Backchannels and fillers are important linguistic expressions in dialogue, but often treated as 'noise' to be bypassed in modern transformerbased language models (LMs).Here, we study how they are represented in LMs using three fine-tuning strategies on three dialogue corpora in English and Japanese, in which backchannels and fillers are both preserved and annotated.This allows us to investigate how fine-tuning can help LMs learn these representations.We first apply clustering analysis to the learnt representation of backchannels and fillers, and find increased silhouette scores in representations from fine-tuned models, which suggests that fine-tuning enables LMs to distinguish the nuanced semantic variation in different backchannel and filler use.We also employ natural language generation metrics and qualitative analyses to verify that utterances produced by fine-tuned LMs resemble those produced by humans more closely.Our findings suggest the potential for transforming general LMs into conversational LMs that can produce human-like language more adequately.

Integrating external knowledge with traditional spoken language understanding (SLU) models can effectively mitigate the ambiguity in user utterances in real-world scenarios. Knowledge graph, as a common source of external knowledge, encapsulates entities enriched with diverse attribute information. Nevertheless, existing models consider all entities as relevant, which introduces significant noise into the input. Additionally, not all attribute information of the entities is essential, resulting in considerable noise and redundancy. In this article, we propose a Noise-Removal of Knowledge-Enhanced (NRKE) framework for SLU, which involves two different types of denoising. The first approach involves hard denoising via entity selection, where we leverage a small clean dataset and introduce a BERT-based auxiliary model to filter out entities unrelated to user utterances, effectively eliminating noisy entities. In addition, we further refine entity selection by incorporating Large Language Models (LLMs) to assist in filtering out entities unrelated to user utterances. The second method involves soft denoising through the selection of entity attribute information. This approach utilizes a keywords-based local semantic selection that gives greater weight to relevant local semantics associated with specific keywords. This allows us to capture task-related information from the chosen entities, thereby minimizing noise and redundancy. To evaluate the generalization capability of existing knowledge-enhanced SLU models, we construct a new dataset named KGCAIS. The experimental results show that our NRKE achieves better performance than the competing models on both the PROSLU and KGCAIS datasets.

Multi-intent spoken language understanding (SLU) that can handle multiple intents in an utterance has attracted increasing attention. Previous studies treat the slot filling task as a token-level sequence labeling task, which results in a lack of entity-related information. In our paper, we propose anEntity-LevelSlotFilling (ELSF) framework for joint multiple intent detection and slot filling. In our framework, two entity-oriented auxiliary tasks, entity boundary detection and entity type assignment, are introduced as the regularization to capture the entity boundary and the context of type, respectively. Besides, to better utilize the entity interaction, we design an effective entity-level coordination mechanism for modeling the interaction in both entity-entity and intent-entity relationships. Experiments on five datasets demonstrate the effectiveness and generalizability of our ELSF.

Intent detection and slot filling are two important tasks for spoken language understanding. Considering the close relation between them, most existing methods joint them by sharing parameters or establishing explicit connection between them for potentially benefiting each other. However, most of them only consider single directional connection and ignore their cross-impact between them. Moreover, these joint methods treat the predicted labels as the gold labels, which may cause error propagation. In this paper, we propose a two-stage Graph Attention Interactive Refine (GAIR) framework. In stage one, the basic SLU model predicts the coarse intent and slots. In stage two, we select the top-k candidate labels from stage one and construct a graph to make full advantage of intent and slot filling information. By constructing such graph, our framework can establish a bidirectional connection between two tasks and refine the coarse result, which can better take full use of cross-impact between two tasks. Moreover, contextual regularization is introduced for better alleviating error propagation. Experiments on two datasets show that our model achieves the state-of-the-arts performance.