Related papers: SideControl: Controlled Open-domain Dialogue Gener…

Sequence labelling tasks like Dialog Act and Emotion/Sentiment identification are a key component of spoken dialog systems. In this work, we propose a new approach to learn generic representations adapted to spoken dialog, which we evaluate…

It is desirable to include more controllable attributes to enhance the diversity of generated responses in open-domain dialogue systems. However, existing methods can generate responses with only one controllable attribute or lack a…

An intelligent dialogue system in a multi-turn setting should not only generate the responses which are of good quality, but it should also generate the responses which can lead to long-term success of the dialogue. Although, the current…

This paper proposes a transformer over transformer framework, called Transformer$^2$, to perform neural text segmentation. It consists of two components: bottom-level sentence encoders using pre-trained transformers, and an upper-level…

Training a personalized dialogue system requires a lot of data, and the data collected for a single user is usually insufficient. One common practice for this problem is to share training dialogues between different users and train multiple…

Generating relevant responses in a dialog is challenging, and requires not only proper modeling of context in the conversation but also being able to generate fluent sentences during inference. In this paper, we propose a two-step framework…

With the rapid increase in the volume of dialogue data from daily life, there is a growing demand for dialogue summarization. Unfortunately, training a large summarization model is generally infeasible due to the inadequacy of dialogue data…

Loading models pre-trained on the large-scale corpus in the general domain and fine-tuning them on specific downstream tasks is gradually becoming a paradigm in Natural Language Processing. Previous investigations prove that introducing a…

We propose a weakly-supervised approach for conditional image generation of complex scenes where a user has fine control over objects appearing in the scene. We exploit sparse semantic maps to control object shapes and classes, as well as…

Multimodal conditionality in transformer-based natural language models has demonstrated state-of-the-art performance in the task of product description generation. Recent approaches condition a language model on one or more images and other…

Recent advances in open-domain dialogue systems rely on the success of neural models that are trained on large-scale data. However, collecting large-scale dialogue data is usually time-consuming and labor-intensive. To address this data…

Recently, pre-training methods have shown remarkable success in task-oriented dialog (TOD) systems. However, most existing pre-trained models for TOD focus on either dialog understanding or dialog generation, but not both. In this paper, we…

Visually-grounded spoken language datasets can enable models to learn cross-modal correspondences with very weak supervision. However, modern audio-visual datasets contain biases that undermine the real-world performance of models trained…

Pre-training language models (LMs) on large-scale unlabeled text data makes the model much easier to achieve exceptional downstream performance than their counterparts directly trained on the downstream tasks. In this work, we study what…

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…

Transformer-based language models excel in NLP tasks, but fine-grained control remains challenging. This paper explores methods for manipulating transformer models through principled interventions at three levels: prompts, activations, and…

Task-oriented dialogue (TOD) system is designed to accomplish user-defined tasks through dialogues. The TOD system has progressed towards end-to-end modeling by leveraging pre-trained large language models. Fine-tuning the pre-trained…

Controllable text generation (CTG) seeks to craft texts adhering to specific attributes, traditionally employing learning-based techniques such as training, fine-tuning, or prefix-tuning with attribute-specific datasets. These approaches,…

There has been a rapid development in data-driven task-oriented dialogue systems with the benefit of large-scale datasets. However, the progress of dialogue systems in low-resource languages lags far behind due to the lack of high-quality…

Recently, neural network based dialogue systems have become ubiquitous in our increasingly digitalized society. However, due to their inherent opaqueness, some recently raised concerns about using neural models are starting to be taken…