相关论文: SRS-Stories: Vocabulary-constrained multilingual s…

While Large Language Models (LLMs) can generate fluent text, producing high-quality creative stories remains challenging. Reinforcement Learning (RL) offers a promising solution but faces two critical obstacles: designing reliable reward…

Stories generated with neural language models have shown promise in grammatical and stylistic consistency. However, the generated stories are still lacking in common sense reasoning, e.g., they often contain sentences deprived of world…

We explore the use of large pretrained language models as few-shot semantic parsers. The goal in semantic parsing is to generate a structured meaning representation given a natural language input. However, language models are trained to…

We propose a sentence-level language model which selects the next sentence in a story from a finite set of fluent alternatives. Since it does not need to model fluency, the sentence-level language model can focus on longer range…

A wide range of control perspectives have been explored in controllable text generation. Structure-controlled summarization is recently proposed as a useful and interesting research direction. However, current structure-controlling methods…

We explore story generation: creative systems that can build coherent and fluent passages of text about a topic. We collect a large dataset of 300K human-written stories paired with writing prompts from an online forum. Our dataset enables…

Generating natural language under complex constraints is a principled formulation towards controllable text generation. We present a framework to allow specification of combinatorial constraints for sentence generation. We propose TSMH, an…

Conversational recommender systems have attracted immense attention recently. The most recent approaches rely on neural models trained on recorded dialogs between humans, implementing an end-to-end learning process. These systems are…

Fixed-vocabulary language models fail to account for one of the most characteristic statistical facts of natural language: the frequent creation and reuse of new word types. Although character-level language models offer a partial solution…

Large language models (LM) based on Transformers allow to generate plausible long texts. In this paper, we explore how this generation can be further controlled at decoding time to satisfy certain constraints (e.g. being non-toxic,…

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…

Yes! In the present-day documenting and preserving endangered languages, the application of Large Language Models (LLMs) presents a promising approach. This paper explores how LLMs, particularly through in-context learning, can assist in…

Speech-comprehension difficulties are common among older people. Standard speech tests do not fully capture such difficulties because the tests poorly resemble the context-rich, story-like nature of ongoing conversation and are typically…

Clustering is a fundamental tool that has garnered significant interest across a wide range of applications including text analysis. To improve clustering accuracy, many researchers have incorporated background knowledge, typically in the…

Lexically constrained text generation is one of the constrained text generation tasks, which aims to generate text that covers all the given constraint lexicons. While the existing approaches tackle this problem using a lexically…

The wave of pre-training language models has been continuously improving the quality of the machine-generated conversations, however, some of the generated responses still suffer from excessive repetition, sometimes repeating words from…

With the remarkable advancements in image generation and open-form text generation, the creation of interleaved image-text content has become an increasingly intriguing field. Multimodal story generation, characterized by producing…

Human languages differ widely in their forms, each having distinct sounds, scripts, and syntax. Yet, they can all convey similar meaning. Do different languages converge on a shared neural substrate for conceptual meaning? We used language…

Existing pre-trained large language models have shown unparalleled generative capabilities. However, they are not controllable. In this paper, we propose MEGATRON-CNTRL, a novel framework that uses large-scale language models and adds…

We propose a novel generative model to explore both local and global context for joint learning topics and topic-specific word embeddings. In particular, we assume that global latent topics are shared across documents, a word is generated…