Related papers: MOCHA: A Multi-Task Training Approach for Coherent…

In recent years, with the development of deep learning, text generation technology has undergone great changes and provided many kinds of services for human beings, such as restaurant reservation and daily communication. The automatically…

Building robust and general dialogue models for spoken conversations is challenging due to the gap in distributions of spoken and written data. This paper presents our approach to build generalized models for the Knowledge-grounded…

Recent work on evaluating the diversity of text generated by LLMs has focused on word-level features. Here we offer an analysis of syntactic features to characterize general repetition in models, beyond frequent n-grams. Specifically, we…

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…

This article presents a hybrid approach based on a Grounded Text Generation (GTG) model to building robust task bots at scale. GTG is a hybrid model which uses a large-scale Transformer neural network as its backbone, combined with…

Language models have demonstrated the ability to generate highly fluent text; however, it remains unclear whether their output retains coherent high-level structure (e.g., story progression). Here, we propose to apply a statistical tool,…

Recently, neural approaches to coherence modeling have achieved state-of-the-art results in several evaluation tasks. However, we show that most of these models often fail on harder tasks with more realistic application scenarios. In…

We propose a novel method for generating titles for unstructured text documents. We reframe the problem as a sequential question-answering task. A deep neural network is trained on document-title pairs with decomposable titles, meaning that…

Coherence is a linguistic term that refers to the relations between small textual units (sentences, propositions), which make the text logically consistent and meaningful to the reader. With the advances of generative foundational models in…

Neural text generation metamorphosed into several critical natural language applications ranging from text completion to free form narrative generation. In order to progress research in text generation, it is critical to absorb the existing…

In text-to-motion generation, controllability as well as generation quality and speed has become increasingly critical. The controllability challenges include generating a motion of a length that matches the given textual description and…

Neural text generation is a key tool in natural language applications, but it is well known there are major problems at its core. In particular, standard likelihood training and decoding leads to dull and repetitive outputs. While some…

Advancements in language foundation models have primarily fueled the recent surge in artificial intelligence. In contrast, generative learning of non-textual modalities, especially videos, significantly trails behind language modeling. This…

Recent advancements in large scale text-to-image models have opened new possibilities for guiding the creation of images through human-devised natural language. However, while prior literature has primarily focused on the generation of…

Large pre-trained language models are capable of generating varied and fluent texts. Starting from the prompt, these models generate a narrative that can develop unpredictably. The existing methods of controllable text generation, which…

Providing pretrained language models with simple task descriptions in natural language enables them to solve some tasks in a fully unsupervised fashion. Moreover, when combined with regular learning from examples, this idea yields…

The rapid dissemination of misinformation through social media increased the importance of automated fact-checking. Furthermore, studies on what deep neural models pay attention to when making predictions have increased in recent years.…

An ideal detection system for machine generated content is supposed to work well on any generator as many more advanced LLMs come into existence day by day. Existing systems often struggle with accurately identifying AI-generated content…

Past work on story generation has demonstrated the usefulness of conditioning on a generation plan to generate coherent stories. However, these approaches have used heuristics or off-the-shelf models to first tag training stories with the…

Generating video stories from text prompts is a complex task. In addition to having high visual quality, videos need to realistically adhere to a sequence of text prompts whilst being consistent throughout the frames. Creating a benchmark…