Related papers: Improving User Controlled Table-To-Text Generation…
Natural language serves as a common and straightforward signal for humans to interact seamlessly with machines. Recognizing the importance of this interface, the machine learning community is investing considerable effort in generating data…
In this paper, we investigate data augmentation for text generation, which we call GenAug. Text generation and language modeling are important tasks within natural language processing, and are especially challenging for low-data regimes. We…
Modern neural text-to-speech (TTS) synthesis can generate speech that is indistinguishable from natural speech. However, the prosody of generated utterances often represents the average prosodic style of the database instead of having wide…
The topic-to-essay generation task is a challenging natural language generation task that aims to generate paragraph-level text with high semantic coherence based on a given set of topic words. Previous work has focused on the introduction…
Human use language not just to convey information but also to express their inner feelings and mental states. In this work, we adapt the state-of-the-art language generation models to generate affective (emotional) text. We posit a model…
Text generation often requires high-precision output that obeys task-specific rules. This fine-grained control is difficult to enforce with off-the-shelf deep learning models. In this work, we consider augmenting neural generation models…
Recent advances in neural network-based generative modeling have reignited the hopes in having computer systems capable of seamlessly conversing with humans and able to understand natural language. Neural architectures have been employed to…
Encoder-only transformer models have been successfully applied to different table understanding tasks, as in TAPAS (Herzig et al., 2020). A major limitation of these architectures is that they are constrained to classification-like tasks…
Large Language Models trained on web-scale text acquire language generation abilities that can solve a wide range of tasks, particularly when task knowledge is refined into the generative prior using in-context examples. However, spurious…
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,…
Text generation aims to produce human-like natural language output for down-stream tasks. It covers a wide range of applications like machine translation, document summarization, dialogue generation and so on. Recently deep neural…
A common and effective means for improving language model capabilities involves finetuning a ``student'' language model's parameters on generations from a more proficient ``teacher'' model. Termed ``synthetic data'', these generations are…
Lyrics-to-melody generation is an interesting and challenging topic in AI music research field. Due to the difficulty of learning the correlations between lyrics and melody, previous methods suffer from low generation quality and lack of…
A well-known way to improve the performance of document retrieval is to expand the user's query. Several approaches have been proposed in the literature, and some of them are considered as yielding state-of-the-art results in IR. In this…
Expressing natural language descriptions of structured facts or relations -- data-to-text generation (D2T) -- increases the accessibility of structured knowledge repositories. Previous work shows that pre-trained language models(PLMs)…
During the pre-training step of natural language models, the main objective is to learn a general representation of the pre-training dataset, usually requiring large amounts of textual data to capture the complexity and diversity of natural…
The increasing prevalence of Large Language Models (LMs) in critical applications highlights the need for controlled language generation strategies that are not only computationally efficient but that also enjoy performance guarantees. To…
The robustness of AI-content detection models against sophisticated adversarial strategies, such as paraphrasing or word switching, is a rising concern in natural language generation (NLG) applications. This study proposes ToBlend, a novel…
As Large Language Models (LLMs) are deployed more widely, customization with respect to vocabulary, style, and character becomes more important. In this work, we introduce model arithmetic, a novel inference framework for composing and…
In this paper, we propose a novel model RevGAN that automatically generates controllable and personalized user reviews based on the arbitrarily given sentimental and stylistic information. RevGAN utilizes the combination of three novel…