Related papers: Top-Down Tree Structured Text Generation
Missing sentence generation (or sentence infilling) fosters a wide range of applications in natural language generation, such as document auto-completion and meeting note expansion. This task asks the model to generate intermediate missing…
Natural language generation (NLG) is a critical component in spoken dialogue systems. Classic NLG can be divided into two phases: (1) sentence planning: deciding on the overall sentence structure, (2) surface realization: determining…
Long story generation (LSG) is one of the coveted goals in natural language processing. Different from most text generation tasks, LSG requires to output a long story of rich content based on a much shorter text input, and often suffers…
Sentences produced by abstractive summarization systems can be ungrammatical and fail to preserve the original meanings, despite being locally fluent. In this paper we propose to remedy this problem by jointly generating a sentence and its…
Long document classification presents challenges in capturing both local and global dependencies due to their extensive content and complex structure. Existing methods often struggle with token limits and fail to adequately model…
This paper proposes new framework of communication system leveraging promising generation capabilities of multi-modal generative models. Regarding nowadays smart applications, successful communication can be made by conveying the perceptual…
In the last two decades, the landscape of text generation has undergone tremendous changes and is being reshaped by the success of deep learning. New technologies for text generation ranging from template-based methods to neural…
Text generation from a knowledge base aims to translate knowledge triples to natural language descriptions. Most existing methods ignore the faithfulness between a generated text description and the original table, leading to generated…
Natural language counterfactual generation aims to minimally modify a given text such that the modified text will be classified into a different class. The generated counterfactuals provide insight into the reasoning behind a model's…
We present a comparison of word-based and character-based sequence-to-sequence models for data-to-text natural language generation, which generate natural language descriptions for structured inputs. On the datasets of two recent generation…
Teaching neural models to generate narrative coherent texts is a critical problem. Recent pre-trained language models have achieved promising results, but there is still a gap between human written texts and machine-generated outputs. In…
Sequence generation applications require satisfying semantic constraints, such as ensuring that programs are correct, using certain keywords, or avoiding undesirable content. Language models, whether fine-tuned or prompted with few-shot…
Table-to-text generation refers to generating a descriptive text from a key-value table. Traditional autoregressive methods, though can generate text with high fluency, suffer from low coverage and poor faithfulness problems. To mitigate…
We propose to tackle data-to-text generation tasks by directly splicing together retrieved segments of text from "neighbor" source-target pairs. Unlike recent work that conditions on retrieved neighbors but generates text token-by-token,…
A number of researchers have recently questioned the necessity of increasingly complex neural network (NN) architectures. In particular, several recent papers have shown that simpler, properly tuned models are at least competitive across…
Building models that take advantage of the hierarchical structure of language without a priori annotation is a longstanding goal in natural language processing. We introduce such a model for the task of machine translation, pairing a…
We propose a recurrent neural model that generates natural-language questions from documents, conditioned on answers. We show how to train the model using a combination of supervised and reinforcement learning. After teacher forcing for…
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…
Large language models generate code one token at a time. Their autoregressive generation process lacks the feedback of observing the program's output. Training LLMs to suggest edits directly can be challenging due to the scarcity of rich…
Modeling the structure of coherent texts is a key NLP problem. The task of coherently organizing a given set of sentences has been commonly used to build and evaluate models that understand such structure. We propose an end-to-end…