Search

Most prior work on task-oriented dialogue systems are restricted to limited coverage of domain APIs. However, users oftentimes have requests that are out of the scope of these APIs. This work focuses on responding to these beyond-API-coverage user turns by incorporating external, unstructured knowledge sources. Our approach works in a pipelined manner with knowledge-seeking turn detection, knowledge selection, and response generation in sequence. We introduce novel data augmentation methods for the first two steps and demonstrate that the use of information extracted from dialogue context improves the knowledge selection and end-to-end performances. Through experiments, we achieve state-of-the-art performance for both automatic and human evaluation metrics on the DSTC9 Track 1 benchmark dataset, validating the effectiveness of our contributions., Comment: Presented as a DIALDOC workshop paper at ACL 2021

A community reveals the features and connections of its members that are different from those in other communities in a network. Detecting communities is of great significance in network analysis. Despite the classical spectral clustering and statistical inference methods, we notice a significant development of deep learning techniques for community detection in recent years with their advantages in handling high dimensional network data. Hence, a comprehensive overview of community detection's latest progress through deep learning is timely to academics and practitioners. This survey devises and proposes a new taxonomy covering different state-of-the-art methods, including deep learning-based models upon deep neural networks, deep nonnegative matrix factorization and deep sparse filtering. The main category, i.e., deep neural networks, is further divided into convolutional networks, graph attention networks, generative adversarial networks and autoencoders. The survey also summarizes the popular benchmark data sets, evaluation metrics, and open-source implementations to address experimentation settings. We then discuss the practical applications of community detection in various domains and point to implementation scenarios. Finally, we outline future directions by suggesting challenging topics in this fast-growing deep learning field., Comment: 29 Pages

Recent developments in Natural Language Processing (NLP) demonstrate that large-scale, self-supervised pre-training can be extremely beneficial for downstream tasks. These ideas have been adapted to other domains, including the analysis of the amino acid sequences of proteins. However, to date most attempts on protein sequences rely on direct masked language model style pre-training. In this work, we design a new, adversarial pre-training method for proteins, extending and specializing similar advances in NLP. We show compelling results in comparison to traditional MLM pre-training, though further development is needed to ensure the gains are worth the significant computational cost.

While most network embedding techniques model the proximity between nodes in a network, recently there has been significant interest in structural embeddings that are based on node equivalences, a notion rooted in sociology: equivalences or positions are collections of nodes that have similar roles--i.e., similar functions, ties or interactions with nodes in other positions--irrespective of their distance or reachability in the network. Unlike the proximity-based methods that are rigorously evaluated in the literature, the evaluation of structural embeddings is less mature. It relies on small synthetic or real networks with labels that are not perfectly defined, and its connection to sociological equivalences has hitherto been vague and tenuous. With new node embedding methods being developed at a breakneck pace, proper evaluation and systematic characterization of existing approaches will be essential to progress. To fill in this gap, we set out to understand what types of equivalences structural embeddings capture. We are the first to contribute rigorous intrinsic and extrinsic evaluation methodology for structural embeddings, along with carefully-designed, diverse datasets of varying sizes. We observe a number of different evaluation variables that can lead to different results (e.g., choice of similarity measure, classifier, label definitions). We find that degree distributions within nodes' local neighborhoods can lead to simple yet effective baselines in their own right and guide the future development of structural embedding. We hope that our findings can influence the design of further node embedding methods and also pave the way for more comprehensive and fair evaluation of structural embedding methods., Comment: A shorter version of this paper was presented in the Mining and Learning with Graphs workshop at KDD 2020

Result relevance prediction is an essential task of e-commerce search engines to boost the utility of search engines and ensure smooth user experience. The last few years eyewitnessed a flurry of research on the use of Transformer-style models and deep text-match models to improve relevance. However, these two types of models ignored the inherent bipartite network structures that are ubiquitous in e-commerce search logs, making these models ineffective. We propose in this paper a novel Second-order Relevance, which is fundamentally different from the previous First-order Relevance, to improve result relevance prediction. We design, for the first time, an end-to-end First-and-Second-order Relevance prediction model for e-commerce item relevance. The model is augmented by the neighborhood structures of bipartite networks that are built using the information of user behavioral feedback, including clicks and purchases. To ensure that edges accurately encode relevance information, we introduce external knowledge generated from BERT to refine the network of user behaviors. This allows the new model to integrate information from neighboring items and queries, which are highly relevant to the focus query-item pair under consideration. Results of offline experiments showed that the new model significantly improved the prediction accuracy in terms of human relevance judgment. An ablation study showed that the First-and-Second-order model gained a 4.3% average gain over the First-order model. Results of an online A/B test revealed that the new model derived more commercial benefits compared to the base model.

Community detection, a fundamental task for network analysis, aims to partition a network into multiple sub-structures to help reveal their latent functions. Community detection has been extensively studied in and broadly applied to many real-world network problems. Classical approaches to community detection typically utilize probabilistic graphical models and adopt a variety of prior knowledge to infer community structures. As the problems that network methods try to solve and the network data to be analyzed become increasingly more sophisticated, new approaches have also been proposed and developed, particularly those that utilize deep learning and convert networked data into low dimensional representation. Despite all the recent advancement, there is still a lack of insightful understanding of the theoretical and methodological underpinning of community detection, which will be critically important for future development of the area of network analysis. In this paper, we develop and present a unified architecture of network community-finding methods to characterize the state-of-the-art of the field of community detection. Specifically, we provide a comprehensive review of the existing community detection methods and introduce a new taxonomy that divides the existing methods into two categories, namely probabilistic graphical model and deep learning. We then discuss in detail the main idea behind each method in the two categories. Furthermore, to promote future development of community detection, we release several benchmark datasets from several problem domains and highlight their applications to various network analysis tasks. We conclude with discussions of the challenges of the field and suggestions of possible directions for future research.

Leukocyte differential test is a widely performed clinical procedure for screening infectious diseases. Existing hematology analyzers require labor-intensive work and a panel of expensive reagents. Here we report an artificial-intelligence enabled reagent-free imaging hematology analyzer (AIRFIHA) modality that can accurately classify subpopulations of leukocytes with minimal sample preparation. AIRFIHA is realized through training a two-step residual neural network using label-free images of separated leukocytes acquired from a custom-built quantitative phase microscope. We validated the performance of AIRFIHA in randomly selected test set and cross-validated it across all blood donors. AIRFIHA outperforms current methods in classification accuracy, especially in B and T lymphocytes, while preserving the natural state of cells. It also shows a promising potential in differentiating CD4 and CD8 cells. Owing to its easy operation, low cost, and strong discerning capability of complex leukocyte subpopulations, we envision AIRFIHA is clinically translatable and can also be deployed in resource-limited settings, e.g., during pandemic situations for the rapid screening of infectious diseases.

Text style transfer is an important task in natural language generation, which aims to control certain attributes in the generated text, such as politeness, emotion, humor, and many others. It has a long history in the field of natural language processing, and recently has re-gained significant attention thanks to the promising performance brought by deep neural models. In this paper, we present a systematic survey of the research on neural text style transfer, spanning over 100 representative articles since the first neural text style transfer work in 2017. We discuss the task formulation, existing datasets and subtasks, evaluation, as well as the rich methodologies in the presence of parallel and non-parallel data. We also provide discussions on a variety of important topics regarding the future development of this task. Our curated paper list is at https://github.com/zhijing-jin/Text_Style_Transfer_Survey, Comment: Computational Linguistics Journal 2022

Graph convolutional networks (GCNs), aiming to integrate high-order neighborhood information through stacked graph convolution layers, have demonstrated remarkable power in many network analysis tasks. However, topological limitations, including over-smoothing and local topology homophily, limit its capability to represent networks. Existing studies only perform feature convolution on network topology, which inevitably introduces unbalance between topology and features. Considering that in real world, the information network consists of not only the node-level citation information but also the local text-sequence information. We propose BiTe-GCN, a novel GCN architecture with bidirectional convolution of both topology and features on text-rich networks to solve these limitations. We first transform the original text-rich network into an augmented bi-typed heterogeneous network, capturing both the global node-level information and the local text-sequence information from texts. We then introduce discriminative convolution mechanisms to performs convolutions of both topology and features simultaneously. Extensive experiments on text-rich networks demonstrate that our new architecture outperforms state-of-the-art by a breakout improvement. Moreover, this architecture can also be applied to several e-commerce searching scenes such as JD searching. The experiments on the JD dataset validate the superiority of the proposed architecture over the related methods., Comment: WSDM 2021

Graph neural networks (GNNs) are popular to use for classifying structured data in the context of machine learning. But surprisingly, they are rarely applied to regression problems. In this work, we adopt GNN for a classic but challenging nonlinear regression problem, namely the network localization. Our main findings are in order. First, GNN is potentially the best solution to large-scale network localization in terms of accuracy, robustness and computational time. Second, proper thresholding of the communication range is essential to its superior performance. Simulation results corroborate that the proposed GNN based method outperforms all state-of-the-art benchmarks by far. Such inspiring results are theoretically justified in terms of data aggregation, non-line-of-sight (NLOS) noise removal and low-pass filtering effect, all affected by the threshold for neighbor selection. Code is available at https://github.com/Yanzongzi/GNN-For-localization., Comment: Accepted by ICASSP 2021, Code available at https://github.com/Yanzongzi/GNN-For-localization

Relevance has significant impact on user experience and business profit for e-commerce search platform. In this work, we propose a data-driven framework for search relevance prediction, by distilling knowledge from BERT and related multi-layer Transformer teacher models into simple feed-forward networks with large amount of unlabeled data. The distillation process produces a student model that recovers more than 97\% test accuracy of teacher models on new queries, at a serving cost that's several magnitude lower (latency 150x lower than BERT-Base and 15x lower than the most efficient BERT variant, TinyBERT). The applications of temperature rescaling and teacher model stacking further boost model accuracy, without increasing the student model complexity. We present experimental results on both in-house e-commerce search relevance data as well as a public data set on sentiment analysis from the GLUE benchmark. The latter takes advantage of another related public data set of much larger scale, while disregarding its potentially noisy labels. Embedding analysis and case study on the in-house data further highlight the strength of the resulting model. By making the data processing and model training source code public, we hope the techniques presented here can help reduce energy consumption of the state of the art Transformer models and also level the playing field for small organizations lacking access to cutting edge machine learning hardwares., Comment: 10 pages, 7 figures, to appear in ICDM 2020

Open domain question answering (OpenQA) tasks have been recently attracting more and more attention from the natural language processing (NLP) community. In this work, we present the first free-form multiple-choice OpenQA dataset for solving medical problems, MedQA, collected from the professional medical board exams. It covers three languages: English, simplified Chinese, and traditional Chinese, and contains 12,723, 34,251, and 14,123 questions for the three languages, respectively. We implement both rule-based and popular neural methods by sequentially combining a document retriever and a machine comprehension model. Through experiments, we find that even the current best method can only achieve 36.7\%, 42.0\%, and 70.1\% of test accuracy on the English, traditional Chinese, and simplified Chinese questions, respectively. We expect MedQA to present great challenges to existing OpenQA systems and hope that it can serve as a platform to promote much stronger OpenQA models from the NLP community in the future., Comment: Submitted to AAAI 2021

We introduce a general framework for leveraging graph stream data for temporal prediction-based applications. Our proposed framework includes novel methods for learning an appropriate graph time-series representation, modeling and weighting the temporal dependencies, and generalizing existing embedding methods for such data. While previous work on dynamic modeling and embedding has focused on representing a stream of timestamped edges using a time-series of graphs based on a specific time-scale (e.g., 1 month), we propose the notion of an $\epsilon$-graph time-series that uses a fixed number of edges for each graph, and show its superiority over the time-scale representation used in previous work. In addition, we propose a number of new temporal models based on the notion of temporal reachability graphs and weighted temporal summary graphs. These temporal models are then used to generalize existing base (static) embedding methods by enabling them to incorporate and appropriately model temporal dependencies in the data. From the 6 temporal network models investigated (for each of the 7 base embedding methods), we find that the top-3 temporal models are always those that leverage the new $\epsilon$-graph time-series representation. Furthermore, the dynamic embedding methods from the framework almost always achieve better predictive performance than existing state-of-the-art dynamic node embedding methods that are developed specifically for such temporal prediction tasks. Finally, the findings of this work are useful for designing better dynamic embedding methods.

Aspect-based sentiment analysis (ABSA) aims to predict the sentiment towards a specific aspect in the text. However, existing ABSA test sets cannot be used to probe whether a model can distinguish the sentiment of the target aspect from the non-target aspects. To solve this problem, we develop a simple but effective approach to enrich ABSA test sets. Specifically, we generate new examples to disentangle the confounding sentiments of the non-target aspects from the target aspect's sentiment. Based on the SemEval 2014 dataset, we construct the Aspect Robustness Test Set (ARTS) as a comprehensive probe of the aspect robustness of ABSA models. Over 92% data of ARTS show high fluency and desired sentiment on all aspects by human evaluation. Using ARTS, we analyze the robustness of nine ABSA models, and observe, surprisingly, that their accuracy drops by up to 69.73%. We explore several ways to improve aspect robustness, and find that adversarial training can improve models' performance on ARTS by up to 32.85%. Our code and new test set are available at https://github.com/zhijing-jin/ARTS_TestSet, Comment: EMNLP 2020, long paper

Generating accurate descriptions for online fashion items is important not only for enhancing customers' shopping experiences, but also for the increase of online sales. Besides the need of correctly presenting the attributes of items, the expressions in an enchanting style could better attract customer interests. The goal of this work is to develop a novel learning framework for accurate and expressive fashion captioning. Different from popular work on image captioning, it is hard to identify and describe the rich attributes of fashion items. We seed the description of an item by first identifying its attributes, and introduce attribute-level semantic (ALS) reward and sentence-level semantic (SLS) reward as metrics to improve the quality of text descriptions. We further integrate the training of our model with maximum likelihood estimation (MLE), attribute embedding, and Reinforcement Learning (RL). To facilitate the learning, we build a new FAshion CAptioning Dataset (FACAD), which contains 993K images and 130K corresponding enchanting and diverse descriptions. Experiments on FACAD demonstrate the effectiveness of our model., Comment: In proceedings of ECCV 2020

Heterogeneous information network (HIN) embedding, aiming to map the structure and semantic information in a HIN to distributed representations, has drawn considerable research attention. Graph neural networks for HIN embeddings typically adopt a hierarchical attention (including node-level and meta-path-level attentions) to capture the information from meta-path-based neighbors. However, this complicated attention structure often cannot achieve the function of selecting meta-paths due to severe overfitting. Moreover, when propagating information, these methods do not distinguish direct (one-hop) meta-paths from indirect (multi-hop) ones. But from the perspective of network science, direct relationships are often believed to be more essential, which can only be used to model direct information propagation. To address these limitations, we propose a novel neural network method via implicitly utilizing attention and meta-paths, which can relieve the severe overfitting brought by the current over-parameterized attention mechanisms on HIN. We first use the multi-layer graph convolutional network (GCN) framework, which performs a discriminative aggregation at each layer, along with stacking the information propagation of direct linked meta-paths layer-by-layer, realizing the function of attentions for selecting meta-paths in an indirect way. We then give an effective relaxation and improvement via introducing a new propagation operation which can be separated from aggregation. That is, we first model the whole propagation process with well-defined probabilistic diffusion dynamics, and then introduce a random graph-based constraint which allows it to reduce noise with the increase of layers. Extensive experiments demonstrate the superiority of the new approach over state-of-the-art methods.

Learning continuous-time stochastic dynamics is a fundamental and essential problem in modeling sporadic time series, whose observations are irregular and sparse in both time and dimension. For a given system whose latent states and observed data are high-dimensional, it is generally impossible to derive a precise continuous-time stochastic process to describe the system behaviors. To solve the above problem, we apply Variational Bayesian method and propose a flexible continuous-time stochastic recurrent neural network named Variational Stochastic Differential Networks (VSDN), which embeds the complicated dynamics of the sporadic time series by neural Stochastic Differential Equations (SDE). VSDNs capture the stochastic dependency among latent states and observations by deep neural networks. We also incorporate two differential Evidence Lower Bounds to efficiently train the models. Through comprehensive experiments, we show that VSDNs outperform state-of-the-art continuous-time deep learning models and achieve remarkable performance on prediction and interpolation tasks for sporadic time series.

While there has been substantial research using adversarial attacks to analyze NLP models, each attack is implemented in its own code repository. It remains challenging to develop NLP attacks and utilize them to improve model performance. This paper introduces TextAttack, a Python framework for adversarial attacks, data augmentation, and adversarial training in NLP. TextAttack builds attacks from four components: a goal function, a set of constraints, a transformation, and a search method. TextAttack's modular design enables researchers to easily construct attacks from combinations of novel and existing components. TextAttack provides implementations of 16 adversarial attacks from the literature and supports a variety of models and datasets, including BERT and other transformers, and all GLUE tasks. TextAttack also includes data augmentation and adversarial training modules for using components of adversarial attacks to improve model accuracy and robustness. TextAttack is democratizing NLP: anyone can try data augmentation and adversarial training on any model or dataset, with just a few lines of code. Code and tutorials are available at https://github.com/QData/TextAttack., Comment: 6 pages. More details are shared at https://github.com/QData/TextAttack

Dialogue state tracking (DST) is at the heart of task-oriented dialogue systems. However, the scarcity of labeled data is an obstacle to building accurate and robust state tracking systems that work across a variety of domains. Existing approaches generally require some dialogue data with state information and their ability to generalize to unknown domains is limited. In this paper, we propose using machine reading comprehension (RC) in state tracking from two perspectives: model architectures and datasets. We divide the slot types in dialogue state into categorical or extractive to borrow the advantages from both multiple-choice and span-based reading comprehension models. Our method achieves near the current state-of-the-art in joint goal accuracy on MultiWOZ 2.1 given full training data. More importantly, by leveraging machine reading comprehension datasets, our method outperforms the existing approaches by many a large margin in few-shot scenarios when the availability of in-domain data is limited. Lastly, even without any state tracking data, i.e., zero-shot scenario, our proposed approach achieves greater than 90% average slot accuracy in 12 out of 30 slots in MultiWOZ 2.1.

Current summarization systems only produce plain, factual headlines, but do not meet the practical needs of creating memorable titles to increase exposure. We propose a new task, Stylistic Headline Generation (SHG), to enrich the headlines with three style options (humor, romance and clickbait), in order to attract more readers. With no style-specific article-headline pair (only a standard headline summarization dataset and mono-style corpora), our method TitleStylist generates style-specific headlines by combining the summarization and reconstruction tasks into a multitasking framework. We also introduced a novel parameter sharing scheme to further disentangle the style from the text. Through both automatic and human evaluation, we demonstrate that TitleStylist can generate relevant, fluent headlines with three target styles: humor, romance, and clickbait. The attraction score of our model generated headlines surpasses that of the state-of-the-art summarization model by 9.68%, and even outperforms human-written references., Comment: ACL 2020

State-of-the-art neural machine translation (NMT) systems are data-hungry and perform poorly on new domains with no supervised data. As data collection is expensive and infeasible in many cases, domain adaptation methods are needed. In this work, we propose a simple but effect approach to the semi-supervised domain adaptation scenario of NMT, where the aim is to improve the performance of a translation model on the target domain consisting of only non-parallel data with the help of supervised source domain data. This approach iteratively trains a Transformer-based NMT model via three training objectives: language modeling, back-translation, and supervised translation. We evaluate this method on two adaptation settings: adaptation between specific domains and adaptation from a general domain to specific domains, and on two language pairs: German to English and Romanian to English. With substantial performance improvement achieved---up to +19.31 BLEU over the strongest baseline, and +47.69 BLEU improvement over the unadapted model---we present this method as a simple but tough-to-beat baseline in the field of semi-supervised domain adaptation for NMT., Comment: Under review

Machine Reading Comprehension (MRC) for question answering (QA), which aims to answer a question given the relevant context passages, is an important way to test the ability of intelligence systems to understand human language. Multiple-Choice QA (MCQA) is one of the most difficult tasks in MRC because it often requires more advanced reading comprehension skills such as logical reasoning, summarization, and arithmetic operations, compared to the extractive counterpart where answers are usually spans of text within given passages. Moreover, most existing MCQA datasets are small in size, making the learning task even harder. We introduce MMM, a Multi-stage Multi-task learning framework for Multi-choice reading comprehension. Our method involves two sequential stages: coarse-tuning stage using out-of-domain datasets and multi-task learning stage using a larger in-domain dataset to help model generalize better with limited data. Furthermore, we propose a novel multi-step attention network (MAN) as the top-level classifier for this task. We demonstrate MMM significantly advances the state-of-the-art on four representative MCQA datasets., Comment: Accepted by AAAI 2020

Structural roles define sets of structurally similar nodes that are more similar to nodes inside the set than outside, whereas communities define sets of nodes with more connections inside the set than outside. Roles based on structural similarity and communities based on proximity are fundamentally different but important complementary notions. Recently, the notion of structural roles has become increasingly important and has gained a lot of attention due to the proliferation of work on learning representations (node/edge embeddings) from graphs that preserve the notion of roles. Unfortunately, recent work has sometimes confused the notion of structural roles and communities (based on proximity) leading to misleading or incorrect claims about the capabilities of network embedding methods. As such, this paper seeks to clarify the misconceptions and key differences between structural roles and communities, and formalize the general mechanisms (e.g., random walks, feature diffusion) that give rise to community or role-based structural embeddings. We theoretically prove that embedding methods based on these mechanisms result in either community or role-based structural embeddings. These mechanisms are typically easy to identify and can help researchers quickly determine whether a method preserves community or role-based embeddings. Furthermore, they also serve as a basis for developing new and improved methods for community or role-based structural embeddings. Finally, we analyze and discuss applications and data characteristics where community or role-based embeddings are most appropriate.

Machine learning algorithms are often vulnerable to adversarial examples that have imperceptible alterations from the original counterparts but can fool the state-of-the-art models. It is helpful to evaluate or even improve the robustness of these models by exposing the maliciously crafted adversarial examples. In this paper, we present TextFooler, a simple but strong baseline to generate natural adversarial text. By applying it to two fundamental natural language tasks, text classification and textual entailment, we successfully attacked three target models, including the powerful pre-trained BERT, and the widely used convolutional and recurrent neural networks. We demonstrate the advantages of this framework in three ways: (1) effective---it outperforms state-of-the-art attacks in terms of success rate and perturbation rate, (2) utility-preserving---it preserves semantic content and grammaticality, and remains correctly classified by humans, and (3) efficient---it generates adversarial text with computational complexity linear to the text length. *The code, pre-trained target models, and test examples are available at https://github.com/jind11/TextFooler., Comment: AAAI 2020 (Oral)

Identity stitching, the task of identifying and matching various online references (e.g., sessions over different devices and timespans) to the same user in real-world web services, is crucial for personalization and recommendations. However, traditional user stitching approaches, such as grouping or blocking, require quadratic pairwise comparisons between a massive number of user activities, thus posing both computational and storage challenges. Recent works, which are often application-specific, heuristically seek to reduce the amount of comparisons, but they suffer from low precision and recall. To solve the problem in an application-independent way, we take a heterogeneous network-based approach in which users (nodes) interact with content (e.g., sessions, websites), and may have attributes (e.g., location). We propose node2bits, an efficient framework that represents multi-dimensional features of node contexts with binary hashcodes. node2bits leverages feature-based temporal walks to encapsulate short- and long-term interactions between nodes in heterogeneous web networks, and adopts SimHash to obtain compact, binary representations and avoid the quadratic complexity for similarity search. Extensive experiments on large-scale real networks show that node2bits outperforms traditional techniques and existing works that generate real-valued embeddings by up to 5.16% in F1 score on user stitching, while taking only up to 1.56% as much storage.

Contextual word embedding models such as ELMo (Peters et al., 2018) and BERT (Devlin et al., 2018) have dramatically improved performance for many natural language processing (NLP) tasks in recent months. However, these models have been minimally explored on specialty corpora, such as clinical text; moreover, in the clinical domain, no publicly-available pre-trained BERT models yet exist. In this work, we address this need by exploring and releasing BERT models for clinical text: one for generic clinical text and another for discharge summaries specifically. We demonstrate that using a domain-specific model yields performance improvements on three common clinical NLP tasks as compared to nonspecific embeddings. These domain-specific models are not as performant on two clinical de-identification tasks, and argue that this is a natural consequence of the differences between de-identified source text and synthetically non de-identified task text., Comment: Clinical Natural Language Processing (ClinicalNLP) Workshop at NAACL 2019