中文
相关论文

相关论文: Maximizing Stylistic Control and Semantic Accuracy…

200 篇论文

The performance of Large Language Models (LLMs) degrades from the temporal drift between data used for model training and newer text seen during inference. One understudied avenue of language change causing data drift is the emergence of…

计算与语言 · 计算机科学 2024-08-14 Jonathan Zheng , Alan Ritter , Wei Xu

In recent years, machine learning - particularly deep learning - has significantly impacted the field of information management. While several strategies have been proposed to restrict models from learning and memorizing sensitive…

计算与语言 · 计算机科学 2024-07-10 Jiajia Li , Lu Yang , Letian Peng , Shitou Zhang , Ping Wang , Zuchao Li , Hai Zhao

In modular dialogue systems, natural language understanding (NLU) and natural language generation (NLG) are two critical components, where NLU extracts the semantics from the given texts and NLG is to construct corresponding natural…

计算与语言 · 计算机科学 2020-05-01 Shang-Yu Su , Chao-Wei Huang , Yun-Nung Chen

Recent studies of the emergent capabilities of transformer-based Natural Language Understanding (NLU) models have indicated that they have an understanding of lexical and compositional semantics. We provide evidence that suggests these…

计算与语言 · 计算机科学 2024-02-01 Erik Arakelyan , Zhaoqi Liu , Isabelle Augenstein

Conversational data is essential in psychology because it can help researchers understand individuals cognitive processes, emotions, and behaviors. Utterance labelling is a common strategy for analyzing this type of data. The development of…

计算与语言 · 计算机科学 2022-08-16 Maria Laricheva , Chiyu Zhang , Yan Liu , Guanyu Chen , Terence Tracey , Richard Young , Giuseppe Carenini

Large language models have shown unprecedented abilities in generating linguistically coherent and syntactically correct natural language output. However, they often return incorrect and inconsistent answers to input questions. Due to the…

数据库 · 计算机科学 2023-12-27 Jasmin Mousavi , Arash Termehchy

Human creativity generates novel ideas to solve real-world problems. This thereby grants us the power to transform the surrounding world and extend our human attributes beyond what is currently possible. Creative ideas are not just new and…

计算与语言 · 计算机科学 2021-06-21 Georgi V. Georgiev , Danko D. Georgiev

AIVisor, an agentic retrieval-augmented LLM for student advising, was used to examine how personalization affects system performance across multiple evaluation dimensions. Using twelve authentic advising questions intentionally designed to…

信息检索 · 计算机科学 2026-05-19 Satyajit Movidi , Stephen Russell

Despite the remarkable advances in language modeling, current mainstream decoding methods still struggle to generate texts that align with human texts across different aspects. In particular, sampling-based methods produce less-repetitive…

计算与语言 · 计算机科学 2024-06-06 Haozhe Ji , Pei Ke , Hongning Wang , Minlie Huang

Model-based, reference-free evaluation metrics have been proposed as a fast and cost-effective approach to evaluate Natural Language Generation (NLG) systems. Despite promising recent results, we find evidence that reference-free evaluation…

计算与语言 · 计算机科学 2022-04-22 Esin Durmus , Faisal Ladhak , Tatsunori Hashimoto

Current approaches to phrase break prediction address crucial prosodic aspects of text-to-speech systems but heavily rely on vast human annotations from audio or text, incurring significant manual effort and cost. Inherent variability in…

计算与语言 · 计算机科学 2025-07-25 Hoyeon Lee , Sejung Son , Ye-Eun Kang , Jong-Hwan Kim

A Large Language Model (LLM) tends to generate inconsistent and sometimes contradictory outputs when presented with a prompt that has equivalent semantics but is expressed differently from the original prompt. To achieve semantic…

计算与语言 · 计算机科学 2025-01-22 Jingyuan Yang , Dapeng Chen , Yajing Sun , Rongjun Li , Zhiyong Feng , Wei Peng

Most research about natural language generation (NLG) relies on evaluation benchmarks with limited references for a sample, which may result in poor correlations with human judgements. The underlying reason is that one semantic meaning can…

计算与语言 · 计算机科学 2024-05-28 Tianyi Tang , Hongyuan Lu , Yuchen Eleanor Jiang , Haoyang Huang , Dongdong Zhang , Wayne Xin Zhao , Tom Kocmi , Furu Wei

Controllable text generation systems often leverage control codes to direct various properties of the output like style and length. Inspired by recent work on causal inference for NLP, this paper reveals a previously overlooked flaw in…

计算与语言 · 计算机科学 2022-10-10 Junyi Chai , Reid Pryzant , Victor Ye Dong , Konstantin Golobokov , Chenguang Zhu , Yi Liu

This thesis investigates the controllability of deep learning-based, end-to-end, generative dialogue systems in both task-oriented and chit-chat scenarios. In particular, we study the different aspects of controlling generative dialogue…

计算与语言 · 计算机科学 2021-08-25 Andrea Madotto

This paper introduces an innovative task focused on editing the personality traits of Large Language Models (LLMs). This task seeks to adjust the models' responses to opinion-related questions on specified topics since an individual's…

计算与语言 · 计算机科学 2024-09-04 Shengyu Mao , Xiaohan Wang , Mengru Wang , Yong Jiang , Pengjun Xie , Fei Huang , Ningyu Zhang

A major challenge in evaluating data-to-text (D2T) generation is measuring the semantic accuracy of the generated text, i.e. checking if the output text contains all and only facts supported by the input data. We propose a new metric for…

计算与语言 · 计算机科学 2020-11-24 Ondřej Dušek , Zdeněk Kasner

Controllable text generation is a challenging and meaningful field in natural language generation (NLG). Especially, poetry generation is a typical one with well-defined and strict conditions for text generation which is an ideal playground…

计算与语言 · 计算机科学 2023-12-20 Zhiyuan Hu , Chumin Liu , Yue Feng , Anh Tuan Luu , Bryan Hooi

While NLP models often seek to capture cognitive states via language, the validity of predicted states is determined by comparing them to annotations created without access the cognitive states of the authors. In behavioral sciences,…

We present a neural model for paraphrasing and train it to generate delexicalized sentences. We achieve this by creating training data in which each input is paired with a number of reference paraphrases. These sets of reference paraphrases…

计算与语言 · 计算机科学 2020-12-07 Boya Yu , Konstantine Arkoudas , Wael Hamza
‹ 上一页 1 8 9 10 下一页 ›