Related papers: Rapformer: Conditional Rap Lyrics Generation with …
Transformers have been shown to emulate logical deduction over natural language theories (logical rules expressed in natural language), reliably assigning true/false labels to candidate implications. However, their ability to generate…
Music has the power to evoke intense emotional experiences and regulate the mood of an individual. With the advent of online streaming services, research in music recommendation services has seen tremendous progress. Modern methods…
In recent years, the generation of conversation content based on deep neural networks has attracted many researchers. However, traditional neural language models tend to generate general replies, lacking logical and emotional factors. This…
Recently, a variety of neural models have been proposed for lyrics generation. However, most previous work completes the generation process in a single pass with little human intervention. We believe that lyrics creation is a creative…
It is increasingly considered that human speech perception and production both rely on articulatory representations. In this paper, we investigate whether this type of representation could improve the performances of a deep generative model…
Writing down lyrics for human consumption involves not only accurately capturing word sequences, but also incorporating punctuation and formatting for clarity and to convey contextual information. This includes song structure, emotional…
We propose a method to learn unsupervised sentence representations in a non-compositional manner based on Generative Latent Optimization. Our approach does not impose any assumptions on how words are to be combined into a sentence…
We present a novel method of performing spelling correction on short input strings, such as search queries or individual words. At its core lies a procedure for generating artificial typos which closely follow the error patterns manifested…
Speech recognition is a well developed research field so that the current state of the art systems are being used in many applications in the software industry, yet as by today, there still does not exist such robust system for the…
Autoregressive models for text sometimes generate repetitive and low-quality output because errors accumulate during the steps of generation. This issue is often attributed to exposure bias - the difference between how a model is trained,…
We present a new topic model that generates documents by sampling a topic for one whole sentence at a time, and generating the words in the sentence using an RNN decoder that is conditioned on the topic of the sentence. We argue that this…
Even for us, it can be challenging to comprehend the meaning of songs. As part of this project, we explore the process of generating the meaning of songs. Despite the widespread use of text-to-text models, few attempts have been made to…
Generating images from semantic visual knowledge is a challenging task, that can be useful to condition the synthesis process in complex, subtle, and unambiguous ways, compared to alternatives such as class labels or text descriptions.…
Discriminative pre-trained language models (PrLMs) can be generalized as denoising auto-encoders that work with two procedures, ennoising and denoising. First, an ennoising process corrupts texts with arbitrary noising functions to…
Neural network-based generative language models like ELMo and BERT can work effectively as general purpose sentence encoders in text classification without further fine-tuning. Is it possible to adapt them in a similar way for use as…
We introduce Autodecompose, a novel self-supervised generative model that decomposes data into two semantically independent properties: the desired property, which captures a specific aspect of the data (e.g. the voice in an audio signal),…
Standard decoding approaches for conditional text generation tasks typically search for an output hypothesis with high model probability, but this may not yield the best hypothesis according to human judgments of quality. Reranking to…
We present a system for generating parsers based directly on the metaphor of parsing as deduction. Parsing algorithms can be represented directly as deduction systems, and a single deduction engine can interpret such deduction systems so as…
Existing recurrent neural language models often fail to capture higher-level structure present in text: for example, rhyming patterns present in poetry. Much prior work on poetry generation uses manually defined constraints which are…
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,…