Related papers: Masking Orchestration: Multi-task Pretraining for …

We propose an approach for pre-training speech representations via a masked reconstruction loss. Our pre-trained encoder networks are bidirectional and can therefore be used directly in typical bidirectional speech recognition models. The…

Multilingual generative models obtain remarkable cross-lingual in-context learning capabilities through pre-training on large-scale corpora. However, they still exhibit a performance bias toward high-resource languages and learn isolated…

End-to-end speaker diarization enables accurate overlap-aware diarization by jointly estimating multiple speakers' speech activities in parallel. This approach is data-hungry, requiring a large amount of labeled conversational data, which…

Pretrained language models (PLMs) display impressive performances and have captured the attention of the NLP community. Establishing best practices in pretraining has, therefore, become a major focus of NLP research, especially since…

Training objectives based on predictive coding have recently been shown to be very effective at learning meaningful representations from unlabeled speech. One example is Autoregressive Predictive Coding (Chung et al., 2019), which trains an…

Open-domain long-term memory conversation can establish long-term intimacy with humans, and the key is the ability to understand and memorize long-term dialogue history information. Existing works integrate multiple models for modelling…

Vision-language models pre-trained on large scale of unlabeled biomedical images and associated reports learn generalizable semantic representations. These multi-modal representations can benefit various downstream tasks in the biomedical…

We describe a two-step approach for dialogue management in task-oriented spoken dialogue systems. A unified neural network framework is proposed to enable the system to first learn by supervision from a set of dialogue data and then…

This paper presents a novel method that allows a machine learning algorithm following the transformation-based learning paradigm \cite{brill95:tagging} to be applied to multiple classification tasks by training jointly and simultaneously on…

Language models like BERT and SpanBERT pretrained on open-domain data have obtained impressive gains on various NLP tasks. In this paper, we probe the effectiveness of domain-adaptive pretraining objectives on downstream tasks. In…

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…

Pre-trained language models (PLM) have marked a huge leap in neural dialogue modeling. While PLMs are pre-trained on large-scale text corpora, they are usually fine-tuned on scarce dialogue data with specific domain knowledge and dialogue…

Designing dialog tutors has been challenging as it involves modeling the diverse and complex pedagogical strategies employed by human tutors. Although there have been significant recent advances in neural conversational systems using large…

Open-domain multi-turn conversations mainly have three features, which are hierarchical semantic structure, redundant information, and long-term dependency. Grounded on these, selecting relevant context becomes a challenge step for…

Self-supervised pretraining has been extensively studied in language and vision domains, where a unified model can be easily adapted to various downstream tasks by pretraining representations without explicit labels. When it comes to…

Depression is a serious mental illness that impacts the way people communicate, especially through their emotions, and, allegedly, the way they interact with others. This work examines depression signals in dialogs, a less studied setting…

We introduce a new pretraining approach geared for multi-document language modeling, incorporating two key ideas into the masked language modeling self-supervised objective. First, instead of considering documents in isolation, we pretrain…

Automatic dialogue evaluation plays a crucial role in open-domain dialogue research. Previous works train neural networks with limited annotation for conducting automatic dialogue evaluation, which would naturally affect the evaluation…

The predominant approach to open-domain dialog generation relies on end-to-end training of neural models on chat datasets. However, this approach provides little insight as to what these models learn (or do not learn) about engaging in…

The recent success of large pre-trained language models such as BERT and GPT-2 has suggested the effectiveness of incorporating language priors in downstream dialog generation tasks. However, the performance of pre-trained models on the…