Related papers: Text Compression for Efficient Language Generation
Conditional story generation and contextual text continuation have become increasingly popular topics in NLP community. Existing models are often prone to output paragraphs of texts that gradually diverge from the given prompt. Although the…
We propose a method to fuse frozen text-only large language models (LLMs) with pre-trained image encoder and decoder models, by mapping between their embedding spaces. Our model demonstrates a wide suite of multimodal capabilities: image…
This paper proposes an effective emotional text-to-speech (TTS) system with a pre-trained language model (LM)-based emotion prediction method. Unlike conventional systems that require auxiliary inputs such as manually defined emotion…
Natural language processing techniques have demonstrated promising results in keyphrase generation. However, one of the major challenges in \emph{neural} keyphrase generation is processing long documents using deep neural networks.…
While Large Language Models (LLMs) become ever more dominant, classic pre-trained word embeddings sustain their relevance through computational efficiency and nuanced linguistic interpretation. Drawing from recent studies demonstrating that…
Pretrained using large amount of data, autoregressive language models are able to generate high quality sequences. However, these models do not perform well under hard lexical constraints as they lack fine control of content generation…
Data-to-text (D2T) generation is the task of generating texts from structured inputs. We observed that when the same target sentence was repeated twice, Transformer (T5) based model generates an output made up of asymmetric sentences from…
Transformers are arguably the preferred architecture for language generation. In this paper, inspired by continued fractions, we introduce a new function class for generative modeling. The architecture family implementing this function…
This study presents a new approach to metaphorical paraphrase generation by masking literal tokens of literal sentences and unmasking them with metaphorical language models. Unlike similar studies, the proposed algorithm does not only focus…
To simplify the generation process, several text-to-speech (TTS) systems implicitly learn intermediate latent representations instead of relying on predefined features (e.g., mel-spectrogram). However, their generation quality is…
In this paper, we compare various methods to compress a text using a neural model. We find that extracting tokens as latent variables significantly outperforms the state-of-the-art discrete latent variable models such as VQ-VAE.…
Diffusion-based generative models have greatly impacted the speech processing field in recent years, exhibiting high speech naturalness and spawning a new research direction. Their application in real-time communication is, however, still…
Neural text generation models are often autoregressive language models or seq2seq models. These models generate text by sampling words sequentially, with each word conditioned on the previous word, and are state-of-the-art for several…
Generative methods have recently seen significant improvements by generating in a lower-dimensional latent representation of the data. However, many of the generative methods applied in the latent space remain complex and difficult to…
Diffusion models have become a new generative paradigm for text generation. Considering the discrete categorical nature of text, in this paper, we propose GlyphDiffusion, a novel diffusion approach for text generation via text-guided image…
Graph neural networks (GNNs) are known to be vulnerable to oversmoothing due to their implicit homophily assumption. We mitigate this problem with a novel scheme that regulates the aggregation of messages, modulating the type and extent of…
Transformer-based large language models (LLM) have been widely used in language processing applications. However, due to the memory constraints of the devices, most of them restrict the context window. Even though recurrent models in…
Discovery of novel and promising materials is a critical challenge in the field of chemistry and material science, traditionally approached through methodologies ranging from trial-and-error to machine learning-driven inverse design. Recent…
This paper considers Pseudo-Relevance Feedback (PRF) methods for dense retrievers in a resource constrained environment such as that of cheap cloud instances or embedded systems (e.g., smartphones and smartwatches), where memory and CPU are…
The emergence of large language models (LLMs) has revolutionized the capabilities of text comprehension and generation. Multi-modal generation attracts great attention from both the industry and academia, but there is little work on…