We consider the communication of natural language text from a source to a destination over
noiseless and character-erasure channels. We exploit language's inherent correlations and …

In spite of their superior performance, neural probabilistic language models (NPLMs) remain
far less widely used than n-gram models due to their notoriously long training times, which …

Neural encoder-decoder models have been successful in natural language generation
tasks. However, real applications of abstractive summarization must consider additional …

Spurred by a huge interest in the post-Shannon communication, it has recently been shown
that leveraging semantics can significantly improve the communication effectiveness across …

Recently, generative semantic communication models have proliferated as they are
revolutionizing semantic communication frameworks, improving their performance, and …

Recent neural models for data-to-text generation rely on massive parallel pairs of data and
text to learn the writing knowledge. They often assume that writing knowledge can be …

Language models are known to produce vague and generic outputs. We propose two
unsupervised decoding strategies based on either word-frequency or point-wise mutual …

Word prediction generally relies on n-grams occurrence statistics, which may have huge
data storage requirements and does not take into account the general meaning of the text …

Generating texts with a large language model (LLM) consumes massive amounts of
memory. Apart from the already-large model parameters, the key/value (KV) cache that …

Existing large language models have to run K times to generate a sequence of K tokens. In
this paper, we present RecycleGPT, a generative language model with fast decoding speed …