Related papers: Text2Data: Low-Resource Data Generation with Textu…

Learning disentangled representations of natural language is essential for many NLP tasks, e.g., conditional text generation, style transfer, personalized dialogue systems, etc. Similar problems have been studied extensively for other forms…

Data augmentation has been established as an efficacious approach to supplement useful information for low-resource datasets. Traditional augmentation techniques such as noise injection and image transformations have been widely used. In…

Recent years have seen many audio-domain text-to-music generation models that rely on large amounts of text-audio pairs for training. However, symbolic-domain controllable music generation has lagged behind partly due to the lack of a…

Multi-aspect controllable text generation aims to control text generation in attributes from multiple aspects, making it a complex but powerful task in natural language processing. Supervised fine-tuning methods are often employed for this…

Neural text-to-speech (TTS) models can synthesize natural human speech when trained on large amounts of transcribed speech. However, collecting such large-scale transcribed data is expensive. This paper proposes an unsupervised pre-training…

Text-to-image synthesis has achieved high-quality results with recent advances in diffusion models. However, text input alone has high spatial ambiguity and limited user controllability. Most existing methods allow spatial control through…

Pretrained language models (PLMs) have made remarkable progress in table-to-text generation tasks. However, the lack of domain-specific knowledge makes it challenging to bridge the topological gap between tabular data and text, especially…

Data availability and quality are major challenges in natural language processing for low-resourced languages. In particular, there is significantly less data available than for higher-resourced languages. This data is also often of low…

Scarcity of training data for task-oriented dialogue systems is a well known problem that is usually tackled with costly and time-consuming manual data annotation. An alternative solution is to rely on automatic text generation which,…

Speech-to-text translation has many potential applications for low-resource languages, but the typical approach of cascading speech recognition with machine translation is often impossible, since the transcripts needed to train a speech…

In this tutorial, we focus on text-to-text generation, a class of natural language generation (NLG) tasks, that takes a piece of text as input and then generates a revision that is improved according to some specific criteria (e.g.,…

We analyze a reversed-supervision strategy that searches over labelings of a large unlabeled set \(B\) to minimize error on a small labeled set \(A\). The search space is \(2^n\), and the resulting complexity remains exponential even under…

Recent deep learning models have shown improving results to natural language generation (NLG) irrespective of providing sufficient annotated data. However, a modest training data may harm such models performance. Thus, how to build a…

Representing documents into high dimensional embedding space while preserving the structural similarity between document sources has been an ultimate goal for many works on text representation learning. Current embedding models, however,…

Developing text-driven symbolic music generation models remains challenging due to the scarcity of aligned text-music datasets and the unreliability of automated captioning pipelines. While most efforts have focused on MIDI, sheet music…

The Data-to-Text task aims to generate human-readable text for describing some given structured data enabling more interpretability. However, the typical generation task is confined to a few particular domains since it requires well-aligned…

Real-world applications of natural language processing (NLP) are challenging. NLP models rely heavily on supervised machine learning and require large amounts of annotated data. These resources are often based on language data available in…

Recent work on controlled text generation has either required attribute-based fine-tuning of the base language model (LM), or has restricted the parameterization of the attribute discriminator to be compatible with the base autoregressive…

Data-to-text (D2T) and text-to-data (T2D) are dual tasks that convert structured data, such as graphs or tables into fluent text, and vice versa. These tasks are usually handled separately and use corpora extracted from a single source.…

Sequence labeling is an important technique employed for many Natural Language Processing (NLP) tasks, such as Named Entity Recognition (NER), slot tagging for dialog systems and semantic parsing. Large-scale pre-trained language models…