Yang Shi, Yifeng Xie, Minzhe Guo, Liangsi Lu, Mingxuan Huang, Jingchao Wang, Zhihong Zhu, Boyan Xu, Zhiqi Huang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Repetitive action counting, which aims to count periodic movements in a video, is valuable for video analysis applications such as fitness monitoring. However, existing methods largely rely on regression networks with limited representational capacity, which hampers their ability to accurately capture variable periodic patterns. Additionally, their supervised learning on narrow, limited training sets leads to overfitting and restricts their ability to generalize across diverse scenarios. To address these challenges, we propose CountLLM, the first large language model (LLM)-based framework that takes video data and periodic text prompts as inputs and outputs the desired counting value. CountLLM leverages the rich clues from explicit textual instructions and the powerful representational capabilities of pre-trained LLMs for repetitive action counting. To effectively guide CountLLM, we develop a periodicity-based structured template for instructions that describes the properties of periodicity and implements a standardized answer format to ensure consistency. Additionally, we propose a progressive multimodal training paradigm to enhance the periodicity-awareness of the LLM. Empirical evaluations on widely recognized benchmarks demonstrate CountLLM’s superior performance and generalization, particularly in handling novel and out-of-domain actions that deviate significantly from the training data, offering a promising avenue for repetitive action counting.

Recent state-of-the-art zero-shot cross-lingual spoken language understanding (SLU) models utilize contrastive learning to achieve multilingual semantics alignment between the original utterance and code-switched counterpart. Despite achieving promising results, we discover that they still suffer from two main issues: the neglect of incorporating language-agnostic information into language models and the lack of supervision for extracting fruitful semantics from unpaired samples. To tackle the two issues, we propose Syntax-aware Multi-view Contrastive Learning termed SMCL for zero-shot cross-lingual SLU. In detail, to solve the first issue, we propose a syntax-aware module that incorporates dependency relations and POS tags into multi-lingual language models, thus explicitly leveraging transferable syntax information across different languages. To solve the second issue, we propose multi-view contrastive learning to achieve semantic consistency within and among pairs. Extensive experiments on the benchmark across nine languages show that our SMCL achieves new state-of-the-art performances.

Xianwei Zhuang, Xuxin Cheng, Liming Liang, Yuxin Xie, Zhichang Wang, Zhiqi Huang, Yuexian Zou. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Recent joint models for multi-intent detection and slot filling (a.k.a multi-intent SLU) have obtained promising results by leveraging the semantic similarities or co-occurrence relationships between intent and slot labels. However, a critical aspect frequently neglected by current models is the significant correlations between label co-occurrences and specific scenarios, such as watching a movie or booking a ticket, which is essential for understanding user utterances in multi-intent SLU. In this paper, we propose a new framework dubbed SALA (short for Scenario-aware Label graph interaction), which effectively captures the dynamic co-occurrence relationships among labels across various scenarios, employing a strategy akin to a divide-and-conquer approach. Concretely, SALA first autonomously classifies the scenario of utterances, and tracks the co-occurring labels by maintaining a unique co-occurrence matrix for each scenario during the training phase. These scenario-independent co-occurrence matrices are further employed to guide the interactions among label representations through graph propagation to conduct accurate prediction. Extensive experiments on two multi-intent SLU benchmark datasets demonstrate the superiority of our SALA. More strikingly, SALA also attains competitive results on four extra single-intent and multi-domain SLU benchmark datasets, demonstrating its strong generalizability.

Dialogue-based relation extraction (DRE) aims to determine the semantic relation of a given pair of arguments from a piece of dialogue, which has received increasing attention. Due to the low information density of dialogue text, it is difficult for the model to focus on key information. To this end, in this paper, we propose a Knowledge-Enhanced Prompt-Tuning (KEPT) method to effectively enhance DRE model by exploiting trigger and label semantic. Specifically, we propose two beneficial tasks, masked trigger prediction, and verbalizer representation learning, to effectively inject trigger knowledge and label semantic knowledge respectively. Furthermore, we convert the DRE task to a masked language modeling task to unify the format of knowledge injection and utilization, aiming to better promote DRE performance. Experimental results on the DialogRE dataset show that our KEPT achieves state-of-the-art performance in F1 and F1c scores. Detailed analyses demonstrate the effectiveness and efficiency of our proposed approach. Code is available at https://github.com/blackbookay/KEPT.

In recent years, Multimodal Sentiment Analysis (MSA) leveraging deep learning has demonstrated exceptional performance in a wide range of domains. Its success lies in effectively utilizing information from multiple modalities to analyze sentiments. Despite these advancements, MSA is confronted with two significant challenges. Firstly, each modality often has a surplus of unimportance data, which can overshadow the essential information. Secondly, the crucial cues for sentiment analysis may conflict across different modalities, thereby complicating the analysis process. These issues have a certain impact on the model’s effectiveness in MSA tasks. To address these challenges, this paper introduces a novel method tailored for MSA, termed InfoEnh. This approach utilizes a masking technique as the bottleneck for information filtering, simultaneously maximizing mutual information to retain crucial data. Furthermore, the method integrates all modalities into a common feature space via domain adaptation, which is enhanced by the application of optimal transport. Extensive experiments conducted on two benchmark MSA datasets demonstrate the effectiveness of our proposed approach. Further analyzes indicate significant improvements over the baselines.

Zero-shot Spoken Language Understanding (SLU) aims to enable task-oriented dialogue systems to understand user needs without training data. Challenging but worthwhile, zero-shot SLU reduces the time and effort that data labeling takes. Recent advancements in large language models (LLMs), such as GPT3.5 and ChatGPT, have shown promising results in zero-shot settings, which motivates us to explore prompt-based methods. In this study, we investigate whether strong SLU models can be constructed by directly prompting LLMs. Specifically, we propose a simple yet effective two-stage framework dubbed GPT-SLU, which transforms the SLU task into a question-answering problem. Powered by multi-stage mutual guided prompts, GPT-SLU can leverage the correlations between two subtasks in SLU to achieve better predictions, which is greatly explored in the traditional fine-tuning paradigm. Experimental results on three SLU benchmark datasets demonstrate the significant potential of LLMs for zero-shot SLU. Comprehensive analyses validate the effectiveness of our proposed framework and also indicate that there is still room for further improvement of LLMs in SLU scenarios.

Multi-modal sarcasm detection aims to identify whether a given sample with multi-modal information (i.e., text and image) is sarcastic, which has received increasing attention due to the rapid growth of multi-modal posts on modern social media. However, mainstream models process the input of each modality in a holistic manner, resulting in redundant and unrefined information. Moreover, the representations of different modalities are entangled in one common latent space to perform complex cross-modal interactions, neglecting the heterogeneity and distribution gap of different modalities. To address these issues, we propose a novel framework DMMD (short for Disentangled Multi-grained Multi-modal Distilling) for multi-modal sarcasm detection, which conducts multi-grained knowledge distilling (i.e., intra-subspace and inter-subspace) based on the disentangled multi-modal representations. Concretely, the representations of each modality are disentangled explicitly into modality-agnostic/specific subspaces. Then we transfer cross-modal knowledge by conducting intra-subspace knowledge distilling in a self-adaptive pattern. We also apply mutual learning to regularize the underlying inter-subspace consistency. Extensive experiments on a commonly used benchmark demonstrate the efficacy of our DMMD over cutting-edge methods. More encouragingly, visualization results indicate the multi-modal representations display meaningful distributional patterns, and we hope it will be helpful for the community of multi-modal knowledge transfer.

The visual question localized-answering (VQLA) system has garnered increasing attention due to its potential as a knowledgeable assistant in surgical education. Apart from providing text-based answers, VQLA can also pinpoint the specific region of interest for better surgical scene understanding. Although recent Transformer-based models for VQLA have obtained promising results, they (1) conduct vanilla text-to-image cross attention, leading to unidirectional and coarse-grained alignment; (2) ignore exploiting the semantics of answers to further boost performance. In this paper, we propose a novel model termed OTAS, which first introduces optimal transport to achieve bidirectional and fine-grained alignment between images and questions, enabling more precise localization. Besides, OTAS incorporates a set of learnable candidate answer embeddings to query the probability of each answer class for a given image-question pair. Through Transformer attention, the candidate answer embeddings interact with the fused features of the image-question pair to make the answer decision. Extensive experiments on two widely-used benchmark datasets demonstrate the superiority of our model over state-of-the-art methods.

Multimodal intent detection leverages diverse modalities for a comprehensive understanding of user intentions in real-world scenarios, playing a critical role in modern taskoriented dialogue systems.While existing methods have made progress in modal alignment and fusion, they overlook two vital limitations: (I) Close entanglement of multimodal semantics with modal structures; (II) Insufficient learning of the causal effects of semantic and modality-specific information on final predictions in end-to-end training.To address these limitations, we introduce the Dualoriented Disentangled Network with Counterfactual Intervention (DuoDN).DuoDN consists of a Dual-oriented Disentangled Encoder that decouples semantics-and modality-oriented representations, and a Counterfactual Intervention Module that uses causal inference to understand causal effects by injecting confounders.Experiments on three benchmark datasets demonstrate DuoDN's superiority over existing methods, with extensive analysis validating its advantages.

Continuous learning requires adapting quickly to incoming tasks while avoiding catastrophic forgetting. Typical solutions resort to a rehearsal buffer to replay old data, which is intractable to apply in real-world scenarios with limited memory and inaccessible privacy. Recently, with the emergence of large-scale pre-trained models, prompting methods have rapidly become a popular rehearsal-free alternative to rehearsal-based methods. The core of prmopting is to encode knowledge leveraging a set of parameters, however, knowledge decoupling and complementarity still remain some challenges. To tackle these challenges, this paper presents a KnowledgeComplementary Prompting approach, KC-Prompt, which end-to-end integrates and releases the task-invariant and task-specific knowledge for the ViT backbone. KC-Prompt designs knowledge maintenance and knowledge sharing mechanisms to form complementary prompt generators. In addition, we employ a components weighting method to instantiate prompt generators, making the training process fully differentiable. Sufficient experiments on CIFAR-100 and Split ImageNet-R benchmarks demonstrate the superiority of KC-Prompt in the challenging and realistic class-incremental learning setting.

Talking head generation is a significant research topic that still faces numerous challenges. Previous works often adopt generative adversarial networks or regression models, which are plagued by generation quality and average facial shape problem. Although diffusion models show impressive generative ability, their exploration in talking head generation remains unsatisfactory. This is because they either solely use the diffusion model to obtain an intermediate representation and then employ another pre-trained renderer, or they overlook the feature decoupling of complex facial details, such as expressions, head poses and appearance textures. Therefore, we propose a Facial Decoupled Diffusion model for Talking head generation called FD2Talk, which fully leverages the advantages of diffusion models and decouples the complex facial details through multi-stages. Specifically, we separate facial details into motion and appearance. In the initial phase, we design the Diffusion Transformer to accurately predict motion coefficients from raw audio. These motions are highly decoupled from appearance, making them easier for the network to learn compared to high-dimensional RGB images. Subsequently, in the second phase, we encode the reference image to capture appearance textures. The predicted facial and head motions and encoded appearance then serve as the conditions for the Diffusion UNet, guiding the frame generation. Benefiting from decoupling facial details and fully leveraging diffusion models, extensive experiments substantiate that our approach excels in enhancing image quality and generating more accurate and diverse results compared to previous state-of-the-art methods.

In the field of multi-modal learning, model parameters are typically large, necessitating the use of parameter-efficient fine-tuning (PEFT) techniques. These methods have been pivotal in enhancing training efficiency for downstream tasks in almost all situations. However, directly applying PEFT methods struggles to fully address the intricate demands of multi-modal tasks, such as multi-modal sarcasm detection (MSD), which demands the extraction and comparison of cues from different modalities. MSD, particularly when reliant on textual and visual modalities, faces challenges in identifying sarcasm's incongruity. This issue often arises from the lack of intermodality interaction during tuning, resulting in a disconnect between textual and visual information. In this paper, we introduce a novel approach called Bi-directional Adapter (BA), designated as MoBA. This approach is designed to minimize training parameters while enhancing the model's ability to interpret sarcasm across modalities. By facilitating an exchange between textual and visual information through a low-rank representation, our method adeptly captures the nuances of sarcastic expressions with a reduced number of training parameters. Our empirical studies, carried out on two publicly accessible and emerging datasets, demonstrate that our model substantially improves sarcasm detection accuracy. These findings indicate that our approach provides a more reliable and efficient solution to address the complexities of MSD.

Despite the success of spoken language understanding (SLU) in high-resource languages, achieving similar performance in low-resource settings, such as zero-shot scenarios, remains challenging due to limited labeled training data.To improve zero-shot cross-lingual SLU, recent studies have explored code-switched sentences containing tokens from multiple languages.However, vanilla code-switched sentences often lack semantic and grammatical coherence.We ascribe this lack to two issues: (1) randomly replacing code-switched tokens with equal probability and (2) disregarding token-level dependency within each language.To tackle these issues, in this paper, we propose a novel method termed SOGO, for zero-shot cross-lingual SLU.First, we use a saliency-based substitution approach to extract keywords as substitution options.Then, we introduce a novel token-level alignment strategy that considers the similarity between the context and the code-switched tokens, ensuring grammatical coherence in code-switched sentences.Extensive experiments and analyses demonstrate the superior performance of SOGO across nine languages on MultiATIS++.

Spoken language understanding system (SLU) typically includes two tasks: Intent detection (ID) and Slot filling (SF). Optimizing these two tasks in an interactive way with attention mechanism has been shown effective. However, previous attention-based works leveraged only the first order attention design, which is lacking in efficacy. To trigger more adequate information interaction between the input intent or slot features, we propose a novel framework with Bilinear attention, which can build the second order feature interactions. By stacking numerous Bilinear attention modules and equipping the Exponential Linear Unit activation, it can build higher and infinity order feature interactions. To demonstrate the effectiveness of the proposed framework, we conduct some experiments on two benchmark datasets, i.e., SNIPS and ATIS. And the experimental results show that our framework is more competitive than multiple baselines as well as the first order attention model.

Recently, attention-based models for joint intent detection and slot filling have achieved state-of-the-art performance. However, we think the conventional attention can only capture the first-order feature interaction between two tasks and is insufficient. To address this issue, we propose a unified BiLinear attention block, which leverages bilinear pooling to synchronously explore both the contextual and channel-wise bilinear attention distributions to capture the second-order interactions between the input intent and slot features. Higher-order interactions are constructed by combining many such blocks and exploiting Exponential Linear activations. Furthermore, we present a Higher-order Attention Network (HAN) to jointly model them. The experimental results show that our approach outperforms the state-of-the-art results. We also conduct experiments on the new SLURP dataset, and give a discussion on HAN’s properties, i.e., robustness and generalization.

While Machine Comprehension (MC) has attracted extensive research interests in recent years, existing approaches mainly belong to the category of Machine Reading Comprehension task which mines textual inputs (paragraphs and questions) to predict the answers (choices or text spans). However, there are a lot of MC tasks that accept audio input in addition to the textual input, e.g. English listening comprehension test. In this paper, we target the problem of Audio-Oriented Multimodal Machine Comprehension, and its goal is to answer questions based on the given audio and textual information. To solve this problem, we propose a Dynamic Inter- and Intra-modality Attention (DIIA) model to effectively fuse the two modalities (audio and textual). DIIA can work as an independent component and thus be easily integrated into existing MC models. Moreover, we further develop a Multimodal Knowledge Distillation (MKD) module to enable our multimodal MC model to accurately predict the answers based only on either the text or the audio. As a result, the proposed approach can handle various tasks including: Audio-Oriented Multimodal Machine Comprehension, Machine Reading Comprehension and Machine Listening Comprehension, in a single model, making fair comparisons possible between our model and the existing unimodal MC models. Experimental results and analysis prove the effectiveness of the proposed approaches. First, the proposed DIIA boosts the baseline models by up to 21.08% in terms of accuracy; Second, under the unimodal scenarios, the MKD module allows our multimodal MC model to significantly outperform the unimodal models by up to 18.87%, which are trained and tested with only audio or textual data.

Zhiqi Huang, Lu Hou, Lifeng Shang, Xin Jiang, Xiao Chen, Qun Liu. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Spoken Language Understanding (SLU) is an essential part of the spoken dialogue system, which typically consists of intent detection (ID) and slot filling (SF) tasks. During the conversation, most utterances of people contain rich sentimental information, which is helpful for performing the ID and SF tasks but ignored to be explored by existing works. In this paper, we argue that implicitly introducing sentimental features can promote SLU performance. Specifically, we present a Multitask Learning (MTL) framework to implicitly extract and utilize the aspect-based sentimental text features. Besides, we introduce an Iteratively Co-Interactive Network (ICN) for the SLU task to fully utilize the comprehensive text features. Experimental results show that with the external BERT representation, our framework achieves new state-of-the-art on two benchmark datasets, i.e., SNIPS and ATIS.

Recently, spoken language understanding (SLU) has attracted extensive research interests, and various SLU datasets have been proposed to promote the development.However, most of the existing methods focus on a single individual dataset, the efforts to improve the robustness of models and obtain better performance by combining the merits of various datasets are not well studied.In this paper, we argue that if these SLU datasets are considered together, different knowledge from different datasets could be learned jointly, and there are high chances to promote the performance of each dataset.At the same time, we further attempt to prevent data leakage when unifying multiple datasets which, arguably, is more useful in an industry setting.To this end, we propose a federated learning framework, which could unify various types of datasets as well as tasks to learn and fuse various types of knowledge, i.e., text representations, from different datasets and tasks, without the sharing of downstream task data.The fused text representations merge useful features from different SLU datasets and tasks and are thus much more powerful than the original text representations alone in individual tasks.At last, in order to provide multi-granularity text representations for our framework, we propose a novel Multi-view Encoder (MV-Encoder) as the backbone of our federated learning framework.Experiments on two SLU benchmark datasets, including two tasks (intention detection and slot filling) and federated learning settings (horizontal federated learning, vertical federated learning and federated transfer learning), demonstrate the effectiveness and universality of our approach.Specifically, we are able to get 1.53% improvement on the intent detection metric accuracy.And we could also boost the performance of a strong baseline by up to 5.29% on the slot filling metric F1.Furthermore, by leveraging BERT as an additional encoder, we establish new state-of-the-art results on SNIPS and ATIS datasets, where we get 99.33% and 98.28% in terms of accuracy on intent detection task as well as 97.20% and 96.41% in terms of F1 score on slot filling task, respectively.

Spoken Language Understanding (SLU) is an essential part of the spoken dialogue system, which typically consists of intent detection (ID) and slot filling (SF) tasks. Recently, recurrent neural networks (RNNs) based methods achieved the state-of-the-art for SLU. It is noted that, in the existing RNN-based approaches, ID and SF tasks are often jointly modeled to utilize the correlation information between them. However, we noted that, so far, the efforts to obtain better performance by supporting bidirectional and explicit information exchange between ID and SF are not well studied. In addition, few studies attempt to capture the local context information to enhance the performance of SF. Motivated by these findings, in this paper, Parallel Interactive Network (PIN) is proposed to model the mutual guidance between ID and SF. Specifically, given an utterance, a Gaussian self-attentive encoder is introduced to generate the context-aware feature embedding of the utterance which is able to capture local context information. Taking the feature embedding of the utterance, Slot2Intent module and Intent2Slot module are developed to capture the bidirectional information flow for ID and SF tasks. Finally, a cooperation mechanism is constructed to fuse the information obtained from Slot2Intent and Intent2Slot modules to further reduce the prediction bias. The experiments on two benchmark datasets, i.e., SNIPS and ATIS, demonstrate the effectiveness of our approach, which achieves a competitive result with state-of-the-art models. More encouragingly, by using the feature embedding of the utterance generated by the pre-trained language model BERT, our method achieves the state-of-the-art among all comparison approaches.

The pre-trained language models like BERT, though powerful in many natural language processing tasks, are both computation and memory expensive. To alleviate this problem, one approach is to compress them for specific tasks before deployment. However, recent works on BERT compression usually compress the large BERT model to a fixed smaller size, and can not fully satisfy the requirements of different edge devices with various hardware performances. In this paper, we propose a novel dynamic BERT model (abbreviated as DynaBERT), which can flexibly adjust the size and latency by selecting adaptive width and depth. The training process of DynaBERT includes first training a width-adaptive BERT and then allowing both adaptive width and depth, by distilling knowledge from the full-sized model to small sub-networks. Network rewiring is also used to keep the more important attention heads and neurons shared by more sub-networks. Comprehensive experiments under various efficiency constraints demonstrate that our proposed dynamic BERT (or RoBERTa) at its largest size has comparable performance as BERT-base (or RoBERTa-base), while at smaller widths and depths consistently outperforms existing BERT compression methods. Code is available at https://github.com/huawei-noah/Pretrained-Language-Model/tree/master/DynaBERT.