texts is vital for medical information retrieval and analysis. Existing approaches have shown promising results, but challenges such as limited instances and ambiguous interpretations persist. In this paper, we propose an approach to address these challenges and enhance the performance of clinical abbreviation disambiguation. Our objective is to leverage the power of Large Language Models (LLMs) and employ a Generative Model (GM) to augment the dataset with contextually relevant instances, enabling more accurate disambiguation across diverse clinical contexts. We integrate the contextual understanding of LLMs, represented by BlueBERT and Transformers, with data augmentation using a Generative Model, called Biomedical Generative Pre-trained Transformer (BIOGPT), that is pretrained on an extensive corpus of biomedical literature to capture the intricacies of medical terminology and context. By providing the BIOGPT with relevant medical terms and sense information, we generate diverse instances of clinical text that accurately represent the intended meanings of abbreviations. We evaluate our approach on the widely recognized CASI dataset, carefully partitioned into training, validation, and test sets. The incorporation of data augmentation with the GM improves the model's performance, particularly for senses with limited instances, effectively addressing dataset imbalance and challenges posed by similar concepts. The results demonstrate the efficacy of our proposed method, showcasing the significance of LLMs and generative techniques in clinical abbreviation disambiguation. Our model achieves a good accuracy on the test set, outperforming previous methods. [ABSTRACT FROM AUTHOR]

The recent development of deep learning-based natural language processing (NLP) methods has fostered many downstream applications in various fields. As one of the applications in the financial industry, fine-grained financial sentiment analysis (FSA) aims to understand the sentimental orientation, i.e., bullish or bearish, of financial texts by predicting the polarity score and has been widely applied in the financial industry stock-related opinion mining. Because of the lack of a large-scale labeled dataset and the domain-dependent nature, FSA is challenging. Previous works mainly focus on constructing and exploiting handcrafted lexicons that encode expert knowledge to enhance the semantic features in decision making, which yields improvements but are expensive to acquire. This paper proposes a lightweight regression model incorporating the statistical distribution of a term over the polarity range, say between − 1 and 1, to address the fine-grained FSA task. More concretely, we first count each word's appearance at different polarity intervals and produce a statistic-based representation for each text, which will be encoded as a corpus-level statistical feature vector by an autoencoder. Subsequently, the obtained feature vector will be integrated with the semantic feature vector in the regression model. Our experiments show such a model can produce significant improvements compared with the baseline models on two FSA subsets, i.e., news headlines and microblogs, without a computational overhead. Furthermore, we notice the signs that lexicon-based approaches have neglected can play an important role in FSA. [ABSTRACT FROM AUTHOR]

Scientific literature is currently the most important resource for scholars, and their citations have provided researchers with a powerful latent way to analyze scientific trends, influences and relationships of works and authors. This paper is focused on automatic citation analysis and summarization for the scientific literature of computational linguistics, which are also the shared tasks in the 2016 workshop of the 2nd Computational Linguistics Scientific Document Summarization at BIRNDL 2016 (The Joint Workshop on Bibliometric-enhanced Information Retrieval and Natural Language Processing for Digital Libraries). Each citation linkage between a citation and the spans of text in the reference paper is recognized according to their content similarities via various computational methods. Then the cited text span is classified to five pre-defined facets, i.e., Hypothesis, Implication, Aim, Results and Method, based on various features of lexicons and rules via Support Vector Machine and Voting Method. Finally, a summary of the reference paper from the cited text spans is generated within 250 words. hLDA (hierarchical Latent Dirichlet Allocation) topic model is adopted for content modeling, which provides knowledge about sentence clustering (subtopic) and word distributions (abstractiveness) for summarization. We combine hLDA knowledge with several other classical features using different weights and proportions to evaluate the sentences in the reference paper. Our systems have been ranked top one and top two according to the evaluation results published by BIRNDL 2016, which has verified the effectiveness of our methods. [ABSTRACT FROM AUTHOR]

In this paper, we present a system for summarization of scientific and structured documents that has three components: section mixture models are used for estimation of the weights of terms; a hypothesis test to select a subset of these terms; and a sentence extractor based on techniques for combinatorial optimization. The section mixture models approach is an adaptation of a bigram mixture model based on the main sections of a scientific document and a collection of citing sentences (citances) from papers that reference the document. The model was adapted from earlier work done on Biomedical documents used in the summarization task of the 2014 Text Analysis Conference (TAC 2014). The mixture model trained on the Biomedical data was used also on the data for the Computational Linguistics scientific summarization task of the Joint Workshop on Bibliometric-enhanced Information Retrieval and Natural Language Processing for Digital Libraries (CL-SciSumm 2016). This model gives rise to machine-generated summaries with ROUGE scores that are nearly as strong as those seen on the Biomedical data and was also the highest scoring submission to the task of generating a human summary. For sentence extraction, we use the OCCAMS algorithm (Davis et al., in: Vreeken, Ling, Zaki, Siebes, Yu, Goethals, Webb, Wu (eds) ICDM workshops, IEEE Computer Society, pp 454-463, 2012) which takes the sentences from the original document and the assignment of weights of the terms computed by the language models and outputs a set of minimally overlapping sentences whose combined term coverage is maximized. Finally, we explore the importance of an appropriate background model for the hypothesis test to select terms to achieve the best quality summaries. [ABSTRACT FROM AUTHOR]

Automatic text summarization is considered as an important task in various fields in natural language processing such as information retrieval. It is a process of automatically generating a text representation. Text summarization can be a solution to the problem of information overload. Hence, with the large amount of information available on the Internet, the presentation of a document by a summary helps to get the most relevant result of a search. We propose in this paper a new free Arabic structured corpus in the standard XML TREC format. ANT corpus v2.1 is collected using RSS feeds from different news sources. This corpus is useful for multiple text mining purposes such as generic text summarization, clustering or classification. We test this corpus for an unsupervised single-document extractive summarization using statistical and graph-based language-independent summarizers such as LexRank, TextRank, Luhn and LSA. We investigate the sensitivity of the summarization process to the stemming and stop words removal steps. We evaluate these summarizers performance by comparing the extracted texts fragments to the abstracts existing in ANT corpus v2.1 using ROUGE and BLEU metrics. Experimental results show that LexRank summarizer has achieved the best scores for the ROUGE metric using the stop words removal scenario. [ABSTRACT FROM AUTHOR]

Automatic themes-based classification of Quran verses is the process of classifying verses to predefined categorizes or themes. It is an essential task for all Muslims and people interested in studying the Quran. Quran themes-based classification could be used in many natural language processing (NLP) fields such as search engines, data mining, question–answering systems, and information retrieval applications. This paper presents an ensemble multi-label classification model that automatically identifies and classifies the Quran verses based on themes/topics. The model is composed of four phases: pre-processing, data vectorization, binary relevance classifier, and voting module. Firstly, the verses of the second chapter of the Quran (Al-Baqarah) are tokenized and normalized. Then, the topics of these verses are manually labeled based on "Mushaf Al-Tajweed" classification. Secondly, verses are converted into features' vectors using term frequency-inverse document frequency (TF-IDF) and word2vec techniques. Word2vec is used to consider the semantic meaning of Quranic words and to improve performance. Also, they are trained on a collected classic Arabic corpus of 200 million words. Then, the binary relevance multi-label classification technique is applied using three different classifiers: logistic regression, support vector machine, and random forest, which categorize verses into 393 topics/tags. Finally, the voting module is applied by picking the tags with the maximum prediction probability among the three classifiers. The results of the three classifiers and the ensemble model are compared against "Mushaf Al-Tajweed." The ensemble model outperforms the three classifiers. Its average hamming loss, recall, precision, and F1-Score are 0.224, 81%, 75%, and 77%, respectively. [ABSTRACT FROM AUTHOR]

Searching for all occurrences of a pattern in a text is a fundamental problem in computer science with applications in many other fields, like natural language processing, information retrieval and computational biology. Sampled string matching is an efficient approach recently introduced in order to overcome the prohibitive space requirements of an index construction, on the one hand, and drastically reduce searching time for the online solutions, on the other hand. In this paper we present a new algorithm for the sampled string matching problem, based on a characters distance sampling approach. The main idea is to sample the distances between consecutive occurrences of a given pivot character and then to search online the sampled data for any occurrence of the sampled pattern, before verifying the original text. From a theoretical point of view we prove that, under suitable conditions, our solution can achieve both linear worst-case time complexity and optimal average-time complexity. From a practical point of view it turns out that our solution shows a sub-linear behaviour in practice and speeds up online searching by a factor of up to 9, using limited additional space whose amount goes from 11 to 2.8% of the text size, with a gain up to 50% if compared with previous solutions. [ABSTRACT FROM AUTHOR]

Algeria's socio-linguistic situation is known as a complex phenomenon involving several historical, cultural and technological factors. However, there are three languages that are mainly spoken in Algeria (Arabic, Tamazight and French) and they can be mixed in the same sentence (code-switching). Moreover, there are several varieties of dialects that differ from one region to another and sometimes within the same region. This paper aims to provide a new multi-purpose parallel corpus (i.e., DZDC12 corpus), which will serve as a testbed for various natural language processing and information retrieval applications. In particular, it can be a useful tool to study Arabic–French code-switching phenomenon, Algerian Romanized Arabic (Arabizi), different Algerian sub-dialects, sentiment analysis, gender writing style, machine translation, abuse detection, etc. To the best of our knowledge, the proposed corpus is the first of its kind, where the texts are written in Latin script and crawled from Facebook. More specifically, this corpus is organised by gender, region and city, and is transliterated into Arabic script and translated into Modern Standard Arabic. In addition, it is annotated for emotion detection and abuse detection, and annotated at the word level. This article focuses in particular on Algeria's socio-linguistic situation and the effect of social media networks. Furthermore, the general guidelines for the design of DZDC12 corpus are described as well as the dialects clustering over the map. [ABSTRACT FROM AUTHOR]

Medical data in online groups and social media contain valuable information, which is provided by both healthcare professionals and patients. In fact, patients can talk freely and share their personal experiences. These resources are a valuable opportunity for health professionals who can access patients' opinions, as well as discussions between patients. Recently, the data processing of the health community and, how to extract knowledge is a significant technical challenge. There are many online group and forums that users can discuss on healthcare issues. Therefore, we can examine these text documents for discovering knowledge and evaluating patients' behavior based on their opinions and discussions. For example, there are many questions and answering groups on Twitter or Facebook. Given the importance of the research, in this paper, we present a semantic framework based on topic model (LDA) and Random forest(RF) to predict and retrieval latent topics of healthcare text-documents from an online forum. We extract our healthcare records (patient-questions) from patient.info website as a real dataset. Experiments on our dataset show that social media forums could help for detecting significant patient safety problems on healthcare issues. [ABSTRACT FROM AUTHOR]

In natural language processing and information retrieval tasks, the bag-of-words model is widely used to represent the semantics of texts. However, it is difficult for machines to sufficiently understand a bag of words as well as the corresponding text without explicit semantic explanation, thus hindering the power of the bag-of-words model in many scenarios. In this paper, we introduce the task of hierarchical conceptual labeling (HCL), which aims to generate a set of conceptual labels with a hierarchy to explicitly explain the semantics of a bag of words, where the candidate labels are selected from a large-scale knowledge base, i.e., Microsoft Concept Graph. To this end, we first propose a denoising algorithm to filter out the noise in a bag of words in advance. Then the hierarchical conceptual labels are generated for the clean bag of words based on a hierarchical clustering algorithm, i.e., Bayesian rose trees. We conduct extensive experiments and prove that (1) the proposed denoising algorithm can effectively delete the noise words from a bag of words, (2) the Bayesian rose trees based algorithm can generate hierarchical conceptual labels for a bag of words with a high accuracy. [ABSTRACT FROM AUTHOR]

In this paper we present a pipeline for the detection of spelling variants, i.e., different spellings that represent the same word, in non-standard texts. For example, in Middle Low German texts in and ihn (among others) are potential spellings of a single word, the personal pronoun 'him'. Spelling variation is usually addressed by normalization, in which non-standard variants are mapped to a corresponding standard variant, e.g. the Modern German word ihn in the case of in. However, the approach to spelling variant detection presented here does not need such a reference to a standard variant and can therefore be applied to data for which a standard variant is missing. The pipeline we present first generates spelling variants for a given word using rewrite rules and surface similarity. Afterwards, the generated types are filtered. We present a new filter that works on the token level, i.e., taking the context of a word into account. Through this mechanism ambiguities on the type level can be resolved. For instance, the Middle Low German word in can not only be the personal pronoun 'him', but also the preposition 'in', and each of these has different variants. The detected spelling variants can be used in two settings for Digital Humanities research: On the one hand, they can be used to facilitate searching in non-standard texts. On the other hand, they can be used to improve the performance of natural language processing tools on the data by reducing the number of unknown words. To evaluate the utility of the pipeline in both applications, we present two evaluation settings and evaluate the pipeline on Middle Low German texts. We were able to improve the F1 score compared with previous work from 0.39 to 0.52 for the search setting and from 0.23 to 0.30 when detecting spelling variants of unknown words. [ABSTRACT FROM AUTHOR]

This paper presents a comprehensive survey on knowledge retrieval of historical concepts using semantic web technologies. The scope of this discussion encompasses research material in the field of computing and humanities including but not limited to Cultural Heritage, Museum and Digital Library research. Semantic web techniques used to describe, store, search, query and retrieve historic concepts such as RDF, RDFs, OWL, and Ontologies are discussed along with other extensively researched methods from domains like Natural Language Processing and Computer Vision. The discussion elaborates on Ontological-enabled information retrieval and the concept of new knowledge discovery. This work presents a comprehensive set of problems identified in the field of information retrieval and their solutions through the semantic web along with an insight in the future directions and the open-ended questions in the domain of retrieval of historic concept. [ABSTRACT FROM AUTHOR]

Web genre detection is a task that can enhance information retrieval systems by providing rich descriptions of documents and enabling more specialized queries. Most of previous studies in this field adopt the closed-set scenario where a given palette comprises all available genre labels. However this is not a realistic setup since web genres are constantly enriched with new labels and existing web genres are evolving in time. Open-set classification, where some pages used in the evaluation phase do not belong to any of the known genres, is a more realistic setup for this task. In this case, all pages not belonging to known genres can be seen as noise. This paper focuses on systematic evaluation of open-set web genre identification when the noise is either structured or unstructured. Two open-set methods combined with alternative text representation schemes and similarity measures are tested based on two benchmark corpora. Moreover, we adopt the openness test for web genre identification that enables the observation of effectiveness for a varying number of known/unknown labels. [ABSTRACT FROM AUTHOR]

Background: This study seeks to develop, test and assess a methodology for automatic extraction of a complete set of 'term-like phrases' and to create a terminology spectrum from a collection of natural language PDF documents in the field of chemistry. The definition of 'term-like phrases' is one or more consecutive words and/or alphanumeric string combinations with unchanged spelling which convey specific scientific meanings. A terminology spectrum for a natural language document is an indexed list of tagged entities including: recognized general scientific concepts, terms linked to existing thesauri, names of chemical substances/reactions and term-like phrases. The retrieval routine is based on n-gram textual analysis with a sequential execution of various 'accept and reject' rules with taking into account the morphological and structural information. Results: The assessment of the retrieval process, expressed quantitatively with a precision (P), recall (R) and F-measure, which are calculated manually from a limited set of documents (the full set of text abstracts belonging to 5 EuropaCat events were processed) by professional chemical scientists, has proved the effectiveness of the developed approach. The term-like phrase parsing efficiency is quantified with precision (P = 0.53), recall (R = 0.71) and F-measure (F = 0.61) values. Conclusion: The paper suggests using such terminology spectra to perform various types of textual analysis across document collections. This sort of the terminology spectrum may be successfully employed for text information retrieval, for reference database development, to analyze research trends in subject fields of research and to look for the similarity between documents.[Figure not available: see fulltext.] [ABSTRACT FROM AUTHOR]