中文
相关论文

相关论文: Maximizing Stylistic Control and Semantic Accuracy…

200 篇论文

Natural language generators for task-oriented dialogue must effectively realize system dialogue actions and their associated semantics. In many applications, it is also desirable for generators to control the style of an utterance. To date,…

计算与语言 · 计算机科学 2018-05-23 Shereen Oraby , Lena Reed , Shubhangi Tandon , T. S. Sharath , Stephanie Lukin , Marilyn Walker

Natural Language Generation (NLG) for task-oriented dialogue systems focuses on communicating specific content accurately, fluently, and coherently. While these attributes are crucial for a successful dialogue, it is also desirable to…

Neural natural language generation (NNLG) from structured meaning representations has become increasingly popular in recent years. While we have seen progress with generating syntactically correct utterances that preserve semantics, various…

计算与语言 · 计算机科学 2019-06-18 Shereen Oraby , Vrindavan Harrison , Abteen Ebrahimi , Marilyn Walker

One of the biggest challenges of end-to-end language generation from meaning representations in dialogue systems is making the outputs more natural and varied. Here we take a large corpus of 50K crowd-sourced utterances in the restaurant…

计算与语言 · 计算机科学 2018-09-17 Juraj Juraska , Marilyn Walker

Prompt-based or in-context learning has achieved high zero-shot performance on many natural language generation (NLG) tasks. Here we explore the performance of prompt-based learning for simultaneously controlling the personality and the…

计算与语言 · 计算机科学 2023-02-09 Angela Ramirez , Mamon Alsalihy , Kartik Aggarwal , Cecilia Li , Liren Wu , Marilyn Walker

Most work on neural natural language generation (NNLG) focus on controlling the content of the generated text. We experiment with controlling several stylistic aspects of the generated text, in addition to its content. The method is based…

计算与语言 · 计算机科学 2017-07-11 Jessica Ficler , Yoav Goldberg

Automated evaluation of open domain natural language generation (NLG) models remains a challenge and widely used metrics such as BLEU and Perplexity can be misleading in some cases. In our paper, we propose to evaluate natural language…

计算与语言 · 计算机科学 2020-02-13 Wangchunshu Zhou , Ke Xu

Natural language generators (NLGs) for task-oriented dialogue typically take a meaning representation (MR) as input. They are trained end-to-end with a corpus of MR/utterance pairs, where the MRs cover a specific set of dialogue acts and…

计算与语言 · 计算机科学 2020-10-02 Lena Reed , Vrindavan Harrison , Shereen Oraby , Dilek Hakkani-Tur , Marilyn Walker

Natural language generators for task-oriented dialog should be able to vary the style of the output utterance while still effectively realizing the system dialog actions and their associated semantics. While the use of neural generation for…

计算与语言 · 计算机科学 2018-09-06 Shereen Oraby , Lena Reed , Sharath TS , Shubhangi Tandon , Marilyn Walker

Recent advances in large pre-trained language models have demonstrated strong results in generating natural languages and significantly improved performances for many natural language generation (NLG) applications such as machine…

计算与语言 · 计算机科学 2022-09-27 Nanyun Peng

With the surge of large language models (LLMs) and their ability to produce customized output, style-personalized text generation--"write like me"--has become a rapidly growing area of interest. However, style personalization is highly…

计算与语言 · 计算机科学 2025-10-16 Anubhav Jangra , Bahareh Sarrafzadeh , Silviu Cucerzan , Adrian de Wynter , Sujay Kumar Jauhar

Neural natural language generation (NNLG) systems are known for their pathological outputs, i.e. generating text which is unrelated to the input specification. In this paper, we show the impact of semantic noise on state-of-the-art NNLG…

计算与语言 · 计算机科学 2019-11-12 Ondřej Dušek , David M. Howcroft , Verena Rieser

Natural language generation (NLG) is a critical component of spoken dialogue and it has a significant impact both on usability and perceived quality. Most NLG systems in common use employ rules and heuristics and tend to generate rigid and…

计算与语言 · 计算机科学 2015-08-27 Tsung-Hsien Wen , Milica Gasic , Nikola Mrksic , Pei-Hao Su , David Vandyke , Steve Young

Neural natural language generation (NLG) models have recently shown remarkable progress in fluency and coherence. However, existing studies on neural NLG are primarily focused on surface-level realizations with limited emphasis on logical…

计算与语言 · 计算机科学 2020-04-29 Wenhu Chen , Jianshu Chen , Yu Su , Zhiyu Chen , William Yang Wang

The natural language generation (NLG) module in a task-oriented dialogue system produces user-facing utterances conveying required information. Thus, it is critical for the generated response to be natural and fluent. We propose to…

计算与语言 · 计算机科学 2020-05-07 Chenguang Zhu

Discourse coherence plays an important role in the translation of one text. However, the previous reported models most focus on improving performance over individual sentence while ignoring cross-sentence links and dependencies, which…

计算与语言 · 计算机科学 2018-11-15 Hao Xiong , Zhongjun He , Hua Wu , Haifeng Wang

As the text generation capabilities of large language models become increasingly prominent, recent studies have focused on controlling particular aspects of the generated text to make it more personalized. However, most research on…

计算与语言 · 计算机科学 2024-02-08 Bashar Alhafni , Vivek Kulkarni , Dhruv Kumar , Vipul Raheja

Natural Language Generation (NLG) refers to the operation of expressing the calculation results of a system in human language. Since the quality of generated sentences from an NLG model cannot be fully represented using only quantitative…

计算与语言 · 计算机科学 2022-08-04 Dojun Park , Youngjin Jang , Harksoo Kim

Neural models trained for next utterance generation in dialogue task learn to mimic the n-gram sequences in the training set with training objectives like negative log-likelihood (NLL) or cross-entropy. Such commonly used training…

计算与语言 · 计算机科学 2021-06-22 Prasanna Parthasarathi , Mohamed Abdelsalam , Joelle Pineau , Sarath Chandar

Natural language generation (NLG) systems are commonly evaluated using n-gram overlap measures (e.g. BLEU, ROUGE). These measures do not directly capture semantics or speaker intentions, and so they often turn out to be misaligned with our…

计算与语言 · 计算机科学 2019-10-14 Benjamin Newman , Reuben Cohn-Gordon , Christopher Potts
‹ 上一页 1 2 3 10 下一页 ›