Related papers: Utterance Rewriting with Contrastive Learning in M…

Spoken language understanding (SLU) is an essential task for machines to understand human speech for better interactions. However, errors from the automatic speech recognizer (ASR) usually hurt the understanding performance. In reality, ASR…

Spoken question answering (SQA) requires fine-grained understanding of both spoken documents and questions for the optimal answer prediction. In this paper, we propose novel training schemes for spoken question answering with a…

This paper addresses the limitations of large language models in understanding long-term context. It proposes a model architecture equipped with a long-term memory mechanism to improve the retention and retrieval of semantic information…

Recent years the task of incomplete utterance rewriting has raised a large attention. Previous works usually shape it as a machine translation task and employ sequence to sequence based architecture with copy mechanism. In this paper, we…

Turn-level user satisfaction is one of the most important performance metrics for conversational agents. It can be used to monitor the agent's performance and provide insights about defective user experiences. Moreover, a powerful…

Dialogue topic segmentation plays a crucial role in various types of dialogue modeling tasks. The state-of-the-art unsupervised DTS methods learn topic-aware discourse representations from conversation data through adjacent discourse…

Retrieve-based dialogue response selection aims to find a proper response from a candidate set given a multi-turn context. Pre-trained language models (PLMs) based methods have yielded significant improvements on this task. The sequence…

The impressive performance of GPT-3 using natural language prompts and in-context learning has inspired work on better fine-tuning of moderately-sized models under this paradigm. Following this line of work, we present a contrastive…

Multi-turn response selection is a challenging task due to its high demands on efficient extraction of the matching features from abundant information provided by context utterances. Since incorporating syntactic information like dependency…

Recent language models have achieved impressive performance in natural language tasks by incorporating instructions with task input during fine-tuning. Since all samples in the same natural language task can be explained with the same task…

The sequential order of utterances is often meaningful in coherent dialogues, and the order changes of utterances could lead to low-quality and incoherent conversations. We consider the order information as a crucial supervised signal for…

Unified multimodal models (UMMs) have achieved remarkable progress yet remain constrained by a single-turn interaction paradigm, effectively functioning as solvers for independent requests rather than assistants in continuous dialogue. To…

We present a novel approach to dialogue state tracking and referring expression resolution tasks. Successful contextual understanding of multi-turn spoken dialogues requires resolving referring expressions across turns and tracking the…

Large language models (LLMs) excel at solving problems with clear and complete statements, but often struggle with nuanced environments or interactive tasks which are common in most real-world scenarios. This highlights the critical need…

Incorporating contrastive learning objectives in sentence representation learning (SRL) has yielded significant improvements on many sentence-level NLP tasks. However, it is not well understood why contrastive learning works for learning…

Contrastive learning has become a popular approach in natural language processing, particularly for the learning of sentence embeddings. However, the discrete nature of natural language makes it difficult to ensure the quality of positive…

A reverse dictionary takes the description of a target word as input and outputs the target word together with other words that match the description. Existing reverse dictionary methods cannot deal with highly variable input queries and…

This paper introduces a model for incomplete utterance restoration (IUR) called JET (\textbf{J}oint learning token \textbf{E}xtraction and \textbf{T}ext generation). Different from prior studies that only work on extraction or abstraction…

In neural dialogue modeling, a neural network is trained to predict the next utterance, and at inference time, an approximate decoding algorithm is used to generate next utterances given previous ones. While this autoregressive framework…

Speech models may be affected by performance imbalance in different population subgroups, raising concerns about fair treatment across these groups. Prior attempts to mitigate unfairness either focus on user-defined subgroups, potentially…