Information Retrieval Tasks Research Articles

KEST: A graph-based keyphrase extraction technique for tweets summarization using Markov Decision Process

Multi-document summarization finds its application in many downstream information retrieval and natural language processing tasks. In the light of recent developments in social media data mining, Tweet summarization has emerged as a fundamental task of automatically detecting important keyphrases from a set of Tweets about current happenings. In the existing literature, the graph-based keyphrase extraction techniques are well-established unsupervised algorithms to capture summaries from dynamically evolving data. We argue that the traditional multi-tweet summarization technique may or may not capture user’s interest-specific keyphrases during tweet summarization. The nature of user-generated factual short-text is different from well-formed descriptive and perceptual long-text due to their repetitive nature. In this context, we introduce a simple yet effective interest-specific keyphrase extraction technique for tweet summarization as KEST: Key Extraction for Summarization of Tweets using Markov Decision Process (MDP). In this research work, we generate a path as evolving chain of highly interconnected words from sub-components in graph of words. We evaluate the effectiveness of our computationally, inexpensive, graph-based, abstractive keyphrase extraction approach over two datasets which we make publicly available.

Improving Biomedical Information Retrieval with Neural Retrievers

Information retrieval (IR) is essential in search engines and dialogue systems as well as natural language processing tasks such as open-domain question answering. IR serve an important function in the biomedical domain, where content and sources of scientific knowledge may evolve rapidly. Although neural retrievers have surpassed traditional IR approaches such as TF-IDF and BM25 in standard open-domain question answering tasks, they are still found lacking in the biomedical domain. In this paper, we seek to improve information retrieval (IR) using neural retrievers (NR) in the biomedical domain, and achieve this goal using a three-pronged approach. First, to tackle the relative lack of data in the biomedical domain, we propose a template-based question generation method that can be leveraged to train neural retriever models. Second, we develop two novel pre-training tasks that are closely aligned to the downstream task of information retrieval. Third, we introduce the ``Poly-DPR'' model which encodes each context into multiple context vectors. Extensive experiments and analysis on the BioASQ challenge suggest that our proposed method leads to large gains over existing neural approaches and beats BM25 in the small-corpus setting. We show that BM25 and our method can complement each other, and a simple hybrid model leads to further gains in the large corpus setting.

Listwise Learning to Rank Based on Approximate Rank Indicators

We study here a way to approximate information retrieval metrics through a softmax-based approximation of the rank indicator function. Indeed, this latter function is a key component in the design of information retrieval metrics, as well as in the design of the ranking and sorting functions. Obtaining a good approximation for it thus opens the door to differentiable approximations of many evaluation measures that can in turn be used in neural end-to-end approaches. We first prove theoretically that the approximations proposed are of good quality, prior to validate them experimentally on both learning to rank and text-based information retrieval tasks.

IdenMD-NRF: a ranking framework for miRNA-disease association identification.

Identifying miRNA-disease associations is an important task for revealing pathogenic mechanism of complicated diseases. Different computational methods have been proposed. Although these methods obtained encouraging performance for detecting missing associations between known miRNAs and diseases, how to accurately predict associated diseases for new miRNAs is still a difficult task. In this regard, a ranking framework named idenMD-NRF is proposed for miRNA-disease association identification. idenMD-NRF treats the miRNA-disease association identification as an information retrieval task. Given a novel query miRNA, idenMD-NRF employs Learning to Rank algorithm to rank associated diseases based on high-level association features and various predictors. The experimental results on two independent test datasets indicate that idenMD-NRF is superior to other compared predictors. A user-friendly web server of idenMD-NRF predictor is freely available at http://bliulab.net/idenMD-NRF/.

Informative Causality Extraction from Medical Literature via Dependency-Tree-Based Patterns.

Extracting cause-effect entities from medical literature is an important task in medical information retrieval. A solution for solving this task can be used for compilation of various causality relations, such as causality between disease and symptoms, between medications and side effects, and between genes and diseases. Existing solutions for extracting cause-effect entities work well for sentences where the cause and the effect phrases are name entities, single-word nouns, or noun phrases consisting of two to three words. Unfortunately, in medical literature, cause and effect phrases in a sentence are not simply nouns or noun phrases, rather they are complex phrases consisting of several words, and existing methods fail to correctly extract the cause and effect entities in such sentences. Partial extraction of cause and effect entities conveys poor quality, non-informative, and often, contradictory facts, comparing to the one intended in the given sentence. In this work, we solve this problem by designing an unsupervised method for cause and effect phrase extraction, PatternCausality, which is specifically suitable for the medical literature. Our proposed approach first uses a collection of cause-effect dependency patterns as template to extract head words of cause and effect phrases and then it uses a novel phrase extraction method to obtain complete and meaningful cause and effect phrases from a sentence. Experiments on a cause-effect dataset built from sentences from PubMed articles show that for extracting cause and effect entities, PatternCausality is substantially better than the existing methods—with an order of magnitude improvement in the F-score metric over the best of the existing methods. We also build different variants of PatternCausality, which use different phrase extraction methods; all variants are better than the existing methods. PatternCausality and its variants also show modest performance improvement over the existing methods for extracting cause and effect entities in a domain-neutral benchmark dataset, in which cause and effect entities are nouns or noun phrases consisting of one to two words.

ILncDA-LTR: Identification of lncRNA-disease associations by learning to rank

Identifying the associations between lncRNAs and diseases is helpful for the treatment and diagnosis of complex diseases. The existing computational methods mainly focus on the identification of associations between known lncRNAs and known diseases. However, with the application of high-throughput sequencing in lncRNA research, more and more lncRNAs have been detected. Predicting diseases related with newly detected lncRNAs has not been fully explored. Therefore, there is an urgent need for developing powerful computational methods to predict diseases related with newly detected lncRNAs. In this paper, we propose a Learning to Rank (LTR)-based method called iLncDA-LTR to predict diseases related with newly detected lncRNAs. iLncDA-LTR treats this task as an information retrieval task. The newly detected lncRNAs and diseases are considered as queries and documents, respectively. For a given newly detected lncRNA (query), iLncDA-LTR integrates multiple relevant information into LTR for predicting candidate diseases associated with query lncRNA. Experimental results show that iLncDA-LTR outperforms the other exiting state-of-the-art predictors on independent dataset. The corresponding web server of iLncDA-LTR has been constructed as well (http://bliulab.net/iLncDA-LTR/).

Multi-Layer Contextual Passage Term Embedding for Ad-Hoc Retrieval

Nowadays, pre-trained language models such as Bidirectional Encoder Representations from Transformer (BERT) are becoming a basic building block in Information Retrieval tasks. Nevertheless, there are several limitations when applying BERT to the query-document matching task: (1) relevance assessments are applicable at the document-level, and the tokens of documents often exceed the maximum input length of BERT; (2) applying BERT to long documents leads to a great consumption of memory usage and run time, owing to the computational cost of the interactions between tokens. This paper explores a novel multi-layer contextual passage architecture that leverage text summarization extraction to generate passage-level evidence for the pre-selected document passage thus brought new possibilities for the long document relevance task. Experiments were conducted on two standard ad-hoc retrieval collections from the Text Retrieval Conference (TREC) 2004 Robust Track (Robust04) and ClueWeb09 with two different characteristics individually. Experimental results show that our approach can significantly outperform the strong baselines and even compared with the same BERT-based models, the precision of our methods as well as state-of-the-art neural ranking models.

Digital literacy and online political behavior

AbstractDigital literacy is receiving increased scholarly attention as a potential explanatory factor in the spread of misinformation and other online pathologies. As a concept, however, it remains surprisingly elusive, with little consensus on definitions or measures. We provide a digital literacy framework for political scientists and test survey items to measure it with an application to online information retrieval tasks. There exists substantial variation in levels of digital literacy in the population, which we show is correlated with age and could confound observed relationships. However, this is obscured by researchers’ reliance on online convenience samples that select for people with computer and internet skills. We discuss the implications of these measurement and sample selection considerations for effect heterogeneity in studies of online political behavior. We argue that there is no universally applicable formula for selecting a given non-probability sample or operationalization of the concept of digital literacy; instead, we conclude, researchers should make theoretically informed arguments about how they select both sample and measure.

Quantum Advantage in Information Retrieval

Random access codes have provided many examples of quantum advantage in communication, but concern only one kind of information retrieval task. We introduce a related task - the Torpedo Game - and show that it admits greater quantum advantage than the comparable random access code. Perfect quantum strategies involving prepare-and-measure protocols with experimentally accessible three-level systems emerge via analysis in terms of the discrete Wigner function. The example is leveraged to an operational advantage in a pacifist version of the strategy game Battleship. We pinpoint a characteristic of quantum systems that enables quantum advantage in any bounded-memory information retrieval task. While preparation contextuality has previously been linked to advantages in random access coding we focus here on a different characteristic called sequential contextuality. It is shown not only to be necessary and sufficient for quantum advantage, but also to quantify the degree of advantage. Our perfect qutrit strategy for the Torpedo Game entails the strongest type of inconsistency with non-contextual hidden variables, revealing logical paradoxes with respect to those assumptions.

MIDI2vec: Learning MIDI embeddings for reliable prediction of symbolic music metadata

An important problem in large symbolic music collections is the low availability of high-quality metadata, which is essential for various information retrieval tasks. Traditionally, systems have addressed this by relying either on costly human annotations or on rule-based systems at a limited scale. Recently, embedding strategies have been exploited for representing latent factors in graphs of connected nodes. In this work, we propose MIDI2vec, a new approach for representing MIDI files as vectors based on graph embedding techniques. Our strategy consists of representing the MIDI data as a graph, including the information about tempo, time signature, programs and notes. Next, we run and optimise node2vec for generating embeddings using random walks in the graph. We demonstrate that the resulting vectors can successfully be employed for predicting the musical genre and other metadata such as the composer, the instrument or the movement. In particular, we conduct experiments using those vectors as input to a Feed-Forward Neural Network and we report good comparable accuracy scores in the prediction with respect to other approaches relying purely on symbolic music, avoiding feature engineering and producing highly scalable and reusable models with low dimensionality. Our proposal has real-world applications in automated metadata tagging for symbolic music, for example in digital libraries for musicology, datasets for machine learning, and knowledge graph completion.

Machine Reading at Scale: A Search Engine for Scientific and Academic Research

The Internet, much like our universe, is ever-expanding. Information, in the most varied formats, is continuously added to the point of information overload. Consequently, the ability to navigate this ocean of data is crucial in our day-to-day lives, with familiar tools such as search engines carving a path through this unknown. In the research world, articles on a myriad of topics with distinct complexity levels are published daily, requiring specialized tools to facilitate the access and assessment of the information within. Recent endeavors in artificial intelligence, and in natural language processing in particular, can be seen as potential solutions for breaking information overload and provide enhanced search mechanisms by means of advanced algorithms. As the advent of transformer-based language models contributed to a more comprehensive analysis of both text-encoded intents and true document semantic meaning, there is simultaneously a need for additional computational resources. Information retrieval methods can act as low-complexity, yet reliable, filters to feed heavier algorithms, thus reducing computational requirements substantially. In this work, a new search engine is proposed, addressing machine reading at scale in the context of scientific and academic research. It combines state-of-the-art algorithms for information retrieval and reading comprehension tasks to extract meaningful answers from a corpus of scientific documents. The solution is then tested on two current and relevant topics, cybersecurity and energy, proving that the system is able to perform under distinct knowledge domains while achieving competent performance.

Library Wayfinding and ESOL Students: Communication Challenges and Empathy-Based Intervention

This article describes a wayfinding study conducted in an urban, academic library to better understand the experiences of multilingual student populations. The study, which incorporated traditional user experience methods and video ethnography, exposed communication obstacles and spatial challenges encountered by students of English for speakers of other languages (ESOL) when attempting information retrieval tasks. After outlining the methodology and examining qualitative findings, the authors discuss how study findings prompted a reevaluation of local practices, service models, and staff training protocols. Finally, the authors explore the potential for qualitative, empathy-based wayfinding studies to transform library practices and spaces.

The incentive contract of subject librarians in university library under the non-linear task importance

Abstract Under the information asymmetry, we consider the impact of task importance on the income of university managers, introducing the non-linear income function of university managers. Based on the principal-agent theory, we construct a non-linear incentive optimisation model for subject librarians. We discussed how university managers allocate incentive intensity and how the subject librarians allocate the effort level to achieve the best net expected income for university administrators and subject librarians while satisfying the constraints of participation and incentive compatibility. The results show that the optimal incentive contract for subject librarians is related to task importance, ability level, risk aversion characteristics and the randomness of the external environment in university libraries. The relative incentive intensity increases with the increase of task importance, risk aversion, ability level and randomness of information retrieval tasks, and decreases with the increase of randomness of subject service tasks.

Information retrieval from scientific abstract and citation databases: A query-by-documents approach based on Monte-Carlo sampling

The rapidly increasing amount of information and entries in abstract and citation databases steadily complicates the information retrieval task. In this study, a novel query-by-document approach using Monte-Carlo sampling of relevant keywords is presented. From a set of input documents (seed) keywords are extracted using TF-IDF and subsequently sampled to repeatedly construct queries to the database. The occurrence of returned documents is counted and serves as a proxy relevance metric. Two case studies based on the Scopus® database are used to demonstrate the method and its key advantages. No expert knowledge and human intervention is needed to construct the final search strings which reduces the human bias. The methods practicality is supported by the high re-retrieval of seed documents of 7/8 and 26/31 in high ranks in the two presented case studies.

Robust pattern for face recognition using combined Weber and pentagonal-triangle graph structure pattern

Face recognition is a challenging task in computer vision and information retrieval due to the large variation in facial images in terms of pose, expression and illumination. These challenges motivate us to propose a robust pattern for face recognition using combined Weber pattern (CWP) and pentagonal-triangle graph structure pattern (PTGSP). Firstly, abrupt intensity variations in facial images are removed by multiblock operation. Further, by exploring the relationship among center, neighboring and adjacent pixels, CWP consisting of three unique Weber patterns is computed. In order to obtain the pattern that is more robust to facial variations, PTGSP has been computed on the facial images. PTGSP covers the widely used features of face images. A feature set of high dimension is produced by combining the features of CWP and PTGSP. Dimensionality of the proposed feature and also variance within class is reduced through principal component analysis (PCA) plus linear discriminant analysis (LDA) algorithm. The classification performance of the proposed method is compared with various state-of-the-art methods on variety of benchmark face datasets with variation in pose, expression, illumination and occlusion. Experiments on FEI, Georgia, ORL, Yale and Faces94 databases clearly prove the robustness of the proposed method in contrast to existing handcrafted feature extraction techniques.

Scalable Representation Learning for Dynamic Heterogeneous Information Networks via Metagraphs

Content representation is a fundamental task in information retrieval. Representation learning is aimed at capturing features of an information object in a low-dimensional space. Most research on representation learning for heterogeneous information networks (HINs) focuses on static HINs. In practice, however, networks are dynamic and subject to constant change. In this article, we propose a novel and scalable representation learning model, M-DHIN , to explore the evolution of a dynamic HIN. We regard a dynamic HIN as a series of snapshots with different time stamps. We first use a static embedding method to learn the initial embeddings of a dynamic HIN at the first time stamp. We describe the features of the initial HIN via metagraphs, which retains more structural and semantic information than traditional path-oriented static models. We also adopt a complex embedding scheme to better distinguish between symmetric and asymmetric metagraphs. Unlike traditional models that process an entire network at each time stamp, we build a so-called change dataset that only includes nodes involved in a triadic closure or opening process, as well as newly added or deleted nodes. Then, we utilize the above metagraph-based mechanism to train on the change dataset. As a result of this setup, M-DHIN is scalable to large dynamic HINs since it only needs to model the entire HIN once while only the changed parts need to be processed over time. Existing dynamic embedding models only express the existing snapshots and cannot predict the future network structure. To equip M-DHIN with this ability, we introduce an LSTM-based deep autoencoder model that processes the evolution of the graph via an LSTM encoder and outputs the predicted graph. Finally, we evaluate the proposed model, M-DHIN , on real-life datasets and demonstrate that it significantly and consistently outperforms state-of-the-art models.

Influence of musical elements on the perception of ‘Chinese style’ in music

Recently Chinese music has been regarded as an independent music school. However, the definition of Chinese music has been an abstract and subjective concept. That makes music information retrieval (MIR) tasks hard to perform on Chinese music. Previous musicological studies have explained how musical elements like melody and instruments shape a certain kind of music genre including Chinese music, but the findings cannot be directly applied to relevant MIR tasks towards large-scale users and real-world problems. In this study, a pipeline of performing a perceptual survey is designed to explore how different musical elements influence people's perception of ‘Chinese style’ in music. Participants with various backgrounds were presented with categorised music excerpts performed in the Erhu or violin and then gave ‘Chinese style’ ratings. Statistical analysis indicates that music content contributes more than instruments. Results were compared between musicians and non-musicians. Subsequently, a supplementary automatic music classification experiment is conducted in comparison with the survey results to discuss the authors’ choice of stimuli in the survey and similarities between computer auditory and human perception. In general, the results in this study can be useful for MIR tasks, such as understanding, representation, and recommendation of Chinese music.

Overview and Discussion of the Competition on Legal Information Extraction/Entailment (COLIEE) 2021

We summarize the 8th Competition on Legal Information Extraction and Entailment. In this edition, the competition included five tasks on case law and statute law. The case law component includes an information retrieval Task (Task 1), and the confirmation of an entailment relation between an existing case and an unseen case (Task 2). The statute law component includes an information retrieval Task (Task 3), an entailment/question answering task based on retrieved civil code statutes (Task 4) and an entailment/question answering task without retrieved civil code statutes (Task 5). Participation was open to any group based on any approach. Eight different teams participated in the case law competition tasks, most of them in more than one task. We received results from six teams for Task 1 (16 runs) and 6 teams for Task 2 (17 runs). On the statute law task, there were eight different teams participating, most in more than one task. Six teams submitted a total of 18 runs for Task 3, 6 teams submitted a total of 18 runs for Task 4, and 4 teams submitted a total of 12 runs for Task 5. Here we summarize the approaches, our official evaluation, and analysis on our data and submission results.

SoundexGR: An algorithm for phonetic matching for the Greek language

AbstractText usually suffers from typos which can negatively affect various Information Retrieval and Natural Language Processing tasks. Although there is a wide variety of choices for tackling this issue in the English language, this is not the case for other languages. For the Greek language, most of the existing phonetic algorithms provide rather insufficient support. For this reason, in this paper, we introduce an algorithm for phonetic matching designed for the Greek language: we start from the original Soundex and we redesign and extend it for accommodating the Greek language’s phonetic rules, ending up to a family of algorithms, that we call ${\tt Soundex}_{GR}$ . Then, we report various experimental results showcasing how the algorithm behaves in different scenarios, and we provide comparative results for various parameters of the algorithm for revealing the trade-off between precision and recall in datasets with different kinds of errors. We also provide comparative results with matching using stemming, full phonemic transcription, and edit distance, that demonstrate that ${\tt Soundex}_{GR}$ performs better (indicatively, it achieves F-Score over 95% in collections of similar-sounded words). The simplicity, efficiency, and effectiveness of the proposed algorithm make it applicable and adaptable to a wide range of tasks.

Query Reformulation for Indonesian Question Answering System Using Word Embedding of Word2Vec

Query reformulation is one of the tasks in Information Retrieval (IR), which automatically creates new queries based on previous queries. The main challenge of query reformulation is to create a new query whose meaning or context is similar to the old query. Query reformulation can improve the search for relevant documents for Open-domain Question Answering (OpenQA). The more queries are given to the search system, and the more documents will be generated. We propose a Word Predicted and Substituted (WPS) method for query reformulation using a word embedding word2vec. We tested this method on the Indonesian Question Answering System (IQAS). The test results obtained an E-1 value of 81% and an E-2 value of 274%. These results prove that the query reformulation method with WPS and word-embedding can improve the search for potential IQAS answers.