Pre-trained language models (PLMs) that rely solely on textual data may exhibit limitations in multimodal semantics comprehension. Existing solutions attempt to alleviate this issue by incorporating explicit image retrieval or generation techniques.However, these methods: (1) focus exclusively on the static image modality; (2) inevitably encounter modality gaps and noise; (3) indiscriminately treat all modalities.In this paper, we propose a novel multimodal-augmented framework termed MaCSC, which can infuse multimodal semantics into PLMs and facilitate a self-balancing calibration of information allocation.Specifically, MaCSC obtains modal-specific conceptual prototypes from contrastive pre-training models (e.g., CLIP),and aggregates the intra- and inter-modal semantics of the conceptual prototype to enhance PLMs.In addition, we utilize a novel self-balancing contrastive loss to achieve multi-scale self-balancing calibration of multimodal information during fine-tuning PLMs.Experimental results show that MaCSC consistently improves the performance of PLMs across various architectures and scales, and outperforms competitive baselines on multiple NLP tasks.

Owing to the scarcity of labeled training data, Spoken Language Understanding (SLU) is still a challenging task in low-resource languages. Therefore, zero-shot cross-lingual SLU attracts more and more attention. Contrastive learning is widely applied to explicitly align representations of similar sentences across different languages. However, the vanilla contrastive learning method may face two problems in zero-shot cross-lingual SLU: (1) the consistency between different languages is neglected; (2) each utterance has two different kinds of SLU labels, i.e. slot and intent, the utterances with one different label are also pushed away without any discrimination, which limits the performance. In this paper, we propose Cyclical Contrastive Learning based on Geodesic (CCLG), which introduces cyclical contrastive learning to achieve the consistency between different languages and leverages geodesic to measure the similarity to construct the positive pairs and negative pairs. Experimental results demonstrate that our proposed framework achieves the new state-of-the-art performance on MultiATIS++ and MTOP datasets, and the model analysis further verifies that CCLG can effectively transfer knowledge between different languages.

As a crucial task in the task-oriented dialogue systems, spoken language understanding (SLU) has garnered increasing attention. However, errors from automatic speech recognition (ASR) often hinder the performance of understanding. To tackle this problem, we propose MoE-SLU, an ASR-Robust SLU framework based on the mixture-of-experts technique. Specifically, we first introduce three strategies to generate additional transcripts from clean transcripts. Then, we employ the mixture-of-experts technique to weigh the representations of the generated transcripts, ASR transcripts, and the corresponding clean manual transcripts. Additionally, we also regularize the weighted average of predictions and the predictions of ASR transcripts by minimizing the Jensen-Shannon Divergence (JSD) between these two output distributions. Experiment results on three benchmark SLU datasets demonstrate that our MoE-SLU achieves state-of-the-art performance. Further model analysis also verifies the superiority of our method.

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.

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.

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.

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.

Spoken language understanding (SLU) inevitably suffers from error propagation from automatic speech recognition (ASR) in actual scenarios. Some recent works attempt to alleviate this issue through contrastive learning. However, they (1) sample negative pairs incorrectly in pre-training; (2) only focus on implicit metric learning while neglecting explicit erroneous predictions; (3) treat manual and ASR transcripts indiscriminately. In this paper, we propose a novel framework termed PCAD, which can calibrate bias and errors and achieve adaptive-balanced decoupling training. Specifically, PCAD utilizes a prototype-based loss to aggregate label and prediction priors and calibrate bias and error-prone semantics for better inter-class discrimination and intra-class consistency. We theoretically analyze the effect of this loss on robustness enhancement. Further, we leverage a teacher-student model for asymmetric decoupling training between different transcripts and formulate a novel gradient-sensitive exponential moving averaging (GS-EMA) algorithm for adaptive balance of accuracy and robustness. Experiments on three datasets show that PCAD significantly outperforms existing approaches and achieves new state-of-the-art performance.

Dialogue State Tracking (DST) is designed to monitor the evolving dialogue state in the conversations and plays a pivotal role in developing task-oriented dialogue systems. However, obtaining the annotated data for the DST task is usually a costly endeavor. In this paper, we focus on employing LLMs to generate dialogue data to reduce dialogue collection and annotation costs. Specifically, GPT-4 is used to simulate the user and agent interaction, generating thousands of dialogues annotated with DST labels. Then a two-stage fine-tuning on LLaMA 2 is performed on the generated data and the real data for the DST prediction. Experimental results on two public DST benchmarks show that with the generated dialogue data, our model performs better than the baseline trained solely on real data. In addition, our approach is also capable of adapting to the dynamic demands in real-world scenarios, generating dialogues in new domains swiftly. After replacing dialogue segments in any domain with the corresponding generated ones, the model achieves comparable performance to the model trained on real data. The source code and generated dialogue data are available at https://github.com/ParticleMedia/LUAS.

Multimodal machine translation (MMT) aims to improve the performance of machine translation with the help of visual information, which has received widespread attention recently. It has been verified that visual information brings greater performance gains when the textual information is limited. However, most previous works ignore to take advantage of the complete textual inputs and the limited textual inputs at the same time, which limits the overall performance. To solve this issue, we propose a mixup method termed Soul-Mix to enhance MMT by using visual information more effectively. We mix the predicted translations of complete textual input and the limited textual inputs. Experimental results on the Multi30K dataset of three translation directions show that our Soul-Mix significantly outperforms existing approaches and achieves new state-of-the-art performance with fewer parameters than some previous models. Besides, the strength of Soul-Mix is more obvious on more challenging MSCOCO dataset which includes more out-of-domain instances with lots of ambiguous verbs.

Zero-shot cross-lingual spoken language understanding (SLU) can promote the globalization application of dialog systems, which has attracted increasing attention. While current code-switching based cross-lingual SLU frameworks have shown promising results, they (i) predominantly utilize contrastive objectives to model hard alignment, which may disrupt the inherent structure within sentences of each language; and (ii) focus optimization objectives solely on the original sentences, neglecting the relation between original sentences and code-switched sentences, which may hinder contextualized embeddings from further alignment. In this paper, we propose a novel framework dubbed REPE (short for Representation-Level and Prediction-Level Alignment), which leverages both code-switched and original sentences to achieve multi-level alignment. Specifically, REPE introduces optimal transport to facilitate soft alignment between the representations of code-switched and original sentences, thereby preserving structural integrity as much as possible. Moreover, REPE adopts multi-view learning to enforce consistency regularization between the prediction of the two sentences, aligning them into a more refined language-invariant space. Based on this, we further incorporate a self-distillation layer to boost the robustness of REPE. Extensive experiments on two benchmarks across ten languages demonstrate the superiority of the proposed REPE framework.

Spoken language understanding (SLU) is a fundamental task in the task-oriented dialogue systems. However, the inevitable errors from automatic speech recognition (ASR) usually impair the understanding performance and lead to error propagation. Although there are some attempts to address this problem through contrastive learning, they (1) treat clean manual transcripts and ASR transcripts equally without discrimination in fine-tuning; (2) neglect the fact that the semantically similar pairs are still pushed away when applying contrastive learning; (3) suffer from the problem of Kullback–Leibler (KL) vanishing. In this paper, we propose Mutual Learning and Large-Margin Contrastive Learning (ML-LMCL), a novel framework for improving ASR robustness in SLU. Specifically, in fine-tuning, we apply mutual learning and train two SLU models on the manual transcripts and the ASR transcripts, respectively, aiming to iteratively share knowledge between these two models. We also introduce a distance polarization regularizer to avoid pushing away the intra-cluster pairs as much as possible. Moreover, we use a cyclical annealing schedule to mitigate KL vanishing issue. Experiments on three datasets show that ML-LMCL outperforms existing models and achieves new state-of-the-art performance.

Joint intent detection and slot filling models have shown promising success in recent years due to the high correlations between the two tasks. However, previous works independently decode the two tasks, which could result in misaligned predictions for both tasks. To address this shortcoming, we propose a novel method named Label-aware Compact Linguistics Representation (LCLR), which leverages label embeddings to jointly guide the decoding process. Concretely, LCLR projects both task-specific hidden states into a joint label latent space, where both task-specific hidden states could be concisely represented as linear combinations of label embeddings. Such feature decomposition of task-specific hidden states increases the representing power for the linguistics of utterance. Extensive experiments on two single- and multi-intent SLU benchmarks prove that LCLR can learn more discriminative label information than previous separate decoders, and consistently outperform previous state-of-the-art methods across all metrics. More encouragingly, LCLR can be applied to boost the performance of existing approaches, making it easy to be incorporated into any existing SLU models.

Enhancing the robustness towards Automatic Speech Recognition (ASR) errors is of great importance for Spoken Language Understanding (SLU). Trending ASR-robust SLU systems have witnessed impressive improvements through global contrastive learning. However, although most ASR errors occur only at local positions of utterances, they can easily lead to severe semantic changes, and utterance-level classification or comparison is difficult to distinguish such differences. To address the problem, we propose a two-stage multi-grained contrastive learning framework dubbed MCLF. Technically, we first adapt the pre-trained language models to downstream SLU datasets via the proposed multi-grained contrastive learning objective and then fine-tune it on the corresponding dataset. Besides, to facilitate contrastive learning in the pre-training stage, we explore several data augmentation methods to expand the training data. Experimental results and detailed analyses on four datasets and four BERT-like backbone models demonstrate the effectiveness of our approach.

Recent non-autoregressive Spoken Language Understanding (SLU) models have attracted increasing attention because of their encouraging inference speed. However, most of existing methods (1) suffer from the multi-modality problem since they have little prior knowledge about the reference during inference; (2) fail to achieve a satisfactory inference speed limited by their complex frameworks. To tackle these issues, in this paper, we propose a Targeted Knowledge Distillation Framework (TKDF) for multi-intent SLU, which utilizes the knowledge distillation method to improve the performance. Specifically, we first train an SLU model as the teacher model, which has higher accuracy while slower inference speed. Then we introduce an evaluator and apply a curriculum learning strategy to select proper targets for the student model. Experiment results on two public multi-intent datasets show that our approach can realize a flexible trade-off between inference speed and accuracy, achieving comparable performance to the state-of-the-art models while speeding up by over 4.5 times. More encouragingly, further analysis shows that distilling only 4% of the original data can help the student model outperform its counterpart trained on the original data by about 14.6% in terms of overall accuracy on MixATIS dataset.

With the rise of non-autoregressive approach, some non-autoregressive models for joint multiple intent detection and slot filling have obtained the promising inference speed. However, most existing SLU models (1) suffer from the multi-modality problem that leads to reference intents and slots may not be suitable for training; (2) lack of alignment between the correct predictions of the two tasks, which extremely limits the overall accuracy. Therefore, in this paper, we propose Modifying the Reference via Reinforcement Learning (MRRL), a novel method for multiple intent detection and slot filling, which introduces a modifier and employs reinforcement learning. Specifically, we try to provide the better training target for the non-autoregressive SLU model via modifying the reference based on the output of the non-autoregressive SLU model, and propose a suitability reward to ensure that the output of the modifier module could fit well with the output of the non-autoregressive SLU model and does not deviate too far from the reference. In addition, we also propose a compromise reward to realize a flexible trade-off between the two subtasks. Experiments on two multi-intent datasets and non-autoregressive baselines demonstrate that our MRRL could consistently improve the performance of baselines. More encouragingly, our best variant achieves new state-of-the-art results, outperforming the previous best approach by 3.6 overall accuracy on MixATIS dataset.

Spoken Language Understanding (SLU), a crucial component of task-oriented dialogue systems, has consistently garnered attention from both academic and industrial communities. Although incorporating syntactic information into models has the potential to enhance the comprehension of user utterances and yield impressive results, its application in SLU systems remains largely unexplored. In this paper, we propose a carefully designed model termed Syntax-aware attention (SAT) to enhance SLU, where attention scopes are constrained based on relationships within the syntactic structure. Experimental results on three datasets show that our model achieves substantial improvements and excellent performance. Moreover, SAT can be integrated into other BERT-based language models to further boost their performance.

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++.