Zenglin Xu


2024

pdf
FedLFC: Towards Efficient Federated Multilingual Modeling with LoRA-based Language Family Clustering
Zhihan Guo | Yifei Zhang | Zhuo Zhang | Zenglin Xu | Irwin King
Findings of the Association for Computational Linguistics: NAACL 2024

Federated Multilingual Modeling (FMM) plays a crucial role in the applications of natural language processing due to the increasing diversity of languages and the growing demand for data privacy. However, FMM faces limitations stemming from (1) the substantial communication costs in networking and (2) the conflicts arising from parameter interference between different languages. To address these challenges, we introduce a communication-efficient federated learning framework with low-rank adaptation and language family clustering for Multilingual Modeling (MM). In this framework, we maintain the weights of the base model, exclusively updating the lightweight Low-rank adaptation (LoRA) parameters to minimize communication costs. Additionally, we mitigate parameter conflicts by grouping languages based on their language family affiliations, as opposed to aggregating all LoRA parameters. Experiments demonstrate that our proposed model not only surpasses the baseline models in performance but also reduces the communication overhead. Our code is available at https://github.com/zhihan-guo/FedLFC.

pdf
XMoE: Sparse Models with Fine-grained and Adaptive Expert Selection
Yuanhang Yang | Shiyi Qi | Wenchao Gu | Chaozheng Wang | Cuiyun Gao | Zenglin Xu
Findings of the Association for Computational Linguistics ACL 2024

Sparse models, including sparse Mixture-of-Experts (MoE) models, have emerged as an effective approach for scaling Transformer models. However, they often suffer from computational inefficiency since a significant number of parameters are unnecessarily involved in computations by multiplying values by zero or low activation values. To address this issue, we present XMoE, a novel MoE designed to enhance both the efficacy and efficiency of sparse MoE models. XMoE leverages small experts and a threshold-based router to enable tokens to selectively engage only essential parameters. Our extensive experiments on language modeling and machine translation tasks demonstrate that enhances model performance and can decrease the computation load at MoE layers by over 50% without sacrificing performance. Furthermore, we present the versatility of by applying it to dense models, enabling sparse computation during inference. We provide a comprehensive analysis and make our code available at https://anonymous.4open.science/r/XMoE.

pdf
SecFormer: Fast and Accurate Privacy-Preserving Inference for Transformer Models via SMPC
Jinglong Luo | Yehong Zhang | Zhuo Zhang | Jiaqi Zhang | Xin Mu | Hui Wang | Yue Yu | Zenglin Xu
Findings of the Association for Computational Linguistics ACL 2024

With the growing use of Transformer models hosted on cloud platforms to offer inference services, privacy concerns are escalating, especially concerning sensitive data like investment plans and bank account details. Secure Multi-Party Computing (SMPC) emerges as a promising solution to protect the privacy of inference data and model parameters. However, the application of SMPC in Privacy-Preserving Inference (PPI) for Transformer models often leads to considerable slowdowns or declines in performance. This is largely due to the multitude of nonlinear operations in the Transformer architecture, which are not well-suited to SMPC and are difficult to circumvent or optimize effectively. To address this concern, we introduce a comprehensive PPI framework called SecFormer to achieve fast and accurate PPI for Transformer models. We successfully eliminate the high-cost exponential and maximum operations in PPI without sacrificing model performance and develop a suite of efficient SMPC protocols by employing suitable numerical computation methods to boost other complex nonlinear functions in PPI, including GeLU, LayerNorm, and a redesigned Softmax. Our extensive experiments reveal that SecFormer outperforms MPCFormer in performance, showing improvements of 3.4% and 24.7% for BERTBASE and BERTLARGE, respectively. In terms of efficiency, SecFormer is 3.57 and 3.58 times faster than PUMA for BERTBASE and BERTLARGE, demonstrating its effectiveness and speed.

pdf
Revisiting Data Reconstruction Attacks on Real-world Dataset for Federated Natural Language Understanding
Zhuo Zhang | Jintao Huang | Xiangjing Hu | Jingyuan Zhang | Yating Zhang | Hui Wang | Yue Yu | Qifan Wang | Lizhen Qu | Zenglin Xu
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

With the growing privacy concerns surrounding natural language understanding (NLU) applications, the need to train high-quality models while safeguarding data privacy has reached unprecedented importance. Federated learning (FL) offers a promising approach to collaborative model training by exchanging model gradients. However, many studies show that eavesdroppers in FL could develop sophisticated data reconstruction attack (DRA) to accurately reconstruct clients’ data from the shared gradients. Regrettably, current DRA methods in federated NLU have been mostly conducted on public datasets, lacking a comprehensive evaluation of real-world privacy datasets. To address this limitation, this paper presents a pioneering study that reexamines the performance of these DRA methods as well as corresponding defense methods. Specifically, we introduce a novel real-world privacy dataset called FedAttack which leads to a significant discovery: existing DRA methods usually fail to accurately recover the original text of real-world privacy data. In detail, the tokens within a recovery sentence are disordered and intertwined with tokens from other sentences in the same training batch. Moreover, our experiments demonstrate that the performance of DRA is also influenced by different languages and domains. By discovering these findings, our work lays a solid foundation for further research into the development of more practical DRA methods and corresponding defenses.

2023

pdf
Once is Enough: A Light-Weight Cross-Attention for Fast Sentence Pair Modeling
Yuanhang Yang | Shiyi Qi | Chuanyi Liu | Qifan Wang | Cuiyun Gao | Zenglin Xu
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Transformer-based models have achieved great success on sentence pair modeling tasks, such as answer selection and natural language inference (NLI). These models generally perform cross-attention over input pairs, leading to prohibitive computational cost. Recent studies propose dual-encoder and late interaction architectures for faster computation. However, the balance between the expressive of cross-attention and computation speedup still needs better coordinated. To this end, this paper introduces a novel paradigm TopicAns for efficient sentence pair modeling. TopicAns involves a lightweight cross-attention mechanism. It conducts query encoding only once while modeling the query-candidate interaction in parallel. Extensive experiments conducted on four tasks demonstrate that our TopicAnscan speed up sentence pairing by over 113x while achieving comparable performance as the more expensive cross-attention models.

pdf
APrompt: Attention Prompt Tuning for Efficient Adaptation of Pre-trained Language Models
Qifan Wang | Yuning Mao | Jingang Wang | Hanchao Yu | Shaoliang Nie | Sinong Wang | Fuli Feng | Lifu Huang | Xiaojun Quan | Zenglin Xu | Dongfang Liu
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

With the continuous growth of large language models, the process of fine-tuning these models for new tasks has become increasingly parameter-intensive. Prompt tuning, a method that involves tuning a small set of soft prompts, has emerged as an effective and efficient approach for adapting large pre-trained language models. However, most existing prompt tuning approaches only introduce prompts at the input layer, limiting their performance and leaving large rooms for improvement. In this work, we propose a novel Attention Prompt tuning method, namely APrompt, for efficient adaptation of pre-trained language models. We first demonstrate that existing prompt tuning can be considered as a special case of attention prompt tuning. We then formally introduce APrompt, which incorporates query, key, and value prompts into the attention layer to guide the attention computation during fine-tuning. Experimental results on the SuperGLUE benchmark consistently demonstrate that our proposed approach outperforms state-of-the-art baselines and full fine-tuning method with pre-trained models at different scales. In addition, a comprehensive set of ablation studies validate the effectiveness of the prompt design, as well as the efficiency of our approach.

pdf
ViLPAct: A Benchmark for Compositional Generalization on Multimodal Human Activities
Terry Yue Zhuo | Yaqing Liao | Yuecheng Lei | Lizhen Qu | Gerard de Melo | Xiaojun Chang | Yazhou Ren | Zenglin Xu
Findings of the Association for Computational Linguistics: EACL 2023

We introduce ViLPAct, a novel vision-language benchmark for human activity planning. It is designed for a task where embodied AI agents can reason and forecast future actions of humans based on video clips about their initial activities and intents in text. The dataset consists of 2.9k videos from Charades extended with intents via crowdsourcing, a multi-choice question test set, and four strong baselines. One of the baselines implements a neurosymbolic approach based on a multi-modal knowledge base (MKB), while the other ones are deep generative models adapted from recent state-of-the-art (SOTA) methods. According to our extensive experiments, the key challenges are compositional generalization and effective use of information from both modalities.

pdf
FedPETuning: When Federated Learning Meets the Parameter-Efficient Tuning Methods of Pre-trained Language Models
Zhuo Zhang | Yuanhang Yang | Yong Dai | Qifan Wang | Yue Yu | Lizhen Qu | Zenglin Xu
Findings of the Association for Computational Linguistics: ACL 2023

With increasing concerns about data privacy, there is an increasing necessity of fine-tuning pre-trained language models (PLMs) for adapting to downstream tasks located in end-user devices or local clients without transmitting data to the central server. This urgent necessity therefore calls the research of investigating federated learning (FL) for PLMs. However, large PLMs bring the curse of prohibitive communication overhead and local model adaptation costs for the FL system. To this end, we investigate the parameter-efficient tuning (PETuning) of PLMs and develop a corresponding federated benchmark for four representative PETuning methods, dubbed FedPETuning. Specifically, FedPETuning provides the first holistic empirical study of representative PLMs tuning methods in FL, covering privacy attacks, performance comparisons, and resource-constrained analysis. Intensive experimental results have indicated that FedPETuning can efficiently defend against privacy attacks and maintains acceptable performance with reducing heavy resource consumption. The open-source code and data are available at https://github.com/SMILELab-FL/FedPETuning.

pdf
MixPAVE: Mix-Prompt Tuning for Few-shot Product Attribute Value Extraction
Li Yang | Qifan Wang | Jingang Wang | Xiaojun Quan | Fuli Feng | Yu Chen | Madian Khabsa | Sinong Wang | Zenglin Xu | Dongfang Liu
Findings of the Association for Computational Linguistics: ACL 2023

The task of product attribute value extraction is to identify values of an attribute from product information. Product attributes are important features, which help improve online shopping experience of customers, such as product search, recommendation and comparison. Most existing works only focus on extracting values for a set of known attributes with sufficient training data. However, with the emerging nature of e-commerce, new products with their unique set of new attributes are constantly generated from different retailers and merchants. Collecting a large number of annotations for every new attribute is costly and time consuming. Therefore, it is an important research problem for product attribute value extraction with limited data. In this work, we propose a novel prompt tuning approach with Mixed Prompts for few-shot Attribute Value Extraction, namely MixPAVE. Specifically, MixPAVE introduces only a small amount (< 1%) of trainable parameters, i.e., a mixture of two learnable prompts, while keeping the existing extraction model frozen. In this way, MixPAVE not only benefits from parameter-efficient training, but also avoids model overfitting on limited training examples. Experimental results on two product benchmarks demonstrate the superior performance of the proposed approach over several state-of-the-art baselines. A comprehensive set of ablation studies validate the effectiveness of the prompt design, as well as the efficiency of our approach.

pdf
MUSTIE: Multimodal Structural Transformer for Web Information Extraction
Qifan Wang | Jingang Wang | Xiaojun Quan | Fuli Feng | Zenglin Xu | Shaoliang Nie | Sinong Wang | Madian Khabsa | Hamed Firooz | Dongfang Liu
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

The task of web information extraction is to extract target fields of an object from web pages, such as extracting the name, genre and actor from a movie page. Recent sequential modeling approaches have achieved state-of-the-art results on web information extraction. However, most of these methods only focus on extracting information from textual sources while ignoring the rich information from other modalities such as image and web layout. In this work, we propose a novel MUltimodal Structural Transformer (MUST) that incorporates multiple modalities for web information extraction. Concretely, we develop a structural encoder that jointly encodes the multimodal information based on the HTML structure of the web layout, where high-level DOM nodes, and low-level text and image tokens are introduced to represent the entire page. Structural attention patterns are designed to learn effective cross-modal embeddings for all DOM nodes and low-level tokens. An extensive set of experiments are conducted on WebSRC and Common Crawl benchmarks. Experimental results demonstrate the superior performance of MUST over several state-of-the-art baselines.

pdf
FEDLEGAL: The First Real-World Federated Learning Benchmark for Legal NLP
Zhuo Zhang | Xiangjing Hu | Jingyuan Zhang | Yating Zhang | Hui Wang | Lizhen Qu | Zenglin Xu
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

The inevitable private information in legal data necessitates legal artificial intelligence to study privacy-preserving and decentralized learning methods. Federated learning (FL) has merged as a promising technique for multiple participants to collaboratively train a shared model while efficiently protecting the sensitive data of participants. However, to the best of our knowledge, there is no work on applying FL to legal NLP. To fill this gap, this paper presents the first real-world FL benchmark for legal NLP, coined FEDLEGAL, which comprises five legal NLP tasks and one privacy task based on the data from Chinese courts. Based on the extensive experiments on these datasets, our results show that FL faces new challenges in terms of real-world non-IID data. The benchmark also encourages researchers to investigate privacy protection using real-world data in the FL setting, as well as deploying models in resource-constrained scenarios. The code and datasets of FEDLEGAL are available here.

2022

pdf
SMARTAVE: Structured Multimodal Transformer for Product Attribute Value Extraction
Qifan Wang | Li Yang | Jingang Wang | Jitin Krishnan | Bo Dai | Sinong Wang | Zenglin Xu | Madian Khabsa | Hao Ma
Findings of the Association for Computational Linguistics: EMNLP 2022

Automatic product attribute value extraction refers to the task of identifying values of an attribute from the product information. Product attributes are essential in improving online shopping experience for customers. Most existing methods focus on extracting attribute values from product title and description.However, in many real-world applications, a product is usually represented by multiple modalities beyond title and description, such as product specifications, text and visual information from the product image, etc. In this paper, we propose SMARTAVE, a Structure Mltimodal trAnsformeR for producT Attribute Value Extraction, which jointly encodes the structured product information from multiple modalities. Specifically, in SMARTAVE encoder, we introduce hyper-tokens to represent the modality-level information, and local-tokens to represent the original text and visual inputs. Structured attention patterns are designed among the hyper-tokens and local-tokens for learning effective product representation. The attribute values are then extracted based on the learned embeddings. We conduct extensive experiments on two multimodal product datasets. Experimental results demonstrate the superior performance of the proposed approach over several state-of-the-art methods. Ablation studies validate the effectiveness of the structured attentions in modeling the multimodal product information.

pdf
Leveraging Only the Category Name for Aspect Detection through Prompt-based Constrained Clustering
Yazheng Li | Pengyun Wang | Yasheng Wang | Yong Dai | Yadao Wang | Lujia Pan | Zenglin Xu
Findings of the Association for Computational Linguistics: EMNLP 2022

Aspect category detection (ACD) aims to automatically identify user-concerned aspects from online reviews, which is of great value for evaluating the fine-grained performance of a product. The most recent solutions tackle this problem via weakly supervised methods, achieving remarkable improvement over unsupervised methods. However, a closer look at these methods reveals that the required human efforts are nontrivial and can sometimes be hard to obtain. In this study, we explore the possibility of minimizing human guidance while improving detection performance, with a deep clustering method that relies merely on the category name of each aspect and a pretrained language model (LM). The LM, combined with prompt techniques, is employed as a knowledge base to automatically generate constraints for clustering, as well as to provide a representation space to perform the clustering. Our method (1) extracts extensive keywords to expand our understanding of each aspect, (2) automatically generates instance-level and concept-level constraints for clustering, and (3) trains the clustering model with the above constraints. We demonstrate the capability of the proposed framework through extensive experiments on nine benchmark datasets. Our model not only performs noticeably better than existing unsupervised approaches but also considerably surpasses weakly supervised methods that require more human efforts.

pdf
Learning to Generate Question by Asking Question: A Primal-Dual Approach with Uncommon Word Generation
Qifan Wang | Li Yang | Xiaojun Quan | Fuli Feng | Dongfang Liu | Zenglin Xu | Sinong Wang | Hao Ma
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Automatic question generation (AQG) is the task of generating a question from a given passage and an answer. Most existing AQG methods aim at encoding the passage and the answer to generate the question. However, limited work has focused on modeling the correlation between the target answer and the generated question. Moreover, unseen or rare word generation has not been studied in previous works. In this paper, we propose a novel approach which incorporates question generation with its dual problem, question answering, into a unified primal-dual framework. Specifically, the question generation component consists of an encoder that jointly encodes the answer with the passage, and a decoder that produces the question. The question answering component then re-asks the generated question on the passage to ensure that the target answer is obtained. We further introduce a knowledge distillation module to improve the model generalization ability. We conduct an extensive set of experiments on SQuAD and HotpotQA benchmarks. Experimental results demonstrate the superior performance of the proposed approach over several state-of-the-art methods.

pdf
Federated Model Decomposition with Private Vocabulary for Text Classification
Zhuo Zhang | Xiangjing Hu | Lizhen Qu | Qifan Wang | Zenglin Xu
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

With the necessity of privacy protection, it becomes increasingly vital to train deep neural models in a federated learning manner for natural language processing (NLP) tasks. However, recent studies show eavesdroppers (i.e., dishonest servers) can still reconstruct the private input in federated learning (FL). Such a data reconstruction attack relies on the mappings between vocabulary and associated word embedding in NLP tasks, which are unfortunately less studied in current FL methods. In this paper, we propose a fedrated model decomposition method that protects the privacy of vocabularies, shorted as FEDEVOCAB. In FEDEVOCAB, each participant keeps the local embedding layer in the local device and detaches the local embedding parameters from federated aggregation. However, it is challenging to train an accurate NLP model when the private mappings are unknown and vary across participants in a cross-device FL setting. To address this problem, we further propose an adaptive updating technique to improve the performance of local models. Experimental results show that FEDEVOCAB maintains competitive performance and provides better privacy-preserving capacity compared to status quo methods.

2021

pdf
Creating and Evaluating Resources for Sentiment Analysis in the Low-resource Language: Sindhi
Wazir Ali | Naveed Ali | Yong Dai | Jay Kumar | Saifullah Tumrani | Zenglin Xu
Proceedings of the Eleventh Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis

In this paper, we develop Sindhi subjective lexicon using a merger of existing English resources: NRC lexicon, list of opinion words, SentiWordNet, Sindhi-English bilingual dictionary, and collection of Sindhi modifiers. The positive or negative sentiment score is assigned to each Sindhi opinion word. Afterwards, we determine the coverage of the proposed lexicon with subjectivity analysis. Moreover, we crawl multi-domain tweet corpus of news, sports, and finance. The crawled corpus is annotated by experienced annotators using the Doccano text annotation tool. The sentiment annotated corpus is evaluated by employing support vector machine (SVM), recurrent neural network (RNN) variants, and convolutional neural network (CNN).

pdf
SiPOS: A Benchmark Dataset for Sindhi Part-of-Speech Tagging
Wazir Ali | Zenglin Xu | Jay Kumar
Proceedings of the Student Research Workshop Associated with RANLP 2021

In this paper, we introduce the SiPOS dataset for part-of-speech tagging in the low-resource Sindhi language with quality baselines. The dataset consists of more than 293K tokens annotated with sixteen universal part-of-speech categories. Two experienced native annotators annotated the SiPOS using the Doccano text annotation tool with an inter-annotation agreement of 0.872. We exploit the conditional random field, the popular bidirectional long-short-term memory neural model, and self-attention mechanism with various settings to evaluate the proposed dataset. Besides pre-trained GloVe and fastText representation, the character-level representations are incorporated to extract character-level information using the bidirectional long-short-term memory encoder. The high accuracy of 96.25% is achieved with the task-specific joint word-level and character-level representations. The SiPOS dataset is likely to be a significant resource for the low-resource Sindhi language.

2020

pdf
SiNER: A Large Dataset for Sindhi Named Entity Recognition
Wazir Ali | Junyu Lu | Zenglin Xu
Proceedings of the Twelfth Language Resources and Evaluation Conference

We introduce the SiNER: a named entity recognition (NER) dataset for low-resourced Sindhi language with quality baselines. It contains 1,338 news articles and more than 1.35 million tokens collected from Kawish and Awami Awaz Sindhi newspapers using the begin-inside-outside (BIO) tagging scheme. The proposed dataset is likely to be a significant resource for statistical Sindhi language processing. The ultimate goal of developing SiNER is to present a gold-standard dataset for Sindhi NER along with quality baselines. We implement several baseline approaches of conditional random field (CRF) and recent popular state-of-the-art bi-directional long-short term memory (Bi-LSTM) models. The promising F1-score of 89.16 outputted by the Bi-LSTM-CRF model with character-level representations demonstrates the quality of our proposed SiNER dataset.

2019

pdf
Constructing Interpretive Spatio-Temporal Features for Multi-Turn Responses Selection
Junyu Lu | Chenbin Zhang | Zeying Xie | Guang Ling | Tom Chao Zhou | Zenglin Xu
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Response selection plays an important role in fully automated dialogue systems. Given the dialogue context, the goal of response selection is to identify the best-matched next utterance (i.e., response) from multiple candidates. Despite the efforts of many previous useful models, this task remains challenging due to the huge semantic gap and also the large size of candidate set. To address these issues, we propose a Spatio-Temporal Matching network (STM) for response selection. In detail, soft alignment is first used to obtain the local relevance between the context and the response. And then, we construct spatio-temporal features by aggregating attention images in time dimension and make use of 3D convolution and pooling operations to extract matching information. Evaluation on two large-scale multi-turn response selection tasks has demonstrated that our proposed model significantly outperforms the state-of-the-art model. Particularly, visualization analysis shows that the spatio-temporal features enables matching information in segment pairs and time sequences, and have good interpretability for multi-turn text matching.