共查询到20条相似文献，搜索用时 46 毫秒
1.
《Information processing & management》2022,59(1):102756
An idiom is a common phrase that means something other than its literal meaning. Detecting idioms automatically is a serious challenge in natural language processing (NLP) domain applications like information retrieval (IR), machine translation and chatbot. Automatic detection of Idioms plays an important role in all these applications. A fundamental NLP task is text classification, which categorizes text into structured categories known as text labeling or categorization. This paper deals with idiom identification as a text classification task. Pre-trained deep learning models have been used for several text classification tasks; though models like BERT and RoBERTa have not been exclusively used for idiom and literal classification. We propose a predictive ensemble model to classify idioms and literals using BERT and RoBERTa, fine-tuned with the TroFi dataset. The model is tested with a newly created in house dataset of idioms and literal expressions, numbering 1470 in all, and annotated by domain experts. Our model outperforms the baseline models in terms of the metrics considered, such as F-score and accuracy, with a 2% improvement in accuracy. 相似文献
2.
《Information processing & management》2019,56(4):1260-1279
This paper presents a robust and comprehensive graph-based rank aggregation approach, used to combine results of isolated ranker models in retrieval tasks. The method follows an unsupervised scheme, which is independent of how the isolated ranks are formulated. Our approach is able to combine arbitrary models, defined in terms of different ranking criteria, such as those based on textual, image or hybrid content representations.We reformulate the ad-hoc retrieval problem as a document retrieval based on fusion graphs, which we propose as a new unified representation model capable of merging multiple ranks and expressing inter-relationships of retrieval results automatically. By doing so, we claim that the retrieval system can benefit from learning the manifold structure of datasets, thus leading to more effective results. Another contribution is that our graph-based aggregation formulation, unlike existing approaches, allows for encapsulating contextual information encoded from multiple ranks, which can be directly used for ranking, without further computations and post-processing steps over the graphs. Based on the graphs, a novel similarity retrieval score is formulated using an efficient computation of minimum common subgraphs. Finally, another benefit over existing approaches is the absence of hyperparameters.A comprehensive experimental evaluation was conducted considering diverse well-known public datasets, composed of textual, image, and multimodal documents. Performed experiments demonstrate that our method reaches top performance, yielding better effectiveness scores than state-of-the-art baseline methods and promoting large gains over the rankers being fused, thus demonstrating the successful capability of the proposal in representing queries based on a unified graph-based model of rank fusions. 相似文献
3.
《Information processing & management》2023,60(2):103200
Performance of text classification models tends to drop over time due to changes in data, which limits the lifetime of a pretrained model. Therefore an ability to predict a model’s ability to persist over time can help design models that can be effectively used over a longer period of time. In this paper, we provide a thorough discussion into the problem, establish an evaluation setup for the task. We look at this problem from a practical perspective by assessing the ability of a wide range of language models and classification algorithms to persist over time, as well as how dataset characteristics can help predict the temporal stability of different models. We perform longitudinal classification experiments on three datasets spanning between 6 and 19 years, and involving diverse tasks and types of data. By splitting the longitudinal datasets into years, we perform a comprehensive set of experiments by training and testing across data that are different numbers of years apart from each other, both in the past and in the future. This enables a gradual investigation into the impact of the temporal gap between training and test sets on the classification performance, as well as measuring the extent of the persistence over time. Through experimenting with a range of language models and algorithms, we observe a consistent trend of performance drop over time, which however differs significantly across datasets; indeed, datasets whose domain is more closed and language is more stable, such as with book reviews, exhibit a less pronounced performance drop than open-domain social media datasets where language varies significantly more. We find that one can estimate how a model will retain its performance over time based on (i) how well the model performs over a restricted time period and its extrapolation to a longer time period, and (ii) the linguistic characteristics of the dataset, such as the familiarity score between subsets from different years. Findings from these experiments have important implications for the design of text classification models with the aim of preserving performance over time. 相似文献
4.
Zara Nasar Syed Waqar Jaffry Muhammad Kamran Malik 《Information processing & management》2019,56(6):102088
With the advent of Web 2.0, there exist many online platforms that results in massive textual data production such as social networks, online blogs, magazines etc. This textual data carries information that can be used for betterment of humanity. Hence, there is a dire need to extract potential information out of it. This study aims to present an overview of approaches that can be applied to extract and later present these valuable information nuggets residing within text in brief, clear and concise way. In this regard, two major tasks of automatic keyword extraction and text summarization are being reviewed. To compile the literature, scientific articles were collected using major digital computing research repositories. In the light of acquired literature, survey study covers early approaches up to all the way till recent advancements using machine learning solutions. Survey findings conclude that annotated benchmark datasets for various textual data-generators such as twitter and social forms are not available. This scarcity of dataset has resulted into relatively less progress in many domains. Also, applications of deep learning techniques for the task of automatic keyword extraction are relatively unaddressed. Hence, impact of various deep architectures stands as an open research direction. For text summarization task, deep learning techniques are applied after advent of word vectors, and are currently governing state-of-the-art for abstractive summarization. Currently, one of the major challenges in these tasks is semantic aware evaluation of generated results. 相似文献
5.
《Information processing & management》2022,59(2):102788
Passage ranking has attracted considerable attention due to its importance in information retrieval (IR) and question answering (QA). Prior works have shown that pre-trained language models (e.g. BERT) can improve ranking performance. However, these simple BERT-based methods tend to focus on passage terms that exactly match the question, which makes them easily fooled by the overlapping but irrelevant (distracting) passages. To solve this problem, we propose a self-matching attention-pooling mechanism (SMAP) to highlight the Essential Terms in the question-passage pairs. Further, we propose a hybrid passage ranking architecture, called BERT-SMAP, which combines SMAP with BERT to more effectively identify distracting passages and downplay their influence. BERT-SMAP uses the representations obtained through SMAP to enhance BERT’s classification mechanism as an interaction-focused neural ranker, and as the inputs of a matching function. Experimental results on three evaluation datasets show that our model outperforms the previous best BERT-based approaches, and is comparable to the state-of-the-art method that utilizes a much stronger pre-trained language model. 相似文献
6.
This paper studies how to learn accurate ranking functions from noisy training data for information retrieval. Most previous work on learning to rank assumes that the relevance labels in the training data are reliable. In reality, however, the labels usually contain noise due to the difficulties of relevance judgments and several other reasons. To tackle the problem, in this paper we propose a novel approach to learning to rank, based on a probabilistic graphical model. Considering that the observed label might be noisy, we introduce a new variable to indicate the true label of each instance. We then use a graphical model to capture the joint distribution of the true labels and observed labels given features of documents. The graphical model distinguishes the true labels from observed labels, and is specially designed for ranking in information retrieval. Therefore, it helps to learn a more accurate model from noisy training data. Experiments on a real dataset for web search show that the proposed approach can significantly outperform previous approaches. 相似文献
7.
《Information processing & management》2020,57(5):102219
GPS-enabled devices and social media popularity have created an unprecedented opportunity for researchers to collect, explore, and analyze text data with fine-grained spatial and temporal metadata. In this sense, text, time and space are different domains with their own representation scales and methods. This poses a challenge on how to detect relevant patterns that may only arise from the combination of text with spatio-temporal elements. In particular, spatio-temporal textual data representation has relied on feature embedding techniques. This can limit a model’s expressiveness for representing certain patterns extracted from the sequence structure of textual data. To deal with the aforementioned problems, we propose an Acceptor recurrent neural network model that jointly models spatio-temporal textual data. Our goal is to focus on representing the mutual influence and relationships that can exist between written language and the time-and-place where it was produced. We represent space, time, and text as tuples, and use pairs of elements to predict a third one. This results in three predictive tasks that are trained simultaneously. We conduct experiments on two social media datasets and on a crime dataset; we use Mean Reciprocal Rank as evaluation metric. Our experiments show that our model outperforms state-of-the-art methods ranging from a 5.5% to a 24.7% improvement for location and time prediction. 相似文献
8.
《Information processing & management》2023,60(4):103336
The literature has not fully and adequately explained why contextual (e.g., BERT-based) representations are so successful to improve the effectiveness of some Natural Language Processing tasks, especially Automatic Text Classifications (ATC). In this article, we evince that such representations, when properly tuned to a target domain, produce an extremely separable space that makes the classification task very effective, independently of the classifier employed for solving the ATC task. To demonstrate our hypothesis, we perform a thorough class separability analysis in order to visualize and measure how well BERT-based embeddings separate documents of different classes in comparison with other widely used representation approaches, e.g., TFIDF BoW, static embeddings (e.g., fastText) and zero-shot (non-tuned) contextual embeddings. We also analyze separability in the context of transfer learning and compare BERT-based representations with those obtained from other transformers (e.g., RoBERTa, XLNET). Our experiments covering sixteen datasets in topic and sentiment classification, eight classification methods and three class separability metrics show that the fine-tuned BERT embeddings are highly separable in the corresponding space (e.g., they are 67% more separable than the static embeddings). As a consequence, they allow the simplest classifiers to achieve similar effectiveness as the most complex methods. We also find moderate to high correlations between separability and effectiveness in all experimented scenarios. Overall, our main finding is that more discriminative (i.e., separable) textual representations constitute a critical part of the ATC solutions that, given the current state-of-the-art in classification algorithms, are more prominent than the algorithmic (classifier) method for solving the task. 相似文献
9.
10.
《Information processing & management》2005,41(5):1051-1063
The text retrieval method using latent semantic indexing (LSI) technique with truncated singular value decomposition (SVD) has been intensively studied in recent years. The SVD reduces the noise contained in the original representation of the term–document matrix and improves the information retrieval accuracy. Recent studies indicate that SVD is mostly useful for small homogeneous data collections. For large inhomogeneous datasets, the performance of the SVD based text retrieval technique may deteriorate. We propose to partition a large inhomogeneous dataset into several smaller ones with clustered structure, on which we apply the truncated SVD. Our experimental results show that the clustered SVD strategies may enhance the retrieval accuracy and reduce the computing and storage costs. 相似文献
11.
《Information processing & management》2020,57(1):102121
Text classification or categorization is the process of automatically tagging a textual document with most relevant labels or categories. When the number of labels is restricted to one, the task becomes single-label text categorization. However, the multi-label version is challenging. For Arabic language, both tasks (especially the latter one) become more challenging in the absence of large and free Arabic rich and rational datasets. Therefore, we introduce new rich and unbiased datasets for both the single-label (SANAD) as well as the multi-label (NADiA) Arabic text categorization tasks. Both corpora are made freely available to the research community on Arabic computational linguistics. Further, we present an extensive comparison of several deep learning (DL) models for Arabic text categorization in order to evaluate the effectiveness of such models on SANAD and NADiA. A unique characteristic of our proposed work, when compared to existing ones, is that it does not require a pre-processing phase and fully based on deep learning models. Besides, we studied the impact of utilizing word2vec embedding models to improve the performance of the classification tasks. Our experimental results showed solid performance of all models on SANAD corpus with a minimum accuracy of 91.18%, achieved by convolutional-GRU, and top performance of 96.94%, achieved by attention-GRU. As for NADiA, attention-GRU achieved the highest overall accuracy of 88.68% for a maximum subsets of 10 categories on “Masrawy” dataset. 相似文献
12.
《Information processing & management》2016,52(5):873-884
OCR errors in text harm information retrieval performance. Much research has been reported on modelling and correction of Optical Character Recognition (OCR) errors. Most of the prior work employ language dependent resources or training texts in studying the nature of errors. However, not much research has been reported that focuses on improving retrieval performance from erroneous text in the absence of training data. We propose a novel approach for detecting OCR errors and improving retrieval performance from the erroneous corpus in a situation where training samples are not available to model errors. In this paper we propose a method that automatically identifies erroneous term variants in the noisy corpus, which are used for query expansion, in the absence of clean text. We employ an effective combination of contextual information and string matching techniques. Our proposed approach automatically identifies the erroneous variants of query terms and consequently leads to improvement in retrieval performance through query expansion. Our proposed approach does not use any training data or any language specific resources like thesaurus for identification of error variants. It also does not expend any knowledge about the language except that the word delimiter is blank space. We have tested our approach on erroneous Bangla (Bengali in English) and Hindi FIRE collections, and also on TREC Legal IIT CDIP and TREC 5 Confusion track English corpora. Our proposed approach has achieved statistically significant improvements over the state-of-the-art baselines on most of the datasets. 相似文献
13.
Text clustering is a well-known method for information retrieval and numerous methods for classifying words, documents or both together have been proposed. Frequently, textual data are encoded using vector models so the corpus is transformed in to a matrix of terms by documents; using this representation text clustering generates groups of similar objects on the basis of the presence/absence of the words in the documents. An alternative way to work on texts is to represent them as a network where nodes are entities connected by the presence and distribution of the words in the documents. In this work, after summarising the state of the art of text clustering we will present a new network approach to textual data. We undertake text co-clustering using methods developed for social network analysis. Several experimental results will be presented to demonstrate the validity of the approach and the advantages of this technique compared to existing methods. 相似文献
14.
《Information processing & management》2022,59(5):103011
Nowadays, stress has become a growing problem for society due to its high impact on individuals but also on health care systems and companies. In order to overcome this problem, early detection of stress is a key factor. Previous studies have shown the effectiveness of text analysis in the detection of sentiment, emotion, and mental illness. However, existing solutions for stress detection from text are focused on a specific corpus. There is still a lack of well-validated methods that provide good results in different datasets. We aim to advance state of the art by proposing a method to detect stress in textual data and evaluating it using multiple public English datasets. The proposed approach combines lexicon-based features with distributional representations to enhance classification performance. To help organize features for stress detection in text, we propose a lexicon-based feature framework that exploits affective, syntactic, social, and topic-related features. Also, three different word embedding techniques are studied for exploiting distributional representation. Our approach has been implemented with three machine learning models that have been evaluated in terms of performance through several experiments. This evaluation has been conducted using three public English datasets and provides a baseline for other researchers. The obtained results identify the combination of FastText embeddings with a selection of lexicon-based features as the best-performing model, achieving F-scores above 80%. 相似文献
15.
《Information processing & management》2023,60(3):103298
Effective learning schemes such as fine-tuning, zero-shot, and few-shot learning, have been widely used to obtain considerable performance with only a handful of annotated training data. In this paper, we presented a unified benchmark to facilitate the problem of zero-shot text classification in Turkish. For this purpose, we evaluated three methods, namely, Natural Language Inference, Next Sentence Prediction and our proposed model that is based on Masked Language Modeling and pre-trained word embeddings on nine Turkish datasets for three main categories: topic, sentiment, and emotion. We used pre-trained Turkish monolingual and multilingual transformer models which can be listed as BERT, ConvBERT, DistilBERT and mBERT. The results showed that ConvBERT with the NLI method yields the best results with 79% and outperforms previously used multilingual XLM-RoBERTa model by 19.6%. The study contributes to the literature using different and unattempted transformer models for Turkish and showing improvement of zero-shot text classification performance for monolingual models over multilingual models. 相似文献
16.
Authorship analysis of electronic texts assists digital forensics and anti-terror investigation. Author identification can be seen as a single-label multi-class text categorization problem. Very often, there are extremely few training texts at least for some of the candidate authors or there is a significant variation in the text-length among the available training texts of the candidate authors. Moreover, in this task usually there is no similarity between the distribution of training and test texts over the classes, that is, a basic assumption of inductive learning does not apply. In this paper, we present methods to handle imbalanced multi-class textual datasets. The main idea is to segment the training texts into text samples according to the size of the class, thus producing a fairer classification model. Hence, minority classes can be segmented into many short samples and majority classes into less and longer samples. We explore text sampling methods in order to construct a training set according to a desirable distribution over the classes. Essentially, by text sampling we provide new synthetic data that artificially increase the training size of a class. Based on two text corpora of two languages, namely, newswire stories in English and newspaper reportage in Arabic, we present a series of authorship identification experiments on various multi-class imbalanced cases that reveal the properties of the presented methods. 相似文献
17.
《Information processing & management》2019,56(2):274-290
In this paper we focus on the problem of question ranking in community question answering (cQA) forums in Arabic. We address the task with machine learning algorithms using advanced Arabic text representations. The latter are obtained by applying tree kernels to constituency parse trees combined with textual similarities, including word embeddings. Our two main contributions are: (i) an Arabic language processing pipeline based on UIMA—from segmentation to constituency parsing—built on top of Farasa, a state-of-the-art Arabic language processing toolkit; and (ii) the application of long short-term memory neural networks to identify the best text fragments in questions to be used in our tree-kernel-based ranker. Our thorough experimentation on a recently released cQA dataset shows that the Arabic linguistic processing provided by Farasa produces strong results and that neural networks combined with tree kernels further boost the performance in terms of both efficiency and accuracy. Our approach also enables an implicit comparison between different processing pipelines as our tests on Farasa and Stanford parsers demonstrate. 相似文献
18.
《Information processing & management》2019,56(6):102060
In this era, the proliferating role of social media in our lives has popularized the posting of the short text. The short texts contain limited context with unique characteristics which makes them difficult to handle. Every day billions of short texts are produced in the form of tags, keywords, tweets, phone messages, messenger conversations social network posts, etc. The analysis of these short texts is imperative in the field of text mining and content analysis. The extraction of precise topics from large-scale short text documents is a critical and challenging task. The conventional approaches fail to obtain word co-occurrence patterns in topics due to the sparsity problem in short texts, such as text over the web, social media like Twitter, and news headlines. Therefore, in this paper, the sparsity problem is ameliorated by presenting a novel fuzzy topic modeling (FTM) approach for short text through fuzzy perspective. In this research, the local and global term frequencies are computed through a bag-of-words (BOW) model. To remove the negative impact of high dimensionality on the global term weighting, the principal component analysis is adopted; thereafter the fuzzy c-means algorithm is employed to retrieve the semantically relevant topics from the documents. The experiments are conducted over the three real-world short text datasets: the snippets dataset is in the category of small dataset whereas the other two datasets, Twitter and questions, are the bigger datasets. Experimental results show that the proposed approach discovered the topics more precisely and performed better as compared to other state-of-the-art baseline topic models such as GLTM, CSTM, LTM, LDA, Mix-gram, BTM, SATM, and DREx+LDA. The performance of FTM is also demonstrated in classification, clustering, topic coherence and execution time. FTM classification accuracy is 0.95, 0.94, 0.91, 0.89 and 0.87 on snippets dataset with 50, 75, 100, 125 and 200 number of topics. The classification accuracy of FTM on questions dataset is 0.73, 0.74, 0.70, 0.68 and 0.78 with 50, 75, 100, 125 and 200 number of topics. The classification accuracies of FTM on snippets and questions datasets are higher than state-of-the-art baseline topic models. 相似文献
19.
Semi-supervised document retrieval 总被引：2，自引：0，他引：2
This paper proposes a new machine learning method for constructing ranking models in document retrieval. The method, which is referred to as SSRank, aims to use the advantages of both the traditional Information Retrieval (IR) methods and the supervised learning methods for IR proposed recently. The advantages include the use of limited amount of labeled data and rich model representation. To do so, the method adopts a semi-supervised learning framework in ranking model construction. Specifically, given a small number of labeled documents with respect to some queries, the method effectively labels the unlabeled documents for the queries. It then uses all the labeled data to train a machine learning model (in our case, Neural Network). In the data labeling, the method also makes use of a traditional IR model (in our case, BM25). A stopping criterion based on machine learning theory is given for the data labeling process. Experimental results on three benchmark datasets and one web search dataset indicate that SSRank consistently and almost always significantly outperforms the baseline methods (unsupervised and supervised learning methods), given the same amount of labeled data. This is because SSRank can effectively leverage the use of unlabeled data in learning. 相似文献
20.
《Information processing & management》2016,52(6):1122-1141
Research on collaborative information retrieval (CIR) has shown positive impacts of collaboration on retrieval effectiveness in the case of complex and/or exploratory tasks. The synergic effect of accomplishing something greater than the sum of its individual components is reached through the gathering of collaborators’ complementary skills. However, these approaches often lack the consideration that collaborators might refine their skills and actions throughout the search session, and that a flexible system mediation guided by collaborators’ behaviors should dynamically adapt to this situation in order to optimize search effectiveness. In this article, we propose a new unsupervised collaborative ranking algorithm which leverages collaborators’ actions for (1) mining their latent roles in order to extract their complementary search behaviors; and (2) ranking documents with respect to the latent role of collaborators. Experiments using two user studies with respectively 25 and 10 pairs of collaborators demonstrate the benefit of such an unsupervised method driven by collaborators’ behaviors throughout the search session. Also, a qualitative analysis of the identified latent role is proposed to explain an over-learning noticed in one of the datasets. 相似文献