United States

The pre-training models such as BERT have achieved great results in various natural language processing problems. However, a large number of parameters need significant amounts of memory and the consumption of inference time, which makes it difficult to deploy them on edge devices. In this work, we propose a knowledge distillation method LRC-BERT based on contrastive learning to fit the output of the intermediate layer from the angular distance aspect, which is not considered by the existing distillation methods. Furthermore, we introduce a gradient perturbation-based training architecture in the training phase to increase the robustness of LRC-BERT, which is the first attempt in knowledge distillation. Additionally, in order to better capture the distribution characteristics of the intermediate layer, we design a two-stage training method for the total distillation loss. Finally, by verifying 8 datasets on the General Language Understanding Evaluation (GLUE) benchmark, the performance of the proposed LRC-BERT exceeds the existing state-of-the-art methods, which proves the effectiveness of our method.

AAAI 2021

LRC-BERT: Latent-Representation Contrastive Knowledge Distillation for Natural Language Understanding

### Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Message from the General Chair: 
*It is my great pleasure and honor to welcome you to the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), held in beautiful Vienna, Austria, from July 27 to August 1, 2025. ACL2025continues our field’s tradition of excellence in scholarship, innovation, and inclusivity, and I am deeply grateful to the many volunteers who have worked tirelessly to bring this event to life.* 
[Read more](https://drive.google.com/file/d/1GI_hvOpjswAuYdUTromfeDiPpCcqidwg/view?usp=sharing)

To access this event page, you need to log in with the **email address you registered with**. Access credentials will be sent to your email from Underline - subject line "Welcome to ACL 2025". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you need to log in with the **email address you registered with**. 

ACL 2025

Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

technical paper

The purpose of the AAAI conference is to promote research in artificial intelligence (AI) and scientific exchange among AI researchers, practitioners, scientists, and engineers in affiliated disciplines. 

Automated planning with neural network transition models is a two stage approach to solving planning problems with unknown transition models. The first stage of the approach learns the unknown transition model from data as a neural network model, and the second stage of the approach compiles the learned model to either a Mixed-Integer Linear Programming (MILP) model or a Recurrent Neural Network (RNN) model, and optimize it using an off-the-shelf solver. The previous studies have shown that both models have their advantages and disadvantages. Namely, the MILP model can be solved optimally using a branch-and-bound algorithm but has been experimentally shown not to scale well for neural networks with multiple hidden layers. In contrast, the RNN model can be solved effectively using a gradient descent algorithm but can only work under very restrictive assumptions. In this paper, we focus on improving the effectiveness of solving the second stage of the approach by introducing (i) a novel Lagrangian RNN architecture that can model the previously ignored components of the planning problem as Lagrangian functions, and (ii) a novel framework that unifies the MILP and the Lagrangian RNN models such that the weakness of one model is complemented by the strength of the other. Experimentally, we show that our unifying framework significantly outperforms the standalone MILP model by solving 80% more problem instances, and showcase the ability of our unifying framework to find high quality solutions to challenging automated planning problems with unknown transition models.

A Unified Framework for Planning with Learned Neural Network Transition Models

Pedestrian trajectory prediction is one of the important tasks required for autonomous navigation and social robots in human environments. Previous studies focused on estimating social forces among individual pedestrians. However, they did not consider the social forces of groups on pedestrians, which results in over-collision avoidance problems. To address this problem, we present a Disentangled Multi-Relational Graph Convolutional Network (DMRGCN) for socially entangled pedestrian trajectory prediction. We first introduce a novel disentangled multi-scale aggregation to better represent social interactions, among pedestrians on a weighted graph. For the aggregation, we construct the multi-relational weighted graphs based on distances and relative displacements among pedestrians. In the prediction step, we propose a global temporal aggregation to alleviate accumulated errors for pedestrians changing their directions. Finally, we apply DropEdge into our DMRGCN to avoid the over-fitting issue on relatively small pedestrian trajectory datasets. Through the effective incorporation of the three parts within an end-to-end framework, DMRGCN achieves state-of-the-art performances on a variety of challenging trajectory prediction benchmarks.

Disentangled Multi-Relational Graph Convolutional Network for Pedestrian Trajectory Prediction

Effective emotion inference from user queries helps to give a more personified response for Voice Dialogue Applications(VDAs). The tremendous amounts of VDA users bring in diverse emotion expressions. How to achieve a high emotion inferring performance from large-scale Internet Voice Data in VDAs? Traditionally, researches on speech emotion recognition are based on acted voice datasets, which have limited speakers but strong and clear emotion expressions. Inspired by this, in this paper, we propose a novel approach to leverage acted voice data with strong emotion expressions to enhance large-scale unlabeled internet voice data with diverse emotion expressions for emotion inferring. Specifically, we propose a novel semi-supervised multi-modal curriculum augmentation deep learning framework. First, to learn more general emotion cues, we adopt a curriculum learning based epoch-wise training strategy, which trains our model guided by strong and balanced emotion samples from acted voice data and sub-sequently leverages weak and unbalanced emotion samples from internet voice data.Second, to employ more diverse emotion expressions, we design a Multi-path Mix-match Multimodal Deep Neural Network(MMMD), which effectively learns feature representations for multiple modalities and trains labeled and unlabeled data in hybrid semi-supervised methods for superior generalization and robustness. Experiments on an internet voice dataset with 500,000 utterances show our method outperforms (+10.09% in terms of F1) several alternative baselines,  while an acted corpus with 2,397 utterances contributes 4.35%. To further compare our method with state-of-the-art techniques in traditionally acted voice datasets, we also conduct experiments on public dataset IEMOCAP. The results reveal the effectiveness of the proposed approach.

Inferring Emotion from Large-Scale Internet Voice Data: A Semi-Supervised Curriculum Augmentation Based Deep Learning Approach

Electrocardiogram (ECG) is the electrical measurement of cardiac activity, whereas Photoplethysmogram (PPG) is the optical measurement of volumetric changes in blood circulation. While both signals are used for heart rate monitoring, from a medical perspective, ECG is more useful as it carries additional cardiac information. Despite many attempts toward incorporating ECG sensing in smartwatches or similar wearable devices for continuous and reliable cardiac monitoring, PPG sensors are the main feasible sensing solution available. In order to tackle this problem, we propose CardioGAN, an adversarial model which takes PPG as input and generates ECG as output. The proposed network utilizes an attention-based generator to learn local salient features, as well as dual discriminators to preserve the integrity of generated data in both time and frequency domains. Our experiments show that the ECG generated by CardioGAN provides more reliable heart rate measurements compared to the original input PPG, reducing the error from 9.74 beats per minute (measured from the PPG) to 2.89 (measured from the generated ECG).

CardioGAN: Attentive Generative Adversarial Network with Dual Discriminators for Synthesis of ECG from PPG

Presence of haze in images obscures underlying information, which is undesirable in applications requiring accurate environment information. To recover such an image, a dehazing algorithm should localize and recover affected regions while ensuring consistency between recovered and its neighboring regions. However owing to fixed receptive field of convolutional kernels and non uniform haze distribution, assuring consistency between regions is difficult. In this paper, we utilize an encoder-decoder based network architecture to perform the task of dehazing and integrate an spatially aware channel attention mechanism to enhance features of interest beyond the receptive field of traditional conventional kernels. To ensure performance consistency across diverse range of haze densities, we utilize greedy localized data augmentation mechanism. Synthetic datasets are typically used to ensure a large amount of paired training samples, however the methodology to generate such samples introduces a gap between them and real images while accounting for only uniform haze distribution and overlooking more realistic scenario of non-uniform haze distribution resulting in inferior dehazing performance when evaluated on real datasets. Despite this, the abundance of paired samples within synthetic datasets cannot be ignored. Thus to ensure performance consistency across diverse datasets, we train the proposed network within an adversarial prior-guided framework that relies on a generated image along with its low and high frequency components to determine if properties of dehazed images matches those of ground truth. We preform extensive experiments to validate the dehazing and domain invariance performance of proposed framework across diverse domains and report state-of-the-art (SoTA) results. The source code with pretrained models will be available at https://github.com/PS06/DIDH.

Towards Domain Invariant Single Image Dehazing

This paper deals with the identification problem of causal effects in randomized trials with noncompliance. In this problem, generally, causal effects are not identifiable and thus have been evaluated under some strict assumptions, or through the bounds. Different from existing studies, we propose novel identification conditions of joint probabilities of potential outcomes, which allow us to derive a consistent estimator of the causal effect. Regarding the identification conditions of joint probabilities of potential outcomes, the assumptions of monotonicity (Pearl, 2009), independence between potential outcomes (Robins & Richardson, 2011), gain equality (Li & Pearl, 2019) and specific functional relationships between cause and effect (Pearl, 2009) have been utilized. In contrast, without such assumptions, the proposed conditions enable us to evaluate joint probabilities of potential outcomes using an instrumental variable and a proxy variable of potential outcomes. The results of this paper extend the range of solvable identification problems in causal inference.

Instrumental Variable-Based Identification for Causal Dffects Using Covariate Information

The need to replan arises in many applications. However, in the context of planning as heuristic search, it raises an annoying problem: if the previous plan is still executing, what should the new plan search take as its initial state? If it were possible to accurately predict how long replanning would take, it would be easy to find the appropriate state at which control will transfer from the previous plan to the new one. But as planning problems can vary enormously in their difficulty, this prediction can be difficult. Many current systems merely use a manually chosen constant duration. In this paper, we show how such ad hoc solutions can be avoided by integrating the choice of the appropriate initial state into the search process itself. The search is initialized with multiple candidate initial states and a time-aware evaluation function is used to prefer plans whose total goal achievement time is minimal. Experimental results show that this approach yields better behavior than either guessing a constant or trying to predict replanning time in advance. By making replanning more effective and easier to implement, this work aids in creating planning systems that can better handle the inevitable exigencies of real-world execution.

Choosing the Initial State for Online Replanning

We study fundamental problems in learning nonstationary time-series: how to effectively regularize time-series models and how to adaptively tune forgetting rates.  The effectiveness of L2 regularization depends on the choice of coordinates, and the variables need to be appropriately normalized.  In nonstationary environment, however, what is appropriate can vary over time.  Proposed regularization is invariant to the invertible linear transformation of coordinates, eliminating the necessity of normalization.  We also propose an ensemble learning approach to adaptively tuning the forgetting rate and regularization-coefficient.  We train multiple models with varying hyperparameters and evaluate their performance by the use of multiple hyper forgetting rates.  At each step, we choose the best performing model on the basis of the best performing hyper forgetting rate.  The effectiveness of the proposed approaches is demonstrated with real time-series.

Second Order Techniques for Learning Time-Series with Structural Breaks

Motion segmentation aims at separating motions of different moving objects in a video sequence. Facing the complicated real-world scenes, recent studies reveal that combining multiple geometric models would be a more effective way than just employing a single one. This motivates a new wave of model-fusion based motion segmentation methods. However, the vast majority of models of this kind merely seek consensus in spectral embeddings. We argue that a simple consensus might be insufficient to filter out the harmful information which is either unreliable or semantically unrelated to the segmentation task. Therefore, how to automatically select valuable patterns across multiple models should be regarded as a key challenge here. In this paper, we present a novel geometric-model-fusion framework for motion segmentation, which targets at constructing a consistent affinity matrix across all the geometric models. Specifically, it incorporates the structural information shared by affinity matrices to select those semantically consistent entries. Meanwhile, a multiplicative decomposition scheme is adopted to ensure structural consistency among multiple affinities. To solve this problem, an alternative optimization scheme is proposed, together with a proof of its global convergence. Experiments on four real-world benchmarks show the superiority of the proposed method.

What to Select: Pursuing Consistent Motion Segmentation from Multiple Geometric Models

Most previous works on neural sentence simplification exploit seq2seq model to rewrite a sentence without explicitly considering the semantic information of the sentence. This may lead to the semantic deviation of the simplified sentence. In this paper, we leverage semantic dependency graph to aid neural sentence simplification system. We propose a new sentence simplification model with semantic dependency information, called SDISS (as shorthand for Semantic Dependency Information guided Sentence Simplification), which incorporates semantic dependency graph to guide sentence simplification. We evaluate SDISS on three benchmark datasets and it outperforms a number of strong baseline models on the SARI and FKGL metrics. Human evaluation also shows SDISS can produce simplified sentences with better quality.

Downloads

Next from AAAI 2021

A Unified Framework for Planning with Learned Neural Network Transition Models

Similar lecture

Maximizing the Effectiveness of Larger BERT Models for Compression

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2021

A Unified Framework for Planning with Learned Neural Network Transition Models

Similar lecture

Maximizing the Effectiveness of Larger BERT Models for Compression

Downloads