相关论文: Unsupervised Dialogue Topic Segmentation with Topi…

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…

Dialogue Topic Segmentation (DTS) aims to divide dialogues into coherent segments. DTS plays a crucial role in various NLP downstream tasks, but suffers from chronic problems: data shortage, labeling ambiguity, and incremental complexity of…

Dialogue topic segmentation is critical in several dialogue modeling problems. However, popular unsupervised approaches only exploit surface features in assessing topical coherence among utterances. In this work, we address this limitation…

In dialogue systems, discourse plays a crucial role in managing conversational focus and coordinating interactions. It consists of two key structures: rhetorical structure and topic structure. The former captures the logical flow of…

Dialogue related Machine Reading Comprehension requires language models to effectively decouple and model multi-turn dialogue passages. As a dialogue development goes after the intentions of participants, its topic may not keep constant…

In settings where only unlabelled speech data is available, speech technology needs to be developed without transcriptions, pronunciation dictionaries, or language modelling text. A similar problem is faced when modelling infant language…

The current trend in automatic speech recognition is to leverage large amounts of labeled data to train supervised neural network models. Unfortunately, obtaining data for a wide range of domains to train robust models can be costly.…

In this paper, we introduce an unsupervised approach for Speech Segmentation, which builds on previously researched approaches, e.g., Speaker Diarization, while being applicable to an inclusive set of acoustic-semantic distinctions, paving…

Dialogue Topic Segmentation (DTS) is crucial for understanding task-oriented public-channel communications, such as maritime VHF dialogues, which feature informal speech and implicit transitions. To address the limitations of traditional…

Topic segmentation and labeling is often considered a prerequisite for higher-level conversation analysis and has been shown to be useful in many Natural Language Processing (NLP) applications. We present two new corpora of email and blog…

We address the problem of unsupervised semantic segmentation of outdoor LiDAR point clouds in diverse traffic scenarios. The key idea is to leverage the spatiotemporal nature of a dynamic point cloud sequence and introduce drastically…

Unsupervised word segmentation in audio utterances is challenging as, in speech, there is typically no gap between words. In a preliminary experiment, we show that recent deep self-supervised features are very effective for word…

Pre-training methods with contrastive learning objectives have shown remarkable success in dialog understanding tasks. However, current contrastive learning solely considers the self-augmented dialog samples as positive samples and treats…

Recent neural supervised topic segmentation models achieve distinguished superior effectiveness over unsupervised methods, with the availability of large-scale training corpora sampled from Wikipedia. These models may, however, suffer from…

Incorporating external knowledge into dialogue generation has been proven to benefit the performance of an open-domain Dialogue System (DS), such as generating informative or stylized responses, controlling conversation topics. In this…

In the retrieval-based multi-turn dialogue modeling, it remains a challenge to select the most appropriate response according to extracting salient features in context utterances. As a conversation goes on, topic shift at discourse-level…

This paper introduces a new unsupervised approach for dialogue act induction. Given the sequence of dialogue utterances, the task is to assign them the labels representing their function in the dialogue. Utterances are represented as…

We address the problem of discovering part segmentations of articulated objects without supervision. In contrast to keypoints, part segmentations provide information about part localizations on the level of individual pixels. Capturing both…

Existing dialogue state tracking (DST) models require plenty of labeled data. However, collecting high-quality labels is costly, especially when the number of domains increases. In this paper, we address a practical DST problem that is…

(Part of the abstract) In this thesis, we investigate the use of unsupervised spoken term discovery in tackling this problem. Unsupervised spoken term discovery aims to discover topic-related terminologies in a speech without knowing the…