Related papers: Conversation Disentanglement with Bi-Level Contras…
Domain mismatch problem caused by speaker-unrelated feature has been a major topic in speaker recognition. In this paper, we propose an explicit disentanglement framework to unravel speaker-relevant features from speaker-unrelated features…
Building robust and general dialogue models for spoken conversations is challenging due to the gap in distributions of spoken and written data. This paper presents our approach to build generalized models for the Knowledge-grounded…
Authentication is a task aiming to confirm the truth between data instances and personal identities. Typical authentication applications include face recognition, person re-identification, authentication based on mobile devices and so on.…
Recent advances in pre-trained language models have significantly improved neural response generation. However, existing methods usually view the dialogue context as a linear sequence of tokens and learn to generate the next word through…
The objective of this paper is to learn representations of speaker identity without access to manually annotated data. To do so, we develop a self-supervised learning objective that exploits the natural cross-modal synchrony between faces…
Dysarthric speech recognition often suffers from performance degradation due to the intrinsic diversity of dysarthric severity and extrinsic disparity from normal speech. To bridge these gaps, we propose a Dynamic Phoneme-level Contrastive…
Fine-tuning a pre-trained language model via the contrastive learning framework with a large amount of unlabeled sentences or labeled sentence pairs is a common way to obtain high-quality sentence representations. Although the contrastive…
We first propose a new task named Dialogue Description (Dial2Desc). Unlike other existing dialogue summarization tasks such as meeting summarization, we do not maintain the natural flow of a conversation but describe an object or an action…
Recent advances in unsupervised representation learning often rely on knowing the number of classes to improve feature extraction and clustering. However, this assumption raises an important question: is the number of classes always…
Session-based recommendation techniques aim to capture dynamic user behavior by analyzing past interactions. However, existing methods heavily rely on historical item ID sequences to extract user preferences, leading to challenges such as…
Machine unlearning aims to eliminate the influence of a subset of training samples (i.e., unlearning samples) from a trained model. Effectively and efficiently removing the unlearning samples without negatively impacting the overall model…
Identifying intents from dialogue utterances forms an integral component of task-oriented dialogue systems. Intent-related tasks are typically formulated either as a classification task, where the utterances are classified into predefined…
The recent abundance of conversational data on the Web and elsewhere calls for effective NLP systems for dialog understanding. Complete utterance-level understanding often requires context understanding, defined by nearby utterances. In…
Distant supervision assumes that any sentence containing the same entity pairs reflects identical relationships. Previous works of distantly supervised relation extraction (DSRE) task generally focus on sentence-level or bag-level…
Retrieval-based conversational systems learn to rank response candidates for a given dialogue context by computing the similarity between their vector representations. However, training on a single textual form of the multi-turn context…
In representation learning, a disentangled representation is highly desirable as it encodes generative factors of data in a separable and compact pattern. Researchers have advocated leveraging disentangled representations to complete…
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…
Contrastive speaker embedding assumes that the contrast between the positive and negative pairs of speech segments is attributed to speaker identity only. However, this assumption is incorrect because speech signals contain not only speaker…
Breaking down a document or a conversation into multiple contiguous segments based on its semantic structure is an important and challenging problem in NLP, which can assist many downstream tasks. However, current works on topic…
Contrastive learning has gained popularity and pushes state-of-the-art performance across numerous large-scale benchmarks. In contrastive learning, the contrastive loss function plays a pivotal role in discerning similarities between…