Data visualization in the form of charts plays a pivotal role in data analysis, offering critical insights and aiding in informed decision-making. Automatic chart understanding has witnessed significant advancements with the rise of large foundation models in recent years. Foundation models, such as large language models, have revolutionized various natural language processing tasks and are increasingly being applied to chart understanding tasks. This survey paper provides a comprehensive overview of the recent developments, challenges, and future directions in chart understanding within the context of these foundation models. We review fundamental building blocks crucial for studying chart understanding tasks. Additionally, we explore various tasks and their evaluation metrics and sources of both charts and textual inputs. Various modeling strategies are then examined, encompassing both classification-based and generation-based approaches, along with tool augmentation techniques that enhance chart understanding performance. Furthermore, we discuss the state-of-the-art performance of each task and discuss how we can improve the performance. Challenges and future directions are addressed, highlighting the importance of several topics, such as domain-specific charts, lack of efforts in developing evaluation metrics, and agent-oriented settings. This survey paper aims to provide valuable insights and directions for future research in chart understanding leveraging large foundation models.

Conversational Recommender Systems (CRS) has become an emerging research topic seeking to perform recommendations through interactive conversations, which generally consist of generation and recommendation modules. Prior work on CRS tends to incorporate more external and domain-specific knowledge like item reviews to enhance performance. Despite the fact that the collection and annotation of theexternal domain-specificinformation needs much human effort and degenerates the generalizability, too much extra knowledge introduces more difficulty to balance among them. Therefore, we propose to fully discover and extract theinternalknowledge from the context. We capture both entity-level and contextual-level representations to jointly model user preferences for the recommendation, where a time-aware attention is designed to emphasize the recently appeared items in entity-level representations. We further use the pre-trained BART to initialize the generation module to alleviate the data scarcity and enhance the context modeling. In addition to conducting experiments on a popular dataset (ReDial), we also include a multi-domain dataset (OpenDialKG) to show the effectiveness of our model. Experiments on both datasets show that our model achieves better performance on most evaluation metrics with less external knowledge and generalizes well to other domains. Additional analyses on the recommendation and generation tasks demonstrate the effectiveness of our model in different scenarios.

We present GradMask, a simple adversarial example detection scheme for natural language processing (NLP) models. It uses gradient signals to detect adversarially perturbed tokens in an input sequence and occludes such tokens by a masking process. GradMask provides several advantages over existing methods including improved detection performance and an interpretation of its decision with a only moderate computational cost. Its approximated inference cost is no more than a single forward- and back-propagation through the target model without requiring any additional detection module. Extensive evaluation on widely adopted NLP benchmark datasets demonstrates the efficiency and effectiveness of GradMask. Code and models are available at https://github.com/Han8931/grad_mask_detection

The database systems course in an undergraduate computer science degree program is gaining increasing importance due to the continuous supply of database-related jobs as well as the rise of Data Science. A key learning goal of learners taking such a course is to understand how SQL queries are executed in an RDBMS in practice. An RDBMS typically exposes a query execution plan (QEP) in a visual or textual format, which describes the execution steps for a given query. However, it is often daunting for a learner to comprehend these QEPs containing vendor-specific implementation details. In this demonstration, we present a novel, generic, and portable system called LANTERN that generates a natural language (NL)-based description of the execution strategy chosen by the underlying RDBMS to process a query. It provides a declarative framework called POOL for subject matter experts (SME) to efficiently create and manipulate the NL descriptions of physical operators of any RDBMS. It then exploits POOL to generate the NL descriptions of QEPs by integrating a rule-based and a deep learning-based techniques to infuse language variability in the descriptions. Such an NL generation strategy mitigates the impact of boredom on learners caused by repeated exposure of similar text generated by a rule-based system.

We study the task of span-level emotion cause analysis (SECA), which is focused on identifying the specific emotion cause span(s) triggering a certain emotion in the text. Compared to the popular clause-level emotion cause analysis (CECA), it is a finer-grained emotion cause analysis (ECA) task. In this paper, we design a BERT-based graph attention network for emotion cause span(s) identification. The proposed model takes advantage of the structure of BERT to capture the relationship information between emotion and text, and utilizes graph attention network to model the structure information of the text. Our SECA method can be easily used for extracting clause-level emotion causes for CECA as well. Experimental results show that the proposed method consistently outperforms the state-of-the-art ECA methods on benchmark emotion cause dataset.

This paper addresses the task of span-level emotion cause analysis (SECA). It is a finer-grained emotion cause analysis (ECA) task, which aims to identify the specific emotion cause span(s) behind certain emotions in text. In this paper, we formalize SECA as a sequence tagging task for which several variants of neural network-based sequence tagging models to extract specific emotion cause span(s) in the given context. These models combine different types of encoding and decoding approaches. Furthermore, to make our models more "emotionally sensitive'', we utilize the multi-head attention mechanism to enhance the representation of context. Experimental evaluations conducted on two benchmark datasets demonstrate the effectiveness of the proposed models.

The database systems course is offered as part of an undergraduate computer science degree program in many major universities. A key learning goal of learners taking such a course is to understand how sql queries are processed in a rdbms in practice. Since aquery execution plan (qep ) describes the execution steps of a query, learners can acquire the understanding by perusing the qep s generated by a rdbms. Unfortunately, in practice, it is often daunting for a learner to comprehend these qep s containing vendor-specific implementation details, hindering her learning process. In this paper, we present a novel, end-to-end,generic system called lantern that generates a natural language description of a qep to facilitate understanding of the query execution steps. It takes as input an sql query and its qep, and generates a natural language description of the execution strategy deployed by the underlying rdbms. Specifically, it deploys adeclarative framework called pool that enablessubject matter experts to efficiently create and maintain natural language descriptions of physical operators used in qep s. Arule-based framework called rule-lantern is proposed that exploits pool to generate natural language descriptions of qep s. Despite the high accuracy of rule-lantern, our engagement with learners reveal that, consistent with existing psychology theories, perusing such rule-based descriptions lead toboredom due to repetitive statements across different qep s. To address this issue, we present a noveldeep learning-based language generation framework called neural -lantern that infuses language variability in the generated description by exploiting a set ofparaphrasing tools andword embedding. Our experimental study with real learners shows the effectiveness of lantern in facilitating comprehension of qep s.

Rumor spread in social media severely jeopardizes the credibility of online content. Thus, automatic debunking of rumors is of great importance to keep social media a healthy environment. While facing a dubious claim, people often dispute its truthfulness sporadically in their posts containing various cues, which can form useful evidence with long-distance dependencies. In this work, we propose to learn discriminative features from microblog posts by following their non-sequential propagation structure and generate more powerful representations for identifying rumors. For modeling non-sequential structure, we first represent the diffusion of microblog posts with propagation trees, which provide valuable clues on how a claim in the original post is transmitted and developed over time. We then present a bottom-up and a top-down tree-structured models based on Recursive Neural Networks (RvNN) for rumor representation learning and classification, which naturally conform to the message propagation process in microblogs. To enhance the rumor representation learning, we reveal that effective rumor detection is highly related to finding evidential posts, e.g., the posts expressing specific attitude towards the veracity of a claim, as an extension of the previous RvNN-based detection models that treat every post equally. For this reason, we design discriminative attention mechanisms for the RvNN-based models to selectively attend on the subset of evidential posts during the bottom-up/top-down recursive composition. Experimental results on four datasets collected from real-world microblog platforms confirm that (1) our RvNN-based models achieve much better rumor detection and classification performance than state-of-the-art approaches; (2) the attention mechanisms for focusing on evidential posts can further improve the performance of our RvNN-based method; and (3) our approach possesses superior capacity on detecting rumors at a very early stage.

A core component of a database systems course at the undergraduate level is the design and implementation of the query optimizer in an rdbms. The query optimization process produces aquery execution plan (qep ), which represents an execution strategy for an sql query. Unfortunately, in practice, it is often difficult for a student to comprehend a query execution strategy by perusing its qep, hindering her learning process. In this demonstration, we present a novel system called neuron that facilitates natural language interaction with qep s to enhance its understanding. neuron accepts an sql query (which may include joins, aggregation, nesting, among other things) as input, executes it, and generates a simplified natural language description (both in text and voice form) of the execution strategy deployed by the underlying rdbms. Furthermore, it facilitates understanding of various features related to a qep through anatural language question answering (nlqa ) framework. We advocate that such tool, world's first of its kind, can greatly enhance students' learning of the query optimization topic.

Sleep plays a vital role in human health, both mental and physical. Sleep disorders like sleep apnea are increasing in prevalence, with the rapid increase in factors like obesity. Sleep apnea is most commonly treated with Continuous Positive Air Pressure (CPAP) therapy. Presently, however, there is no mechanism to monitor a patient's progress with CPAP. Accurate detection of sleep stages from CPAP flow signal is crucial for such a mechanism. We propose, for the first time, an automated sleep staging model based only on the flow signal. Deep neural networks have recently shown high accuracy on sleep staging by eliminating handcrafted features. However, these methods focus exclusively on extracting informative features from the input signal, without paying much attention to the dynamics of sleep stages in the output sequence. We propose an end-to-end framework that uses a combination of deep convolution and recurrent neural networks to extract high-level features from raw flow signal with a structured output layer based on a conditional random field to model the temporal transition structure of the sleep stages. We improve upon the previous methods by 10% using our model, that can be augmented to the previous sleep staging deep learning methods. We also show that our method can be used to accurately track sleep metrics like sleep efficiency calculated from sleep stages that can be deployed for monitoring the response of CPAP therapy on sleep apnea patients. Apart from the technical contributions, we expect this study to motivate new research questions in sleep science.

Textual reviews, which are readily available on many e-commerce and review websites such as Amazon and Yelp, serve as an invaluable source of information for recommender systems. However, not all parts of the reviews are equally important, and the same choice of words may reflect a different meaning based on its context. In this paper, we propose a novel end-to-end Aspect-based Neural Recommender (ANR) to perform aspect-based representation learning for both users and items via an attention-based component. Furthermore, we model the multi-faceted process behind how users rate items by estimating the aspect-level user and item importance by adapting the neural co-attention mechanism. Our proposed model concurrently address several shortcomings of existing recommender systems, and a thorough experimental study on 25 benchmark datasets from Amazon and Yelp shows that ANR significantly outperforms recently proposed state-of-the-art baselines such as DeepCoNN, D-Attn and ALFM.

Discourse processing is a suite of Natural Language Processing (NLP) tasks to uncover linguistic structures from texts at several levels, which can support many text mining applications. This involves identifying the topic structure, the coherence structure, the coreference structure, and the conversation structure for conversational discourse. Taken together, these structures can inform text summarization, essay scoring, sentiment analysis, machine translation, information extraction, question answering, and thread recovery. The tutorial starts with an overview of basic concepts in discourse analysis - monologue vs. conversation, synchronous vs. asynchronous conversation, and key linguistic structures in discourse analysis. It then covers traditional machine learning methods along with the most recent works using deep learning, and compare their performances on benchmark datasets. For each discourse structure we describe, we show its applications in downstream text mining tasks. Methods and metrics for evaluation are discussed in detail. We conclude the tutorial with an interactive discussion of future challenges and opportunities.

Despite the efforts in 70+ years in all aspects of entity resolution (ER), there is still a high demand for democratizing ER - by reducing the heavy human involvement in labeling data, performing feature engineering, tuning parameters, and defining blocking functions. With the recent advances in deep learning, in particular distributed representations of words ( a.k.a . word embeddings), we present a novel ER system, called D eep ER, that achieves good accuracy, high efficiency, as well as ease-of-use ( i.e ., much less human efforts). We use sophisticated composition methods, namely uni- and bi-directional recurrent neural networks (RNNs) with long short term memory (LSTM) hidden units, to convert each tuple to a distributed representation ( i.e ., a vector), which can in turn be used to effectively capture similarities between tuples. We consider both the case where pre-trained word embeddings are available as well the case where they are not; we present ways to learn and tune the distributed representations that are customized for a specific ER task under different scenarios. We propose a locality sensitive hashing (LSH) based blocking approach that takes all attributes of a tuple into consideration and produces much smaller blocks, compared with traditional methods that consider only a few attributes. We evaluate our algorithms on multiple datasets (including benchmarks, biomedical data, as well as multi-lingual data) and the extensive experimental results show that D eep ER outperforms existing solutions.

Vector representation of sentences is important for many text processing tasks that involve classifying, clustering, or ranking sentences. For solving these tasks, bag-of-word based representation has been used for a long time. In recent years, distributed representation of sentences learned by neural models from unlabeled data has been shown to outperform traditional bag-of-words representations. However, most existing methods belonging to the neural models consider only the content of a sentence, and disregard its relations with other sentences in the context. In this paper, we first characterize two types of contexts depending on their scope and utility. We then propose two approaches to incorporate contextual information into content-based models. We evaluate our sentence representation models in a setup, where context is available to infer sentence vectors. Experimental results demonstrate that our proposed models outshine existing models on three fundamental tasks, such as, classifying, clustering, and ranking sentences.

We study how to find relevant questions in community forums when the language of the new questions is different from that of the existing questions in the forum. In particular, we explore the Arabic-English language pair. We compare a kernel-based system with a feed-forward neural network in a scenario where a large parallel corpus is available for training a machine translation system, bilingual dictionaries, and cross-language word embeddings. We observe that both approaches degrade the performance of the system when working on the translated text, especially the kernel-based system, which depends heavily on a syntactic kernel. We address this issue using a cross-language tree kernel, which compares the original Arabic tree to the English trees of the related questions. We show that this kernel almost closes the performance gap with respect to the monolingual system. On the neural network side, we use the parallel corpus to train cross-language embeddings, which we then use to represent the Arabic input and the English related questions in the same space. The results also improve to close to those of the monolingual neural network. Overall, the kernel system shows a better performance compared to the neural network in all cases.