Despite the recent remarkable advances in neural machine translation, translation quality for low-resource language pairs remains subpar. Ensembling multiple systems is a widely adopted technique to enhance performance, often accomplished by combining probability distributions. However, previous approaches face the challenge of high computational costs for training multiple models. Furthermore, for black-box models, averaging token-level probabilities at each decoding step is not feasible. To address the problems of multi-model ensemble methods, we present a pivot-based single model ensemble. The proposed strategy consists of two steps: pivot-based candidate generation and post-hoc aggregation. In the first step, we generate candidates through pivot translation. This can be achieved with only a single model and facilitates knowledge transfer from high-resource pivot languages, resulting in candidates that are not only diverse but also more accurate. Next, in the aggregation step, we select k high-quality candidates from the generated candidates and merge them to generate a final translation that outperforms the existing candidates. Our experimental results show that our method produces translations of superior quality by leveraging candidates from pivot translation to capture the subtle nuances of the source sentence.

In this study, we introduce a new dataset specifically designed for detecting messenger phishing, an increasingly significant issue in cybercrime. To overcome the scarcity of labeled phishing data, we employ large language models (LLMs) to generate synthetic data, thereby expanding the dataset and improving detection capabilities. Our experimental results show that a model trained exclusively on synthetic data performs comparably to those trained with labeled data. Furthermore, combining synthetic data with labeled data achieves superior F1 and accuracy scores compared to using labeled data only while reducing misclassification errors.

Cardinality estimation of LIKE predicate queries has an important role in the query optimization of database systems. Traditional approaches generally use a summary of text data with some statistical assumptions. Recently, the deep learning model for cardinality estimation of LIKE predicate queries has been investigated. To provide more accurate cardinality estimates and reduce the maximum estimation errors, we propose a deep learning model that utilizes the extended N-gram table and the conditional regression header. We next investigate how to efficiently generate training data. Our LEADER (LikE predicate trAining Data gEneRation) algorithms utilize the shareable results across the relational queries corresponding to the LIKE predicates. By analyzing the queries corresponding to LIKE predicates, we develop an efficient join method and utilize the join order for fast query execution and maximal sharing of shareable results. Extensive experiments with real-life datasets confirm the efficiency of the proposed training data generation algorithms and the effectiveness of the proposed model.

Recently, as messenger phishing has been occurring more frequently, the need for its detection has increased; however, datasets for messenger phishing detection are publicly unavailable. In this paper, we address the data scarcity problem of the newly collected messenger phishing dataset by leveraging various types of pre-existing auxiliary phishing data. Experimental results demonstrate that the error rate decreased by up to 1.81 % and the F1 score improved by 7.35% when smishing and voice phishing data are used. These findings confirm that integrating heterogeneous phishing data can mitigate the data scarcity problem and enhance messenger phishing detection performance.

Defect detection in photovoltaic (PV) modules is crucial for ensuring energy efficiency and long-term performance. Traditionally, electroluminescence (EL) images have been manually analyzed by workers, leading to inefficiencies and subjectivity in the inspection process. To address these issues, deep learning algorithms, such as convolutional neural networks (CNN), have been employed, but most of these approaches using only module-level labels restrict defect detection to the module level and lack precision in identifying defective cells. On the other hand, methods relying solely on cell-level labels can detect defects at the cell-level but they require extensive annotation, making them impractical for industrial applications. To overcome these limitations, we propose a novel two-stage learning method that combines module-level and cell-level labels for training. Our approach applies semi-supervised learning to improve defect detection performance at both the module and cell levels, with a limited number of cell-level labels. Experimental results on the same dataset demonstrate that our method outperforms traditional approaches relying on single-level labels, achieving superior performance.

In Machine Translation (MT) evaluations, the conventional approach is to compare a translated sentence against its human-created reference sentence. MT metrics provide an absolute score (e.g., from 0 to 1) to a candidate sentence based on the similarity with the reference sentence. Thus, existing MT metrics give the maximum score to the reference sentence. However, this approach overlooks the potential for a candidate sentence to exceed the reference sentence in terms of quality. In particular, recent advancements in Large Language Models (LLMs) have highlighted this issue, as LLM-generated sentences often exceed the quality of human-written sentences. To address the problem, we introduce the Residual score Metric (ResuMe), which evaluates the relative quality between reference and candidate sentences. ResuMe assigns a positive score to candidate sentences that outperform their reference sentences, and a negative score when they fall short. By adding the residual scores from ResuMe to the absolute scores from MT metrics, it can be possible to allocate higher scores to candidate sentences than what reference sentences are received from MT metrics. Experimental results demonstrate that ResuMe enhances the alignments between MT metrics and human judgments both at the segment-level and the system-level.

End-to-end automatic speech recognition (E2E ASR) systems have significantly improved speech recognition through training on extensive datasets. Despite these advancements, they still struggle to accurately recognize domain specific words, such as proper nouns and technical terminologies. To address this problem, we propose a method to utilize the state-of-the-art Whisper without modifying its architecture, preserving its generalization performance while enabling it to leverage descriptions effectively. Moreover, we propose two additional training techniques to improve the domain specific ASR: decoder fine-tuning, and context perturbation. We also propose a method to use a Large Language Model (LLM) to generate descriptions with simple metadata, when descriptions are unavailable. Our experiments demonstrate that proposed methods notably enhance domain-specific ASR accuracy on real-life datasets, with LLM-generated descriptions outperforming human-crafted ones in effectiveness.

Geospatial data provides a lot of benefits for personalized services. However, since the geospatial data contains sensitive information about personal activities, collecting the raw data has a potential risk of leaking private information from the collectors. Recently, local differential privacy (LDP), which protects the privacy of users without trusting the collector, has been adopted to preserve privacy in many real applications. In this paper, we investigate the problem of collecting the locations of individual users under LDP, and propose a perturbation mechanism designed carefully to minimize the expected error of perturbed locations according to the privacy budget and the data domain. The frequency distribution of perturbed locations inevitably has a large error. To tackle the problem, we also propose a postprocessing algorithm to estimate the original frequency distribution of collected data by using convex optimization. By experiments with various real datasets, we show the effectiveness of the proposed algorithms.

Despite the rapid growth in model architecture, the scarcity of large parallel corpora remains the main bottleneck in Neural Machine Translation. Data augmentation is a technique that enhances the performance of data-hungry models by generating synthetic data instead of collecting new ones. We explore prompt-based data augmentation approaches that leverage large-scale language models such as ChatGPT. To create a synthetic parallel corpus, we compare 3 methods using different prompts. We employ two assessment metrics to measure the diversity of the generated synthetic data. This approach requires no further model training cost, which is mandatory in other augmentation methods like back-translation. The proposed method improves the unaugmented baseline by 0.68 BLEU score.

Over the past few years, various domain-specific pretrained language models (PLMs) have been proposed and have outperformed general-domain PLMs in specialized areas such as biomedical, scientific, and clinical domains. In addition, financial PLMs have been studied because of the high economic impact of financial data analysis. However, we found that financial PLMs were not pretrained on sufficiently diverse financial data. This lack of diverse training data leads to a subpar generalization performance, resulting in general-purpose PLMs, including BERT, often outperforming financial PLMs on many downstream tasks. To address this issue, we collected a broad range of financial corpus and trained the Financial Language Model (FiLM) on these diverse datasets. Our experimental results confirm that FiLM outperforms not only existing financial PLMs but also general domain PLMs. Furthermore, we provide empirical evidence that this improvement can be achieved even for unseen corpus groups.

Strong and weak supervisions have complementary characteristics. However, utilizing both supervisions for named entity recognition (NER) has not been extensively studied. Moreover, the existing works address only incomplete annotations and neglects inaccurate annotations during NER model training. To effectively utilize weak labels, we introduce an auxiliary classifier that learns from weak labels. Furthermore, we adopt the teacher-student framework to handle both incomplete and inaccurate weak labels. A teacher model is first trained using both strongly and weakly supervised data, and next generates pseudo labels to replace weak labels. Then, the student model is trained so that the main classifier learns from both strong labels and confident pseudo labels while the auxiliary classifier learns from less confident pseudo labels. We also incorporate data augmentation through ChatGPT to generate additional annotated sentences to improve model performance and generalization capabilities. The experimental results with different weak supervisions demonstrate that our proposed method surpasses existing techniques.

Named Entity Recognition (NER) frequently suffers from the problem of insufficient labeled data, particularly in fine-grained NER scenarios. Although K-shot learning techniques can be applied, their performance tends to saturate when the number of annotations exceeds several tens of labels. To overcome this problem, we utilize existing coarse-grained datasets that offer a large number of annotations. A straightforward approach to address this problem is pre-finetuning, which employs coarse-grained data for representation learning. However, it cannot directly utilize the relationships between fine-grained and coarse-grained entities, although a fine-grained entity type is likely to be a subcategory of a coarse-grained entity type. We propose a fine-grained NER model with a Fine-to-Coarse(F2C) mapping matrix to leverage the hierarchical structure explicitly. In addition, we present an inconsistency filtering method to eliminate coarse-grained entities that are inconsistent with fine-grained entity types to avoid performance degradation. Our experimental results show that our method outperforms both K-shot learning and supervised learning methods when dealing with a small number of fine-grained annotations.

Cardinality estimation of an approximate substring query is an important problem in database systems. Traditional approaches build a summary from the text data and estimate the cardinality using the summary with some statistical assumptions. Since deep learning models can learn underlying complex data patterns effectively, they have been successfully applied and shown to outperform traditional methods for cardinality estimations of queries in database systems. However, since they are not yet applied to approximate substring queries, we investigate a deep learning approach for cardinality estimation of such queries. Although the accuracy of deep learning models tends to improve as the train data size increases, producing a large train data is computationally expensive for cardinality estimation of approximate substring queries. Thus, we develop efficient train data generation algorithms by avoiding unnecessary computations and sharing common computations. We also propose a deep learning model as well as a novel learning method to quickly obtain an accurate deep learning-based estimator. Extensive experiments confirm the superiority of our data generation algorithms and deep learning model with the novel learning method.

Geospatial data provides a lot of benefits for personalized services. However, since the geospatial data contains sensitive information about personal activities, collecting the raw data has a potential risk of leaking private information from the collectors. Recently, local differential privacy (LDP), which protects the privacy of users without trusting the collector, has been adopted to preserve privacy in many real applications. However, most of existing LDP algorithms focus on obtaining aggregated values such as mean and histogram from the collected data. In this paper, we investigate the problem of collecting the locations of individual users under LDP, and propose a perturbation mechanism designed carefully to reduce the error of each perturbed location according to the privacy budget and the domain size. In addition, we show the effectiveness of the proposed algorithm through experiments on various real datasets.

Log data from mobile devices generally contain a series of events with temporal information including time intervals which consist of the start and finish times. However, the problem of releasing differentially private time interval datasets has not been tackled yet. A time interval dataset can be represented by a two dimensional (2D) histogram. Most of the methods to publish 2D histograms partition the data into rectangular spaces to reduce the aggregated noise error for range queries. However, the existing algorithms to publish 2D histograms suffer from the structural error when applied to time interval datasets. To reduce the aggregated noise errors and suppress the increase in the structural error, we propose the TIDY (publishing Time Intervals via Differential privacY) algorithm. We use the frequency vectors as a compact representation of the time interval dataset. After applying the Laplace mechanism to the frequency vectors, we improve the utility of the frequency vectors based on a maximum likelihood estimation. We also develop a new partitioning method adapted for the frequency vectors to balance the trade-off between the noise and structural errors. Our empirical study on real-life and synthetic datasets confirms that TIDY outperforms the existing algorithms for 2D histograms.

Relation extraction (RE) has been extensively studied due to its importance in real-world applications such as knowledge base construction and question answering. Most of the existing works train the models on either distantly supervised data or human-annotated data. To take advantage of the high accuracy of human annotation and the cheap cost of distant supervision, we propose the dual supervision framework which effectively utilizes both types of data. However, simply combining the two types of data to train a RE model may decrease the prediction accuracy since distant supervision has labeling bias. We employ two separate prediction networks HA-Net and DS-Net to predict the labels by human annotation and distant supervision, respectively, to prevent the degradation of accuracy by the incorrect labeling of distant supervision. Furthermore, we propose an additional loss term called disagreement penalty to enable HA-Net to learn from distantly supervised labels. In addition, we exploit additional networks to adaptively assess the labeling bias by considering contextual information. Our performance study on sentence-level and document-level REs confirms the effectiveness of the dual supervision framework.

Document-level relation extraction (RE) has recently received a lot of attention. However, existing models for document-level RE have similar structures to the models for sentence-level RE. Thus, they still do not consider some unique characteristics of the new problem setting. For example, in Wikipedia, there is a title for each page and it usually represents the topic entity that is mainly described on the page. In many cases, the topic entity is omitted in the text. Thus, existing RE models often fail to find the relations with the omitted topic entity. To tackle the problem, we propose a Topic-aware Relation EXtraction (T-REX) model. To extract the relations with the (possibly omitted) topic entity, the proposed model first encodes the topic entity by aggregating the information of all its mentions in the document. Then it finds the relations between the topic entity and each mention of other entities. Finally, the output layer combines the mention-wise results and outputs all relations expressed in the document. Our performance study with a large-scale dataset confirms the effectiveness of the T-REX model.

시계열 데이터 분석에서 널리 이용되는 거리 측도 중 하나인 동적 시간 워핑(Dynamic Time Warping, DTW)은 시계열 데이터의 길이가 길어질수록 시간이 오래 걸리는 단점이 존재한다. 이를 극복하기 위해 최근에 런-길이 부호화라는 압축 방법을 이용하여 DTW를 빠른 시간 내에 근사하는 알고리즘들이 개발되었다. 하지만 기존의 방법들로 계산된 DTW의 상계값에는 불필요하게 더해지는 거리값이 존재한다. 본 논문은 시간복잡도를 유지하면서 런-길이 부호화를 통한 DTW 근사 알고리즘들을 개선하는 동적계획법(Dynamic programming) 기반의 알고리즘을 제시한다. 또한, 현실 세계의 데이터 및 인공 데이터를 활용한 실험을 통해 제안하는 방법의 효용성을 보인다.

Existing works for truth discovery in categorical data usually assume that claimed values are mutually exclusive and only one among them is correct. However, many claimed values are not mutually exclusive even for functional predicates due to their hierarchical structures. Thus, we need to consider the hierarchical structure to effectively estimate the trustworthiness of the sources and infer the truths. We propose a probabilistic model to utilize the hierarchical structures and an inference algorithm to find the truths. In addition, in the knowledge fusion, the step of automatically extracting information from unstructured data (e.g., text) generates a lot of false claims. To take advantages of the human cognitive abilities in understanding unstructured data, we utilize crowdsourcing to refine the result of the truth discovery. We propose a task assignment algorithm to maximize the accuracy of the inferred truths. The performance study with real-life datasets confirms the effectiveness of our truth inference and task assignment algorithms.