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 stateof-the-art performance. Further model analysis also verifies the superiority of our method.

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.

Multimodal intent detection is designed to leverage diverse modalities for a comprehensive understanding of user intentions in real-world scenarios, thus playing a critical role in modern task-oriented dialogue systems. Existing methods have made great progress in modal alignment and fusion, however, two vital limitations are neglected: (I) close entanglement of multimodal semantics with modal structures; (II) insufficient learning of the causal effects of semantic and modality-specific information on the final predictions under the end-to-end training fashion. To alleviate the above limitations, we introduce the Dual-oriented Disentangled Network with Counterfactual Intervention (DuoDN). DuoDN addresses key limitations in current systems by effectively disentangling and utilizing modality-specific and multimodal semantic information. The model consists of a Dual-oriented Disentangled Encoder that decouples semantics-oriented and modality-oriented representations, alongside a Counterfactual Intervention Module that applies 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.

Due to the rapid development with pre-trained language models, fully end-to-end Task-Oriented Dialogue (TOD) systems exhibit superior performance. How to achieve the ability to efficiently retrieve entities in cross-domain large-scale databases is a key issue. Most existing end-to-end Task-Oriented Dialogue systems suffer from the following problems: The ability to handle erroneous but easily confused entities needs to be improved; Matching information between contexts and entities is not captured, leading to weak modeling of domain-invariant and interpretable features, making it difficult to generalize to unseen domains. In this paper, we propose a method for knowledge retrieval driven by matching representations. The approach consists of a matching signal extractor for extracting matching representations between contexts and entities that have generic conceptual features and hence domain invariant properties, and an Attribute Filter for filtering irrelevant information to facilitate the re-selection of entities. Experiments on three standard benchmarks at the dialogue level and on large knowledge bases show that our retriever performs knowledge retrieval more efficiently than existing approaches.

Pre-trained language models (PLMs) that rely solely on textual corpus may present limitations in multimodal semantics comprehension. Existing studies attempt to alleviate this issue by incorporating additional modal information through image retrieval or generation. However, these methods: (1) inevitably encounter modality gaps and noise; (2) treat all modalities indiscriminately; and (3) ignore visual or acoustic semantics of key entities. To tackle these challenges, we propose a novel principled iterative framework for multimodal-augmented PLMs termed MASE, which achieves efficient and balanced injection of multimodal semantics under the proposed Expectation Maximization (EM) based iterative algorithm. Initially, MASE utilizes multimodal proxies instead of explicit data to enhance PLMs, which avoids noise and modality gaps. In E-step, MASE adopts a novel information-driven self-balanced strategy to estimate allocation weights. Furthermore, MASE employs heterogeneous graph attention to capture entity-level fine-grained semantics on the proposed multimodal-semantic scene graph. In M-step, MASE injects global multimodal knowledge into PLMs through a cross-modal contrastive loss. Experimental results show that MASE consistently outperforms competitive baselines on multiple tasks across various architectures. More impressively, MASE is compatible with existing efficient parameter fine-tuning methods, such as prompt learning.

Retrieving accurate domain knowledge and providing helpful information are crucial in developing an effective end-to-end task-oriented dialogue system (E2ETOD). The field has witnessed numerous methods following the retrieve-then-generate paradigm and training their systems on one specific domain. However, existing approaches still suffer from the Distractive Attributes Problem (DAP): struggling to deal with false but similar knowledge (hard negative entities), which is even more intractable when countless pieces of knowledge from different domains are blended in a real-world scenario. To alleviate DAP, we propose the Relevance-aware Adaptive Learning (ReAL) method, a two-stage training framework that eliminates hard negatives step-by-step and aligns retrieval with generation. In the first stage, we introduce a top-k adaptive contrastive loss and utilize the divergence-driven feedback from the frozen generator to pre-train the retriever. In the second stage, we propose using the metric score distribution as an anchor to align retrieval with generation. Thorough experiments on three benchmark datasets demonstrate ReAL’s superiority over existing methods, with extensive analysis validating its strong capabilities of overcoming in- and cross-domain distractions.

Given coupled sentence image pairs, Multimodal Aspect-based Sentiment Analysis (MABSA) aims to detect aspect terms and predict their sentiment polarity. While existing methods have made great efforts in aligning images and text for improved MABSA performance, they still struggle to effectively mitigate the challenge of the noisy correspondence problem (NCP): the text description is often not well-aligned with the visual content. To alleviate NCP, in this paper, we introduce Aspect-driven Alignment and Refinement (ADAR), which is a two-stage coarse-to-fine alignment framework. In the first stage, ADAR devises a novel Coarse-to-fine Aspect-driven Alignment Module, which introduces Optimal Transport (OT) to learn the coarse-grained alignment between visual and textual features. Then the adaptive filter bin is applied to remove the irrelevant image regions at a fine-grained level; In the second stage, ADAR introduces an Aspect-driven Refinement Module to further refine the cross-modality feature representation. Extensive experiments on two benchmark datasets demonstrate the superiority of our model over state-of-the-art performance in the MABSA task.

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.

Fully end-to-end task-oriented dialogue (EToD) systems have shown excellent performance, which requires the ability to retrieve entities accurately for generation. Existing methods improve the accuracy of entity retrieval and construct data flows between retrieval results and response generator, achieving promising results. However, most of them suffer from the following issues: (1) The entity is retrieved by directly interacting with the context at a coarse-grained level, so the similarity score may be disturbed by irrelevant attributes; (2) The generator pays equal attention to retrieved entities and the context and does not learn the generation preferences for the current turn. In this paper, we propose a framework called Regulating Preferences of Generator (RPG) based on retrieval results, which includes a generator preference extractor, an entity retriever, and a generator with the gate-controlled preference regulator. The generator preference extractor not only improves the entity retriever by filtering the interference of irrelevant attributes but also provides more focused guidance to the generator by performing inter-turn attribute prediction. Experiments and analyses on three standard benchmarks show that our framework outperforms existing methods and improves the quality of the dialogue.

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.

Large Vision-Language Models (LVLMs) may produce outputs that are unfaithful to reality, also known as visual hallucinations (VH), which hinders their application in multimodal understanding and decision-making. In this work, we introduce a novel plug-and-play train-free decoding algorithm named Game and Tree based Hallucination Mitigation (GTHM), designed for mitigating VH. GTHM is inspired by empirical observations that the fuzziness of multi-granularity view perception exacerbates VH. Based on this, GTHM leverages visual information to construct a coarse-to-fine visual view tree (CFTree) that organizes visual objects, attributes, and relationships in a hierarchical manner. Additionally, we innovatively model the optimal visual-token matching process on the CFTree as the cooperative game. Specifically, we define the Tree-based Shapley Value (TSV) for each visual view on the CFTree to assess its significant contribution to the overall visual understanding, thereby determining the optimal visual granularity. Subsequently, we utilize the TSV as guidance to implement adaptive weight contrastive decoding to achieve vision-aware decoding. Extensive experiments on four popular benchmarks confirm the effectiveness of our GTHM in alleviating VH across different LVLM families without additional training or post-processing. Our code is published at https://github.com/mengchuang123/GTHM.