Natural language generation ≈ Natural language generation
View article
Unified Language Model Pre-training for Natural Language Understanding and Generation Open
This paper presents a new Unified pre-trained Language Model (UniLM) that can be fine-tuned for both natural language understanding and generation tasks. The model is pre-trained using three types of language modeling tasks: unidirectional…
View article
Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation Open
This paper surveys the current state of the art in Natural Language Generation (NLG), defined as the task of generating text or speech from non-linguistic input. A survey of NLG is timely in view of the changes that the field has undergone…
View article
Learning to Ask: Neural Question Generation for Reading Comprehension Open
We study automatic question generation for sentences from text passages in reading comprehension. We introduce an attention-based sequence learning model for the task and investigate the effect of encoding sentence- vs. paragraph-level inf…
View article
G-Eval: NLG Evaluation using Gpt-4 with Better Human Alignment Open
The quality of texts generated by natural language generation (NLG) systems is hard to measure automatically. Conventional reference-based metrics, such as BLEU and ROUGE, have been shown to have relatively low correlation with human judgm…
View article
Wordcraft: Story Writing With Large Language Models Open
The latest generation of large neural language models such as GPT-3 have achieved new levels of performance on benchmarks for language understanding and generation. These models have even demonstrated an ability to perform arbitrary tasks …
View article
Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model Open
Pretrained general-purpose language models can achieve state-of-the-art accuracies in various natural language processing domains by adapting to downstream tasks via zero-shot, few-shot and fine-tuning techniques. Because of their success,…
View article
e-SNLI: Natural Language Inference with Natural Language Explanations Open
In order for machine learning to garner widespread public adoption, models must be able to provide interpretable and robust explanations for their decisions, as well as learn from human-provided explanations at train time. In this work, we…
View article
Plan-and-Write: Towards Better Automatic Storytelling Open
Automatic storytelling is challenging since it requires generating long, coherent natural language to describes a sensible sequence of events. Despite considerable efforts on automatic story generation in the past, prior work either is res…
View article
Diffusion-LM Improves Controllable Text Generation Open
Controlling the behavior of language models (LMs) without re-training is a major open problem in natural language generation. While recent works have demonstrated successes on controlling simple sentence attributes (e.g., sentiment), there…
View article
A Survey of Knowledge-enhanced Text Generation Open
The goal of text-to-text generation is to make machines express like a human in many applications such as conversation, summarization, and translation. It is one of the most important yet challenging tasks in natural language processing (N…
View article
Is ChatGPT a Good NLG Evaluator? A Preliminary Study Open
Recently, the emergence of ChatGPT has attracted wide attention from the computational linguistics community. Many prior studies have shown that ChatGPT achieves remarkable performance on various NLP tasks in terms of automatic evaluation …
View article
Evaluation of Text Generation: A Survey Open
The paper surveys evaluation methods of natural language generation (NLG) systems that have been developed in the last few years. We group NLG evaluation methods into three categories: (1) human-centric evaluation metrics, (2) automatic me…
View article
Best practices for the human evaluation of automatically generated text Open
Currently, there is little agreement as to how Natural Language Generation (NLG) systems should be evaluated. While there is some agreement regarding automatic metrics, there is a high degree of variation in the way that human evaluation i…
View article
Automated rationale generation Open
Explainable AI Dataset for paper published in the proceedings of IUI 2019 titled, "Automated rationale generation: a technique for explainable AI and its effects on human perceptions". Consists of data collected from human participants via…
View article
Relevance of Unsupervised Metrics in Task-Oriented Dialogue for Evaluating Natural Language Generation Open
Automated metrics such as BLEU are widely used in the machine translation literature. They have also been used recently in the dialogue community for evaluating dialogue response generation. However, previous work in dialogue response gene…
View article
Chat2VIS: Generating Data Visualizations via Natural Language Using ChatGPT, Codex and GPT-3 Large Language Models Open
The field of data visualisation has long aimed to devise solutions for generating visualisations directly from natural language text. Research in Natural Language Interfaces (NLIs) has contributed towards the development of such techniques…
View article
A Comprehensive Study of ChatGPT: Advancements, Limitations, and Ethical Considerations in Natural Language Processing and Cybersecurity Open
This paper presents an in-depth study of ChatGPT, a state-of-the-art language model that is revolutionizing generative text. We provide a comprehensive analysis of its architecture, training data, and evaluation metrics and explore its adv…
View article
SentiGAN: Generating Sentimental Texts via Mixture Adversarial Networks Open
Generating texts of different sentiment labels is getting more and more attention in the area of natural language generation. Recently, Generative Adversarial Net (GAN) has shown promising results in text generation. However, the texts gen…
View article
Unifying Human and Statistical Evaluation for Natural Language Generation Open
Tatsunori B. Hashimoto, Hugh Zhang, Percy Liang. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 2019.
View article
Leveraging Context Information for Natural Question Generation Open
Linfeng Song, Zhiguo Wang, Wael Hamza, Yue Zhang, Daniel Gildea. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers). 2018.
View article
Affect-LM: A Neural Language Model for Customizable Affective Text Generation Open
Human verbal communication includes affective messages which are conveyed through use of emotionally colored words. There has been a lot of research effort in this direction but the problem of integrating state-of-the-art neural language m…
View article
Few-shot Natural Language Generation for Task-Oriented Dialog Open
As a crucial component in task-oriented dialog systems, the Natural Language Generation (NLG) module converts a dialog act represented in a semantic form into a response in natural language. The success of traditional template-based or sta…
View article
Event Representations for Automated Story Generation with Deep Neural Nets Open
Automated story generation is the problem of automatically selecting a sequence of events, actions, or words that can be told as a story. We seek to develop a system that can generate stories by learning everything it needs to know from te…
View article
Toward Controlled Generation of Text Open
Generic generation and manipulation of text is challenging and has limited success compared to recent deep generative modeling in visual domain. This paper aims at generating plausible natural language sentences, whose attributes are dynam…
View article
The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics Open
International audience
View article
CGMH: Constrained Sentence Generation by Metropolis-Hastings Sampling Open
In real-world applications of natural language generation, there are often constraints on the target sentences in addition to fluency and naturalness requirements. Existing language generation techniques are usually based on recurrent neur…
View article
A Pre-Training Based Personalized Dialogue Generation Model with Persona-Sparse Data Open
Endowing dialogue systems with personas is essential to deliver more human-like conversations. However, this problem is still far from well explored due to the difficulties of both embodying personalities in natural languages and the perso…
View article
Human evaluation of automatically generated text: Current trends and best practice guidelines Open
Currently, there is little agreement as to how Natural Language Generation (NLG) systems should be evaluated, with a particularly high degree of variation in the way that human evaluation is carried out. This paper provides an overview of …
View article
Cross-Lingual Natural Language Generation via Pre-Training Open
In this work we focus on transferring supervision signals of natural language generation (NLG) tasks between multiple languages. We propose to pretrain the encoder and the decoder of a sequence-to-sequence model under both monolingual and …
View article
Keep Meeting Summaries on Topic: Abstractive Multi-Modal Meeting Summarization Open
Transcripts of natural, multi-person meetings differ significantly from documents like news articles, which can make Natural Language Generation models for generating summaries unfocused. We develop an abstractive meeting summarizer from b…