首页/论文/2010.05511

arXiv 2010.055112020-10-12cs.CL

A Sentiment-Controllable Topic-to-Essay Generator with Topic Knowledge Graph

School of Software and Microelectronics, Peking University（北京大学软件与微电子学院）；Pattern Recognition Center, WeChat AI, Tencent Inc（腾讯公司微信人工智能模式识别中心）

Lin Qiao, Jianhao Yan, Fandong Meng, Zhendong Yang, Jie Zhou

备注：: Accepted as a regular paper in Findings of EMNLP 2020

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

Generating a vivid, novel, and diverse essay with only several given topic words is a challenging task of natural language generation. In previous work, there are two problems left unsolved: neglect of sentiment beneath the text and insufficient utilization of topic-related knowledge. Therefore, we propose a novel Sentiment-Controllable topic-to-essay generator with a Topic Knowledge Graph enhanced decoder, named SCTKG, which is based on the conditional variational autoencoder (CVAE) framework. We firstly inject the sentiment information into the generator for controlling sentiment for each sentence, which leads to various generated essays. Then we design a Topic Knowledge Graph enhanced decoder. Unlike existing models that use knowledge entities separately, our model treats the knowledge graph as a whole and encodes more structured, connected semantic information in the graph to generate a more relevant essay. Experimental results show that our SCTKG can generate sentiment controllable essays and outperform the state-of-the-art approach in terms of topic relevance, fluency, and diversity on both automatic and human evaluation.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Click：基于序列似然对比学习的可控文本生成

Click: Controllable Text Generation with Sequence Likelihood Contrastive Learning

Tsinghua University（清华大学）

本文提出 Click，通过序列似然对比损失和似然排序样本构建策略，在不修改架构的情况下提升语言模型的可控文本生成效果。

2023-06-06cs.CL

CAT-Gen: Improving Robustness in NLP Models via Controlled Adversarial Text Generation

University of Virginia（弗吉尼亚大学）；Google Research（谷歌研究院）

NLP models are shown to suffer from robustness issues, i.e., a model's prediction can be easily changed under small perturbations to the input. In this work, we present a Controlled Adversarial Text Generation (CAT-Gen) model that, given an input text, generates adversarial texts through controllable attributes that are known to be invariant to task labels. For example, in order to attack a model for sentiment classification over product reviews, we can use the product categories as the controllable attribute which would not change the sentiment of the reviews. Experiments on real-world NLP da…

2020-10-05cs.CL

Classifiers are Better Experts for Controllable Text Generation

Tinkoff（Tinkoff公司）

This paper proposes a simple method for controllable text generation based on weighting logits with a free-form classifier, namely CAIF sampling. Using an arbitrary text classifier, we adjust a small part of a language model's logits and guide text generation towards or away from classifier prediction. We experimented with toxicity avoidance and sentiment control tasks and showed that the proposed method significantly outperforms recent PPLM, GeDi, and DExperts on PPL and task accuracy metrics based on the external classifier of generated texts. In addition, compared to other approaches, it is…

2022-11-11cs.CLcs.LG

A Distributional Lens for Multi-Aspect Controllable Text Generation

Harbin Institute of Technology（哈尔滨工业大学）；Peng Cheng Laboratory（鹏城实验室）

Multi-aspect controllable text generation is a more challenging and practical task than single-aspect control. Existing methods achieve complex multi-aspect control by fusing multiple controllers learned from single-aspect, but suffer from attribute degeneration caused by the mutual interference of these controllers. To address this, we provide observations on attribute fusion from a distributional perspective and propose to directly search for the intersection areas of multiple attribute distributions as their combination for generation. Our method first estimates the attribute space with an …

2022-10-19cs.CL

SENSESHIFT：基于编码器的掩码填充实现连续情感控制文本生成

SENSESHIFT: Continuous Sentiment-Controlled Text Generation via Encoder-based Mask Infilling

Johannes Kepler University Linz（约翰开普勒林茨大学）；Thomson Reuters Labs（汤森路透实验室）；University of Toronto（多伦多大学）；Vector Institute（向量研究所）

该研究提出基于编码器的框架SenseShift，通过双向注意力等技术实现细粒度句子级情感控制文本生成，在故事与评论生成任务上，相比大解码器基线模型，情感可控性更强且文本质量与鲁棒性更优。

2026-08-26cs.AIcs.CL

Quark: Controllable Text Generation with Reinforced Unlearning

Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；Paul G. Allen School of Computer Science, University of Washington（华盛顿大学保罗·G·艾伦计算机科学学院）

Large-scale language models often learn behaviors that are misaligned with user expectations. Generated text may contain offensive or toxic language, contain significant repetition, or be of a different sentiment than desired by the user. We consider the task of unlearning these misalignments by fine-tuning the language model on signals of what not to do. We introduce Quantized Reward Konditioning (Quark), an algorithm for optimizing a reward function that quantifies an (un)wanted property, while not straying too far from the original model. Quark alternates between (i) collecting samples with…

2022-11-16cs.CLcs.LG

更多相关论文收起更多论文

Diffusion-LM Improves Controllable Text Generation

Stanford University（斯坦福大学）

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 has been little progress on complex, fine-grained controls (e.g., syntactic structure). To address this challenge, we develop a new non-autoregressive language model based on continuous diffusions that we call Diffusion-LM. Building upon the recent successes of diffusion models in continuous domains, Diffusion-LM iteratively denoises a sequence of Gaussian v…

2022-05-27cs.AIcs.CLcs.LG

EdiText：基于扩散语言模型的可控由粗到细文本编辑

EdiText: Controllable Coarse-to-Fine Text Editing with Diffusion Language Models

Department of Electrical and Computer Engineering, Seoul National University（电子与计算机工程系，首尔国立大学）；AIIS, ASRI, INMC, ISRC, and IPAI, Seoul National University（人工智能研究所、先进系统研究室、智能网络中心、信息科学研究中心和人工智能计划，首尔国立大学）

本文提出 EdiText，结合 SDEdit 与自条件化细粒度编辑方法，实现由粗到细的可控文本编辑，在毒性与情感控制等任务中展现出广泛且精确的属性调整能力。

2025-06-02cs.CLcs.LG

基于解耦反事实增强的多方面可控文本生成

Multi-Aspect Controllable Text Generation with Disentangled Counterfactual Augmentation

Nanjing University（南京大学）；National Institute of Healthcare Data Science, Nanjing University（南京大学国家医疗数据科学研究院）

针对多方面可控文本生成中因属性相关性不平衡导致的刻板印象问题，提出MAGIC方法，通过解耦反事实增强缓解训练阶段的不平衡并在推理阶段强化属性相关性，在多种场景下优于基线。

2024-05-30cs.AIcs.CL

Investigation of Sentiment Controllable Chatbot

National Taiwan University（台湾大学）

Conventional seq2seq chatbot models attempt only to find sentences with the highest probabilities conditioned on the input sequences, without considering the sentiment of the output sentences. In this paper, we investigate four models to scale or adjust the sentiment of the chatbot response: a persona-based model, reinforcement learning, a plug and play model, and CycleGAN, all based on the seq2seq model. We also develop machine-evaluated metrics to estimate whether the responses are reasonable given the input. These metrics, together with human evaluation, are used to analyze the performance …

2020-07-11cs.AIcs.CL

一种用于多方面可控文本生成的可扩展即插即用方法

An Extensible Plug-and-Play Method for Multi-Aspect Controllable Text Generation

Meituan（美团）；Tsinghua University（清华大学）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）

本文针对多方面可控文本生成中多前缀相互干扰的问题，提出基于可训练门控归一化前缀干预的即插即用方法，实现训练时未见方面组合的低成本扩展，并统一处理类别型与自由形式约束，在约束准确率、文本质量和可扩展性上优于基线。

2023-05-28cs.AIcs.CL

Plug and Play Language Models: A Simple Approach to Controlled Text Generation

Caltech（加州理工学院）；HKUST（香港科技大学）；Uber AI（优步AI）

Large transformer-based language models (LMs) trained on huge text corpora have shown unparalleled generation capabilities. However, controlling attributes of the generated language (e.g. switching topic or sentiment) is difficult without modifying the model architecture or fine-tuning on attribute-specific data and entailing the significant cost of retraining. We propose a simple alternative: the Plug and Play Language Model (PPLM) for controllable language generation, which combines a pretrained LM with one or more simple attribute classifiers that guide text generation without any further t…

2020-03-03cs.AIcs.CLcs.LG

Computational analyses of the topics, sentiments, literariness, creativity and beauty of texts in a large Corpus of English Literature

Freie Universität Berlin（柏林自由大学）

The Gutenberg Literary English Corpus (GLEC, Jacobs, 2018a) provides a rich source of textual data for research in digital humanities, computational linguistics or neurocognitive poetics. In this study we address differences among the different literature categories in GLEC, as well as differences between authors. We report the results of three studies providing i) topic and sentiment analyses for six text categories of GLEC (i.e., children and youth, essays, novels, plays, poems, stories) and its >100 authors, ii) novel measures of semantic complexity as indices of the literariness, creativit…

2022-01-12cs.CL