arXiv subjects

Albert Y. S. Lam

Publications and source records attributed to Albert Y. S. Lam.

At least 19 recordsLinked to original sources

arXiv2025

New Intent Discovery with Pre-training and Contrastive Learning

New intent discovery aims to uncover novel intent categories from user utterances to expand the set of supported intent classes. It is a critical task for the development and service expansion of a practical dialogue system. Despite its importance, this problem remains under-explored in the literature. Existing approaches typically rely on a large amount of labeled utterances and employ pseudo-labeling methods for representation learning and clustering, which are label-intensive, inefficient, and inaccurate. In this paper, we provide new solutions to two important research questions for new intent discovery: (1) how to learn semantic utterance representations and (2) how to better cluster utterances. Particularly, we first propose a multi-task pre-training strategy to leverage rich unlabeled data along with external labeled data for representation learning. Then, we design a new contrastive loss to exploit self-supervisory signals in unlabeled data for clustering. Extensive experiments on three intent recognition benchmarks demonstrate the high effectiveness of our proposed method, which outperforms state-of-the-art methods by a large margin in both unsupervised and semi-supervised scenarios. The source code will be available at https://github.com/zhang-yu-wei/MTP-CLNN.

cs.CL↗

arXiv2024

Continual Dialogue State Tracking via Reason-of-Select Distillation

An ideal dialogue system requires continuous skill acquisition and adaptation to new tasks while retaining prior knowledge. Dialogue State Tracking (DST), vital in these systems, often involves learning new services and confronting catastrophic forgetting, along with a critical capability loss termed the "Value Selection Quandary." To address these challenges, we introduce the Reason-of-Select (RoS) distillation method by enhancing smaller models with a novel 'meta-reasoning' capability. Meta-reasoning employs an enhanced multi-domain perspective, combining fragments of meta-knowledge from domain-specific dialogues during continual learning. This transcends traditional single-perspective reasoning. The domain bootstrapping process enhances the model's ability to dissect intricate dialogues from multiple possible values. Its domain-agnostic property aligns data distribution across different domains, effectively mitigating forgetting. Additionally, two novel improvements, "multi-value resolution" strategy and Semantic Contrastive Reasoning Selection method, significantly enhance RoS by generating DST-specific selection chains and mitigating hallucinations in teachers' reasoning, ensuring effective and reliable knowledge transfer. Extensive experiments validate the exceptional performance and robust generalization capabilities of our method. The source code is provided for reproducibility.

cs.CL↗

arXiv2024

Diversity-grounded Channel Prototypical Learning for Out-of-Distribution Intent Detection

In the realm of task-oriented dialogue systems, a robust intent detection mechanism must effectively handle malformed utterances encountered in real-world scenarios. This study presents a novel fine-tuning framework for large language models (LLMs) aimed at enhancing in-distribution (ID) intent classification and out-of-distribution (OOD) intent detection, which utilizes semantic matching with prototypes derived from ID class names. By harnessing the highly distinguishable representations of LLMs, we construct semantic prototypes for each ID class using a diversity-grounded prompt tuning approach. We rigorously test our framework in a challenging OOD context, where ID and OOD classes are semantically close yet distinct, referred to as \emph{near} OOD detection. For a thorough assessment, we benchmark our method against the prevalent fine-tuning approaches. The experimental findings reveal that our method demonstrates superior performance in both few-shot ID intent classification and near-OOD intent detection tasks.

cs.CL↗

arXiv2024

Effectiveness of Pre-training for Few-shot Intent Classification

This paper investigates the effectiveness of pre-training for few-shot intent classification. While existing paradigms commonly further pre-train language models such as BERT on a vast amount of unlabeled corpus, we find it highly effective and efficient to simply fine-tune BERT with a small set of labeled utterances from public datasets. Specifically, fine-tuning BERT with roughly 1,000 labeled data yields a pre-trained model -- IntentBERT, which can easily surpass the performance of existing pre-trained models for few-shot intent classification on novel domains with very different semantics. The high effectiveness of IntentBERT confirms the feasibility and practicality of few-shot intent detection, and its high generalization ability across different domains suggests that intent classification tasks may share a similar underlying structure, which can be efficiently learned from a small set of labeled data. The source code can be found at https://github.com/hdzhang-code/IntentBERT.

cs.CL↗

arXiv2024

Fine-tuning Pre-trained Language Models for Few-shot Intent Detection: Supervised Pre-training and Isotropization

It is challenging to train a good intent classifier for a task-oriented dialogue system with only a few annotations. Recent studies have shown that fine-tuning pre-trained language models with a small amount of labeled utterances from public benchmarks in a supervised manner is extremely helpful. However, we find that supervised pre-training yields an anisotropic feature space, which may suppress the expressive power of the semantic representations. Inspired by recent research in isotropization, we propose to improve supervised pre-training by regularizing the feature space towards isotropy. We propose two regularizers based on contrastive learning and correlation matrix respectively, and demonstrate their effectiveness through extensive experiments. Our main finding is that it is promising to regularize supervised pre-training with isotropization to further improve the performance of few-shot intent detection. The source code can be found at https://github.com/fanolabs/isoIntentBert-main.

cs.CL↗

arXiv2024

Revisit Few-shot Intent Classification with PLMs: Direct Fine-tuning vs. Continual Pre-training

We consider the task of few-shot intent detection, which involves training a deep learning model to classify utterances based on their underlying intents using only a small amount of labeled data. The current approach to address this problem is through continual pre-training, i.e., fine-tuning pre-trained language models (PLMs) on external resources (e.g., conversational corpora, public intent detection datasets, or natural language understanding datasets) before using them as utterance encoders for training an intent classifier. In this paper, we show that continual pre-training may not be essential, since the overfitting problem of PLMs on this task may not be as serious as expected. Specifically, we find that directly fine-tuning PLMs on only a handful of labeled examples already yields decent results compared to methods that employ continual pre-training, and the performance gap diminishes rapidly as the number of labeled data increases. To maximize the utilization of the limited available data, we propose a context augmentation method and leverage sequential self-distillation to boost performance. Comprehensive experiments on real-world benchmarks show that given only two or more labeled samples per class, direct fine-tuning outperforms many strong baselines that utilize external data sources for continual pre-training. The code can be found at https://github.com/hdzhang-code/DFTPlus.

cs.CL↗

arXiv2024

Minimizing PLM-Based Few-Shot Intent Detectors

Recent research has demonstrated the feasibility of training efficient intent detectors based on pre-trained language model~(PLM) with limited labeled data. However, deploying these detectors in resource-constrained environments such as mobile devices poses challenges due to their large sizes. In this work, we aim to address this issue by exploring techniques to minimize the size of PLM-based intent detectors trained with few-shot data. Specifically, we utilize large language models (LLMs) for data augmentation, employ a cutting-edge model compression method for knowledge distillation, and devise a vocabulary pruning mechanism called V-Prune. Through these approaches, we successfully achieve a compression ratio of 21 in model memory usage, including both Transformer and the vocabulary, while maintaining almost identical performance levels on four real-world benchmarks.

cs.CL↗

arXiv2022

Two-Stage Auction Mechanism for Long-Term Participation in Crowdsourcing

Crowdsourcing has become an important tool to collect data for various artificial intelligence applications and auction can be an effective way to allocate work and determine reward in a crowdsourcing platform. In this paper, we focus on the crowdsourcing of small tasks such as image labelling and voice recording where we face a number of challenges. First, workers have different limits on the amount of work they would be willing to do, and they may also misreport these limits in their bid for work. Secondly, if the auction is repeated over time, unsuccessful workers may drop out of the system, reducing competition and diversity. To tackle these issues, we first extend the results of the celebrated Myerson's optimal auction mechanism for a single-parameter bid to the case where the bid consists of the unit cost of work, the maximum amount of work one is willing to do, and the actual work completed. We show that a simple payment mechanism is sufficient to ensure a dominant strategy from the workers, and that this dominant strategy is robust to the true utility function of the workers. Secondly, we propose a novel, flexible work allocation mechanism, which allows the requester to balance between cost efficiency and equality. While cost minimization is obviously important, encouraging equality in the allocation of work increases the diversity of the workforce as well as promotes long-term participation on the crowdsourcing platform. Our main results are proved analytically and validated through simulations.

cs.GT↗

arXiv2021

Out-of-Scope Intent Detection with Self-Supervision and Discriminative Training

Out-of-scope intent detection is of practical importance in task-oriented dialogue systems. Since the distribution of outlier utterances is arbitrary and unknown in the training stage, existing methods commonly rely on strong assumptions on data distribution such as mixture of Gaussians to make inference, resulting in either complex multi-step training procedures or hand-crafted rules such as confidence threshold selection for outlier detection. In this paper, we propose a simple yet effective method to train an out-of-scope intent classifier in a fully end-to-end manner by simulating the test scenario in training, which requires no assumption on data distribution and no additional post-processing or threshold setting. Specifically, we construct a set of pseudo outliers in the training stage, by generating synthetic outliers using inliner features via self-supervision and sampling out-of-scope sentences from easily available open-domain datasets. The pseudo outliers are used to train a discriminative classifier that can be directly applied to and generalize well on the test task. We evaluate our method extensively on four benchmark dialogue datasets and observe significant improvements over state-of-the-art approaches. Our code has been released at https://github.com/liam0949/DCLOOS.

cs.CL↗

arXiv2020

Chance-Constrained OPF in Droop-Controlled Microgrids with Power Flow Routers

High penetration of renewable generation poses great challenge to power system operation due to its uncertain nature. In droop-controlled microgrids, the voltage volatility induced by renewable uncertainties is aggravated by the high droop gains. This paper proposes a chance-constrained optimal power flow (CC-OPF) problem with power flow routers (PFRs) to better regulate the voltage profile in microgrids. PFR refer to a general type of network-side controller that brings more flexibility to the power network. Comparing with the normal CC-OPF that relies on power injection flexibility only, the proposed model introduces a new dimension of control from power network to enhance system performance under renewable uncertainties. Since the inclusion of PFRs complicates the problem and makes common solvers no longer apply directly, we design an iterative solution algorithm. For the subproblem in each iteration, chance constraints are transformed into equivalent deterministic ones via sensitivity analysis, so that the subproblem can be efficiently solved by the convex relaxation method. The proposed method is verified on the modified IEEE 33-bus system and the results show that PFRs make a significant contribution to mitigating the voltage volatility and make the system operate in a more economic and secure way.

eess.SY↗

arXiv2020

Robust Transient Stability Constrained Optimal Power Flow with Power Flow Routers Considering Renewable Uncertainties

This paper proposes a robust transient stability constrained optimal power flow problem that addresses renewable uncertainties by the coordination of generation re-dispatch and power flow router (PFR) tuning.PFR refers to a general type of network-side controller that enlarges the feasible region of the OPF problem. The coordination between network-side and generator-side control in the proposed model is more general than the traditional methods which focus on generation dispatch only. An offline-online solution framework is developed to solve the problem efficiently. Under this framework the original problem is significantly simplified, so that we only need to solve a low-dimensional deterministic problem at the online stage to achieve real-time implementation with a high robustness level. The proposed method is verified on the modified New England 39-bus system. Numerical results demonstrate that the proposed method is efficient and shows good performance on economy and robustness.

eess.SY↗

arXiv2020

Reducing BESS Capacity for Accommodating Renewables in Subtransmission Systems with Power Flow Routers

Widespread utilization of renewable energy sources (RESs) in subtransmission systems causes serious problems on power quality, such as voltage violations, leading to significant curtailment of renewables. This is due to the inherent variability of renewables and the high R/X ratio of the subtransmission system. To achieve full utilization of renewables, battery energy storage systems (BESSs) are commonly used to mitigate the negative effects of massive fluctuations of RESs. Power flow router (PFR), which can be regarded as a general type of network-side controller, has also been verified to enhance the grid flexibility for accommodating renewables. In this paper, we investigate the value of PFR in helping BESSs for renewable power accommodation. The performance of PFR is evaluated with the minimum BESS capacity required for zero renewable power curtailment with and without PFRs. The operational constraints of BESSs and the terminal voltage property of PFRs are considered in a multi-period optimization model. The proposed model is tested through numerical simulations on a modified IEEE 30-bus subtransmission system and a remarkable result shows that 15% reduction of BESS capacity can be achieved by installing PFRs on a single line.

eess.SY↗

arXiv2017

A Unified Framework for Wide Area Measurement System Planning

Wide area measurement system (WAMS) is one of the essential components in the future power system. To make WAMS construction plans, practical models of the power network observability, reliability, and underlying communication infrastructures need to be considered. To address this challenging problem, in this paper we propose a unified framework for WAMS planning to cover most realistic concerns in the construction process. The framework jointly optimizes the system construction cost, measurement reliability, and volume of synchrophasor data traffic resulting in a multi-objective optimization problem, which provides multiple Pareto optimal solutions to suit different requirements by the utilities. The framework is verified on two IEEE test systems. The simulation results demonstrate the trade-off relationships among the proposed objectives. Moreover, the proposed framework can develop optimal WAMS plans for full observability with minimal cost. This work develops a comprehensive framework for most practical WAMS construction designs.

eess.SY↗

arXiv2017

Delay Aware Intelligent Transient Stability Assessment System

Transient stability assessment is a critical tool for power system design and operation. With the emerging advanced synchrophasor measurement techniques, machine learning methods are playing an increasingly important role in power system stability assessment. However, most existing research makes a strong assumption that the measurement data transmission delay is negligible. In this paper, we focus on investigating the influence of communication delay on synchrophasor-based transient stability assessment. In particular, we develop a delay aware intelligent system to address this issue. By utilizing an ensemble of multiple long short-term memory networks, the proposed system can make early assessments to achieve a much shorter response time by utilizing incomplete system variable measurements. Compared with existing work, our system is able to make accurate assessments with a significantly improved efficiency. We perform numerous case studies to demonstrate the superiority of the proposed intelligent system, in which accurate assessments can be developed with time one third less than state-of-the-art methodologies. Moreover, the simulations indicate that noise in the measurements has trivial impact on the assessment performance, demonstrating the robustness of the proposed system.

eess.SY↗

arXiv2017

Intelligent Time-Adaptive Transient Stability Assessment System

Online identification of post-contingency transient stability is essential in power system control, as it facilitates the grid operator to decide and coordinate system failure correction control actions. Utilizing machine learning methods with synchrophasor measurements for transient stability assessment has received much attention recently with the gradual deployment of wide-area protection and control systems. In this paper, we develop a transient stability assessment system based on the long short-term memory network. By proposing a temporal self-adaptive scheme, our proposed system aims to balance the trade-off between assessment accuracy and response time, both of which may be crucial in real-world scenarios. Compared with previous work, the most significant enhancement is that our system learns from the temporal data dependencies of the input data, which contributes to better assessment accuracy. In addition, the model structure of our system is relatively less complex, speeding up the model training process. Case studies on three power systems demonstrate the efficacy of the proposed transient stability assessment system.

eess.SY↗

arXiv2017

Coordinated Electric Vehicle Charging Control with Aggregator Power Trading and Indirect Load Control

Due to the increasing concern for greenhouse gas emissions and fossil fuel security, electric vehicles (EVs) have attracted much attention in recent years. EVs can aggregate together constituting the vehicle-to-grid system. Coordination of EVs is beneficial to the power system in many ways. In this paper, we formulate a novel large-scale EV charging problem with energy trading in order to maximize the aggregator profit. This problem is non-convex and can be solved with a centralized iterative approach. To overcome the computation complexity issue brought by the non-convexity, we develop a distributed optimization-based heuristic. To evaluate our proposed approach, a modified IEEE 118 bus testing system is employed with 10 aggregators serving 30 000 EVs. The simulation results indicate that our proposed distributed heuristic with energy trading can effectively increase the total profit of aggregators. In addition, the proposed distributed optimization-based heuristic strategy can achieve near-optimal performance.

eess.SY↗

arXiv2017

Coordinated Autonomous Vehicle Parking for Vehicle-to-Grid Services: Formulation and Distributed Algorithm

Autonomous vehicles (AVs) will revolutionarize ground transport and take a substantial role in the future transportation system. Most AVs are likely to be electric vehicles (EVs) and they can participate in the vehicle-to-grid (V2G) system to support various V2G services. Although it is generally infeasible for EVs to dictate their routes, we can design AV travel plans to fulfill certain system-wide objectives. In this paper, we focus on the AVs looking for parking and study how they can be led to appropriate parking facilities to support V2G services. We formulate the Coordinated Parking Problem (CPP), which can be solved by a standard integer linear program solver but requires long computational time. To make it more practical, we develop a distributed algorithm to address CPP based on dual decomposition. We carry out a series of simulations to evaluate the proposed solution methods. Our results show that the distributed algorithm can produce nearly optimal solutions with substantially less computational time. A coarser time scale can improve computational time but degrade the solution quality resulting in possible infeasible solution. Even with communication loss, the distributed algorithm can still perform well and converge with only little degradation in speed.

eess.SY↗

arXiv2017

Vehicular Energy Network

The smart grid spawns many innovative ideas, but many of them cannot be easily integrated into the existing power system due to power system constraints, such as the lack of capacity to transport renewable energy in remote areas to the urban centers. An energy delivery system can be built upon the traffic network and electric vehicles (EVs) utilized as energy carriers to transport energy over a large geographical region. A generalized architecture called the vehicular energy network (VEN) is constructed and a mathematically tractable framework is developed. Dynamic wireless (dis)charging allows electric energy, as an energy packet, to be added and subtracted from EV batteries seamlessly. With proper routing, energy can be transported from the sources to destinations through EVs along appropriate vehicular routes. This paper gives a preliminary study of VEN. Models are developed to study its operational and economic feasibilities with real traffic data in the United Kingdom. Our study shows that a substantial amount of renewable energy can be transported from some remote wind farms to London under some reasonable settings and VEN is likely to be profitable in the near future. VEN can complement the power network and enhance its power delivery capability.

eess.SY↗