中文
相关论文

相关论文: Characterizing Variation in Crowd-Sourced Data for…

200 篇论文

Responses in task-oriented dialogue systems often realize multiple propositions whose ultimate form depends on the use of sentence planning and discourse structuring operations. For example a recommendation may consist of an explicitly…

计算与语言 · 计算机科学 2018-11-05 Lena Reed , Shereen Oraby , Marilyn Walker

Text generation from semantic graphs is traditionally performed with deterministic methods, which generate a unique description given an input graph. However, the generation problem admits a range of acceptable textual outputs, exhibiting…

计算与语言 · 计算机科学 2021-08-16 Jiuzhou Han , Daniel Beck , Trevor Cohn

Sequence labeling is an important technique employed for many Natural Language Processing (NLP) tasks, such as Named Entity Recognition (NER), slot tagging for dialog systems and semantic parsing. Large-scale pre-trained language models…

计算与语言 · 计算机科学 2020-12-14 Yaqing Wang , Subhabrata Mukherjee , Haoda Chu , Yuancheng Tu , Ming Wu , Jing Gao , Ahmed Hassan Awadallah

Large Transformer-based language models can aid human authors by suggesting plausible continuations of text written so far. However, current interactive writing assistants do not allow authors to guide text generation in desired topical…

计算与语言 · 计算机科学 2021-03-30 Haw-Shiuan Chang , Jiaming Yuan , Mohit Iyyer , Andrew McCallum

Collecting human judgements is currently the most reliable evaluation method for natural language generation systems. Automatic metrics have reported flaws when applied to measure quality aspects of generated text and have been shown to…

计算与语言 · 计算机科学 2022-04-29 Thórhildur Thorleiksdóttir , Cedric Renggli , Nora Hollenstein , Ce Zhang

This paper addresses the task of generating fluent descriptions by training on a non-uniform combination of data sources, containing both human-annotated and web-collected captions. Large-scale datasets with noisy image-text pairs, indeed,…

计算机视觉与模式识别 · 计算机科学 2023-12-01 Marcella Cornia , Lorenzo Baraldi , Giuseppe Fiameni , Rita Cucchiara

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

Knowledge-grounded dialogue systems are intended to convey information that is based on evidence provided in a given source text. We discuss the challenges of training a generative neural dialogue model for such systems that is controlled…

计算与语言 · 计算机科学 2021-07-16 Hannah Rashkin , David Reitter , Gaurav Singh Tomar , Dipanjan Das

The spontaneous behavior that often occurs in conversations makes speech more human-like compared to reading-style. However, synthesizing spontaneous-style speech is challenging due to the lack of high-quality spontaneous datasets and the…

声音 · 计算机科学 2023-09-01 Weiqin Li , Shun Lei , Qiaochu Huang , Yixuan Zhou , Zhiyong Wu , Shiyin Kang , Helen Meng

Natural language serves as a common and straightforward signal for humans to interact seamlessly with machines. Recognizing the importance of this interface, the machine learning community is investing considerable effort in generating data…

计算与语言 · 计算机科学 2025-01-03 Shiyu Wang , Yihao Feng , Tian Lan , Ning Yu , Yu Bai , Ran Xu , Huan Wang , Caiming Xiong , Silvio Savarese

Recent advances in large language models have created new opportunities for stylometry, the study of writing styles and authorship. Two challenges, however, remain central: training generative models when no paired data exist, and…

计算与语言 · 计算机科学 2025-11-26 Mosab Rezaei , Mina Rajaei Moghadam , Abdul Rahman Shaikh , Hamed Alhoori , Reva Freedman

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…

计算与语言 · 计算机科学 2024-10-08 Yongjie Wang , Xiaoqi Qiu , Yu Yue , Xu Guo , Zhiwei Zeng , Yuhong Feng , Zhiqi Shen

Machine learning approaches to multi-label document classification have to date largely relied on discriminative modeling techniques such as support vector machines. A drawback of these approaches is that performance rapidly drops off as…

机器学习 · 统计学 2011-11-11 Timothy N. Rubin , America Chambers , Padhraic Smyth , Mark Steyvers

Large Language Models (LLMs) are now capable of generating highly fluent, human-like text. They enable many applications, but also raise concerns such as large scale spam, phishing, or academic misuse. While much work has focused on…

计算与语言 · 计算机科学 2026-04-16 Swati Rallapalli , Shannon Gallagher , Ronald Yurko , Tyler Brooks , Chuck Loughin , Michele Sezgin , Violet Turri

Today's probabilistic language generators fall short when it comes to producing coherent and fluent text despite the fact that the underlying models perform well under standard metrics, e.g., perplexity. This discrepancy has puzzled the…

计算与语言 · 计算机科学 2025-06-06 Clara Meister , Tiago Pimentel , Gian Wiher , Ryan Cotterell

We study the problem of generating source code in a strongly typed, Java-like programming language, given a label (for example a set of API calls or types) carrying a small amount of information about the code that is desired. The generated…

编程语言 · 计算机科学 2018-04-16 Vijayaraghavan Murali , Letao Qi , Swarat Chaudhuri , Chris Jermaine

Neural conversation models tend to generate safe, generic responses for most inputs. This is due to the limitations of likelihood-based decoding objectives in generation tasks with diverse outputs, such as conversation. To address this…

计算与语言 · 计算机科学 2018-09-06 Ashutosh Baheti , Alan Ritter , Jiwei Li , Bill Dolan

The extensive use of online social media has highlighted the importance of privacy in the digital space. As more scientists analyse the data created in these platforms, privacy concerns have extended to data usage within the academia.…

人机交互 · 计算机科学 2022-03-04 Giannis Haralabopoulos , Ioannis Anagnostopoulos

Text style transfer is an exciting task within the field of natural language generation that is often plagued by the need for high-quality paired datasets. Furthermore, training a model for multi-attribute text style transfer requires…

计算与语言 · 计算机科学 2023-05-26 Debarati Das , David Ma , Dongyeop Kang

We study the problem of generating interesting endings for stories. Neural generative models have shown promising results for various text generation problems. Sequence to Sequence (Seq2Seq) models are typically trained to generate a single…

机器学习 · 计算机科学 2019-07-22 Prakhar Gupta , Vinayshekhar Bannihatti Kumar , Mukul Bhutani , Alan W Black