Related papers: SPACE-2: Tree-Structured Semi-Supervised Contrasti…

Few-shot dialogue state tracking (DST) is a realistic problem that trains the DST model with limited labeled data. Existing few-shot methods mainly transfer knowledge learned from external labeled dialogue data (e.g., from question…

Spatio-temporal representation learning is critical for video self-supervised representation. Recent approaches mainly use contrastive learning and pretext tasks. However, these approaches learn representation by discriminating sampled…

Most dialogue systems in real world rely on predefined intents and answers for QA service, so discovering potential intents from large corpus previously is really important for building such dialogue services. Considering that most…

State-of-the-art model for zero-shot cross-lingual spoken language understanding performs cross-lingual unsupervised contrastive learning to achieve the label-agnostic semantic alignment between each utterance and its code-switched data.…

Conversational search has been regarded as the next-generation search paradigm. Constrained by data scarcity, most existing methods distill the well-trained ad-hoc retriever to the conversational retriever. However, these methods, which…

A long-standing goal of task-oriented dialogue research is the ability to flexibly adapt dialogue models to new domains. To progress research in this direction, we introduce DialoGLUE (Dialogue Language Understanding Evaluation), a public…

In this paper, we propose a novel SQL guided pre-training framework STAR for context-dependent text-to-SQL parsing, which leverages contextual information to enrich natural language (NL) utterance and table schema representations for…

Identifying breakdowns in ongoing dialogues helps to improve communication effectiveness. Most prior work on this topic relies on human annotated data and data augmentation to learn a classification model. While quality labeled dialogue…

Unpaired image-to-image translation involves learning mappings between source domain and target domain in the absence of aligned or corresponding samples. Score based diffusion models have demonstrated state-of-the-art performance in…

We describe a method to jointly pre-train speech and text in an encoder-decoder modeling framework for speech translation and recognition. The proposed method incorporates four self-supervised and supervised subtasks for cross modality…

In this work, we explore the application of PLATO-2 on various dialogue systems, including open-domain conversation, knowledge grounded dialogue, and task-oriented conversation. PLATO-2 is initially designed as an open-domain chatbot,…

Context-aware methods have achieved remarkable advancements in supervised scene text recognition by leveraging semantic priors from words. Considering the heterogeneity of text and background in STR, we propose that such contextual priors…

This paper aims to build a multi-speaker expressive TTS system, synthesizing a target speaker's speech with multiple styles and emotions. To this end, we propose a novel contrastive learning-based TTS approach to transfer style and emotion…

While image-text representation learning has become very popular in recent years, existing models tend to lack spatial awareness and have limited direct applicability for dense understanding tasks. For this reason, self-supervised…

Efficiently capturing the complex spatiotemporal representations from large-scale unlabeled traffic data remains to be a challenging task. In considering of the dilemma, this work employs the advanced contrastive learning and proposes a…

Contrastive representation learning has proven to be an effective self-supervised learning method. Most successful approaches are based on Noise Contrastive Estimation (NCE) and use different views of an instance as positives that should be…

We present a neural semi-supervised learning model termed Self-Pretraining. Our model is inspired by the classic self-training algorithm. However, as opposed to self-training, Self-Pretraining is threshold-free, it can potentially update…

Recent multimodal models such as Contrastive Language-Image Pre-training (CLIP) have shown remarkable ability to align visual and linguistic representations. However, domains where small visual differences carry large semantic significance,…

While Self-Supervised Learning has helped reap the benefit of the scale from the available unlabeled data, the learning paradigms are continuously being bettered. We present a new pre-training strategy named ccc-wav2vec 2.0, which uses…

Multi-party dialogue generation presents significant challenges due to the complex interplay of multiple speakers and interwoven conversational threads. Traditional approaches often fall short in capturing these complexities, particularly…