Searcharxiv⌕ Search

arXiv subjects

Dell Zhang

Publications and source records attributed to Dell Zhang.

At least 37 records · Page 2Linked to original sources
arXiv2023

Context-Aware Classification of Legal Document Pages

For many business applications that require the processing, indexing, and retrieval of professional documents such as legal briefs (in PDF format etc.), it is often essential to classify the pages of any given document into their corresponding types beforehand. Most existing studies in the field of document image classification either focus on single-page documents or treat multiple pages in a document independently. Although in recent years a few techniques have been proposed to exploit the context information from neighboring pages to enhance document page classification, they typically cannot be utilized with large pre-trained language models due to the constraint on input length. In this paper, we present a simple but effective approach that overcomes the above limitation. Specifically, we enhance the input with extra tokens carrying sequential information about previous pages - introducing recurrence - which enables the usage of pre-trained Transformer models like BERT for context-aware page classification. Our experiments conducted on two legal datasets in English and Portuguese respectively show that the proposed approach can significantly improve the performance of document page classification compared to the non-recurrent setup as well as the other context-aware baselines.

cs.CL↗
arXiv2023

PerCoNet: News Recommendation with Explicit Persona and Contrastive Learning

Personalized news recommender systems help users quickly find content of their interests from the sea of information. Today, the mainstream technology for personalized news recommendation is based on deep neural networks that can accurately model the semantic match between news items and users' interests. In this paper, we present \textbf{PerCoNet}, a novel deep learning approach to personalized news recommendation which features two new findings: (i) representing users through \emph{explicit persona analysis} based on the prominent entities in their recent news reading history could be more effective than latent persona analysis employed by most existing work, with a side benefit of enhanced explainability; (ii) utilizing the title and abstract of each news item via cross-view \emph{contrastive learning} would work better than just combining them directly. Extensive experiments on two real-world news datasets clearly show the superior performance of our proposed approach in comparison with current state-of-the-art techniques.

cs.IR↗
arXiv2023

Making a Computational Attorney

This "blue sky idea" paper outlines the opportunities and challenges in data mining and machine learning involving making a computational attorney -- an intelligent software agent capable of helping human lawyers with a wide range of complex high-level legal tasks such as drafting legal briefs for the prosecution or defense in court. In particular, we discuss what a ChatGPT-like Large Legal Language Model (L$^3$M) can and cannot do today, which will inspire researchers with promising short-term and long-term research objectives.

cs.CL↗
arXiv2022

A Survey on Knowledge-Enhanced Pre-trained Language Models

Natural Language Processing (NLP) has been revolutionized by the use of Pre-trained Language Models (PLMs) such as BERT. Despite setting new records in nearly every NLP task, PLMs still face a number of challenges including poor interpretability, weak reasoning capability, and the need for a lot of expensive annotated data when applied to downstream tasks. By integrating external knowledge into PLMs, \textit{\underline{K}nowledge-\underline{E}nhanced \underline{P}re-trained \underline{L}anguage \underline{M}odels} (KEPLMs) have the potential to overcome the above-mentioned limitations. In this paper, we examine KEPLMs systematically through a series of studies. Specifically, we outline the common types and different formats of knowledge to be integrated into KEPLMs, detail the existing methods for building and evaluating KEPLMS, present the applications of KEPLMs in downstream tasks, and discuss the future research directions. Researchers will benefit from this survey by gaining a quick and comprehensive overview of the latest developments in this field.

cs.CL↗
arXiv2022

TegFormer: Topic-to-Essay Generation with Good Topic Coverage and High Text Coherence

Creating an essay based on a few given topics is a challenging NLP task. Although several effective methods for this problem, topic-to-essay generation, have appeared recently, there is still much room for improvement, especially in terms of the coverage of the given topics and the coherence of the generated text. In this paper, we propose a novel approach called TegFormer which utilizes the Transformer architecture where the encoder is enriched with domain-specific contexts while the decoder is enhanced by a large-scale pre-trained language model. Specifically, a \emph{Topic-Extension} layer capturing the interaction between the given topics and their domain-specific contexts is plugged into the encoder. Since the given topics are usually concise and sparse, such an additional layer can bring more topic-related semantics in to facilitate the subsequent natural language generation. Moreover, an \emph{Embedding-Fusion} module that combines the domain-specific word embeddings learnt from the given corpus and the general-purpose word embeddings provided by a GPT-2 model pre-trained on massive text data is integrated into the decoder. Since GPT-2 is at a much larger scale, it contains a lot more implicit linguistic knowledge which would help the decoder to produce more grammatical and readable text. Extensive experiments have shown that the pieces of text generated by TegFormer have better topic coverage and higher text coherence than those from SOTA topic-to-essay techniques, according to automatic and human evaluations. As revealed by ablation studies, both the Topic-Extension layer and the Embedding-Fusion module contribute substantially to TegFormer's performance advantage.

cs.CL↗
arXiv2022

Forgetting Fast in Recommender Systems

Users of a recommender system may want part of their data being deleted, not only from the data repository but also from the underlying machine learning model, for privacy or utility reasons. Such right-to-be-forgotten requests could be fulfilled by simply retraining the recommendation model from scratch, but that would be too slow and too expensive in practice. In this paper, we investigate fast machine unlearning techniques for recommender systems that can remove the effect of a small amount of training data from the recommendation model without incurring the full cost of retraining. A natural idea to speed this process up is to fine-tune the current recommendation model on the remaining training data instead of starting from a random initialization. This warm-start strategy indeed works for neural recommendation models using standard 1st-order neural network optimizers (like AdamW). However, we have found that even greater acceleration could be achieved by employing 2nd-order (Newton or quasi-Newton) optimization methods instead. To overcome the prohibitively high computational cost of 2nd-order optimizers, we propose a new recommendation unlearning approach AltEraser which divides the optimization problem of unlearning into many small tractable sub-problems. Extensive experiments on three real-world recommendation datasets show promising results of AltEraser in terms of consistency (forgetting thoroughness), accuracy (recommendation effectiveness), and efficiency (unlearning speed). To our knowledge, this work represents the first attempt at fast approximate machine unlearning for state-of-the-art neural recommendation models.

cs.IR↗
arXiv2022

Micro-Behavior Encoding for Session-based Recommendation

Session-based Recommendation (SR) aims to predict the next item for recommendation based on previously recorded sessions of user interaction. The majority of existing approaches to SR focus on modeling the transition patterns of items. In such models, the so-called micro-behaviors describing how the user locates an item and carries out various activities on it (e.g., click, add-to-cart, and read-comments), are simply ignored. A few recent studies have tried to incorporate the sequential patterns of micro-behaviors into SR models. However, those sequential models still cannot effectively capture all the inherent interdependencies between micro-behavior operations. In this work, we aim to investigate the effects of the micro-behavior information in SR systematically. Specifically, we identify two different patterns of micro-behaviors: "sequential patterns" and "dyadic relational patterns". To build a unified model of user micro-behaviors, we first devise a multigraph to aggregate the sequential patterns from different items via a graph neural network, and then utilize an extended self-attention network to exploit the pair-wise relational patterns of micro-behaviors. Extensive experiments on three public real-world datasets show the superiority of the proposed approach over the state-of-theart baselines and confirm the usefulness of these two different micro-behavior patterns for SR.

cs.IR↗
arXiv2021

Recommendation Fairness: From Static to Dynamic

Driven by the need to capture users' evolving interests and optimize their long-term experiences, more and more recommender systems have started to model recommendation as a Markov decision process and employ reinforcement learning to address the problem. Shouldn't research on the fairness of recommender systems follow the same trend from static evaluation and one-shot intervention to dynamic monitoring and non-stop control? In this paper, we portray the recent developments in recommender systems first and then discuss how fairness could be baked into the reinforcement learning techniques for recommendation. Moreover, we argue that in order to make further progress in recommendation fairness, we may want to consider multi-agent (game-theoretic) optimization, multi-objective (Pareto) optimization, and simulation-based optimization, in the general framework of stochastic games.

cs.IR↗
arXiv2021

Grounding Natural Language Instructions: Can Large Language Models Capture Spatial Information?

Models designed for intelligent process automation are required to be capable of grounding user interface elements. This task of interface element grounding is centred on linking instructions in natural language to their target referents. Even though BERT and similar pre-trained language models have excelled in several NLP tasks, their use has not been widely explored for the UI grounding domain. This work concentrates on testing and probing the grounding abilities of three different transformer-based models: BERT, RoBERTa and LayoutLM. Our primary focus is on these models' spatial reasoning skills, given their importance in this domain. We observe that LayoutLM has a promising advantage for applications in this domain, even though it was created for a different original purpose (representing scanned documents): the learned spatial features appear to be transferable to the UI grounding setting, especially as they demonstrate the ability to discriminate between target directions in natural language instructions.

cs.CL↗
arXiv2020

Process Discovery for Structured Program Synthesis

A core task in process mining is process discovery which aims to learn an accurate process model from event log data. In this paper, we propose to use (block-) structured programs directly as target process models so as to establish connections to the field of program synthesis and facilitate the translation from abstract process models to executable processes, e.g., for robotic process automation. Furthermore, we develop a novel bottom-up agglomerative approach to the discovery of such structured program process models. In comparison with the popular top-down recursive inductive miner, our proposed agglomerative miner enjoys the similar theoretical guarantee to produce sound process models (without deadlocks and other anomalies) while exhibiting some advantages like avoiding silent activities and accommodating duplicate activities. The proposed algorithm works by iteratively applying a few graph rewriting rules to the directly-follows-graph of activities. For real-world (sparse) directly-follows-graphs, the algorithm has quadratic computational complexity with respect to the number of distinct activities. To our knowledge, this is the first process discovery algorithm that is made for the purpose of program synthesis. Experiments on the BPI-Challenge 2020 dataset and the Karel programming dataset have demonstrated that our proposed algorithm can outperform the inductive miner not only according to the traditional process discovery metrics but also in terms of the effectiveness in finding out the true underlying structured program from a small number of its execution traces.

cs.AI↗
arXiv2020

On the Evaluation of Intelligent Process Automation

Intelligent Process Automation (IPA) is emerging as a sub-field of AI to support the automation of long-tail processes which requires the coordination of tasks across different systems. So far, the field of IPA has been largely driven by systems and use cases, lacking a more formal definition of the task and its assessment. This paper aims to address this gap by providing a formalisation of IPA and by proposing specific metrics to support the empirical evaluation of IPA systems. This work also compares and contrasts IPA against related tasks such as end-user programming and program synthesis.

cs.HC↗
arXiv2019

Factorized Q-Learning for Large-Scale Multi-Agent Systems

Deep Q-learning has achieved significant success in single-agent decision making tasks. However, it is challenging to extend Q-learning to large-scale multi-agent scenarios, due to the explosion of action space resulting from the complex dynamics between the environment and the agents. In this paper, we propose to make the computation of multi-agent Q-learning tractable by treating the Q-function (w.r.t. state and joint-action) as a high-order high-dimensional tensor and then approximate it with factorized pairwise interactions. Furthermore, we utilize a composite deep neural network architecture for computing the factorized Q-function, share the model parameters among all the agents within the same group, and estimate the agents' optimal joint actions through a coordinate descent type algorithm. All these simplifications greatly reduce the model complexity and accelerate the learning process. Extensive experiments on two different multi-agent problems demonstrate the performance gain of our proposed approach in comparison with strong baselines, particularly when there are a large number of agents.

cs.MA↗
arXiv2019

SCRAM: Spatially Coherent Randomized Attention Maps

Attention mechanisms and non-local mean operations in general are key ingredients in many state-of-the-art deep learning techniques. In particular, the Transformer model based on multi-head self-attention has recently achieved great success in natural language processing and computer vision. However, the vanilla algorithm computing the Transformer of an image with n pixels has O(n^2) complexity, which is often painfully slow and sometimes prohibitively expensive for large-scale image data. In this paper, we propose a fast randomized algorithm --- SCRAM --- that only requires O(n log(n)) time to produce an image attention map. Such a dramatic acceleration is attributed to our insight that attention maps on real-world images usually exhibit (1) spatial coherence and (2) sparse structure. The central idea of SCRAM is to employ PatchMatch, a randomized correspondence algorithm, to quickly pinpoint the most compatible key (argmax) for each query first, and then exploit that knowledge to design a sparse approximation to non-local mean operations. Using the argmax (mode) to dynamically construct the sparse approximation distinguishes our algorithm from all of the existing sparse approximate methods and makes it very efficient. Moreover, SCRAM is a broadly applicable approximation to any non-local mean layer in contrast to some other sparse approximations that can only approximate self-attention. Our preliminary experimental results suggest that SCRAM is indeed promising for speeding up or scaling up the computation of attention maps in the Transformer.

cs.LG↗
arXiv2019

Market Trend Prediction using Sentiment Analysis: Lessons Learned and Paths Forward

Financial market forecasting is one of the most attractive practical applications of sentiment analysis. In this paper, we investigate the potential of using sentiment \emph{attitudes} (positive vs negative) and also sentiment \emph{emotions} (joy, sadness, etc.) extracted from financial news or tweets to help predict stock price movements. Our extensive experiments using the \emph{Granger-causality} test have revealed that (i) in general sentiment attitudes do not seem to Granger-cause stock price changes; and (ii) while on some specific occasions sentiment emotions do seem to Granger-cause stock price changes, the exhibited pattern is not universal and must be looked at on a case by case basis. Furthermore, it has been observed that at least for certain stocks, integrating sentiment emotions as additional features into the machine learning based market trend prediction model could improve its accuracy.

cs.CL↗
arXiv2018

On the Equilibrium of Query Reformulation and Document Retrieval

In this paper, we study jointly query reformulation and document relevance estimation, the two essential aspects of information retrieval (IR). Their interactions are modelled as a two-player strategic game: one player, a query formulator, taking actions to produce the optimal query, is expected to maximize its own utility with respect to the relevance estimation of documents produced by the other player, a retrieval modeler; simultaneously, the retrieval modeler, taking actions to produce the document relevance scores, needs to optimize its likelihood from the training data with respect to the refined query produced by the query formulator. Their equilibrium or equilibria will be reached when both are the best responses to each other. We derive our equilibrium theory of IR using normal-form representations: when a standard relevance feedback algorithm is coupled with a retrieval model, they would share the same objective function and thus form a partnership game; by contrast, pseudo relevance feedback pursues a rather different objective than that of retrieval models, therefore the interaction between them would lead to a general-sum game (though implicitly collaborative). Our game-theoretical analyses not only yield useful insights into the two major aspects of IR, but also offer new practical algorithms for achieving the equilibrium state of retrieval which have been shown to bring consistent performance improvements in both text retrieval and item recommendation.

cs.IR↗
arXiv2018

IRGAN: A Minimax Game for Unifying Generative and Discriminative Information Retrieval Models

This paper provides a unified account of two schools of thinking in information retrieval modelling: the generative retrieval focusing on predicting relevant documents given a query, and the discriminative retrieval focusing on predicting relevancy given a query-document pair. We propose a game theoretical minimax game to iteratively optimise both models. On one hand, the discriminative model, aiming to mine signals from labelled and unlabelled data, provides guidance to train the generative model towards fitting the underlying relevance distribution over documents given the query. On the other hand, the generative model, acting as an attacker to the current discriminative model, generates difficult examples for the discriminative model in an adversarial way by minimising its discrimination objective. With the competition between these two models, we show that the unified framework takes advantage of both schools of thinking: (i) the generative model learns to fit the relevance distribution over documents via the signals from the discriminative model, and (ii) the discriminative model is able to exploit the unlabelled data selected by the generative model to achieve a better estimation for document ranking. Our experimental results have demonstrated significant performance gains as much as 23.96% on Precision@5 and 15.50% on MAP over strong baselines in a variety of applications including web search, item recommendation, and question answering.

cs.IR↗
arXiv2016

The Anatomy of a Search and Mining System for Digital Archives

Samtla (Search And Mining Tools with Linguistic Analysis) is a digital humanities system designed in collaboration with historians and linguists to assist them with their research work in quantifying the content of any textual corpora through approximate phrase search and document comparison. The retrieval engine uses a character-based n-gram language model rather than the conventional word-based one so as to achieve great flexibility in language agnostic query processing. The index is implemented as a space-optimised character-based suffix tree with an accompanying database of document content and metadata. A number of text mining tools are integrated into the system to allow researchers to discover textual patterns, perform comparative analysis, and find out what is currently popular in the research community. Herein we describe the system architecture, user interface, models and algorithms, and data storage of the Samtla system. We also present several case studies of its usage in practice together with an evaluation of the systems' ranking performance through crowdsourcing.

cs.DL↗