paper-with-me

Papers

Collocation2Text: Controllable Text Generation from Guide Phrases in Russian

2022-06-18 · Sergey Vychegzhanin, Evgeny Kotelnikov

Large pre-trained language models are capable of generating varied and fluent texts. Starting from the prompt, these models generate a narrative that can develop unpredictably. The existing methods of controllable text generation, which guide the narrative in the text in the user-specified direction, require creating a training corpus and an additional time-consuming training procedure. The paper proposes and investigates Collocation2Text, a plug-and-play method for automatic controllable text generation in Russian, which does not require fine-tuning. The method is based on two interacting models: the autoregressive language ruGPT-3 model and the autoencoding language ruRoBERTa model. The idea of the method is to shift the output distribution of the autoregressive model according to the output distribution of the autoencoding model in order to ensure a coherent transition of the narrative in the text towards the guide phrase, which can contain single words or collocations. The autoencoding model, which is able to take into account the left and right contexts of the token, "tells" the autoregressive model which tokens are the most and least logical at the current generation step, increasing or decreasing the probabilities of the corresponding tokens. The experiments on generating news articles using the proposed method showed its effectiveness for automatically generated fluent texts which contain coherent transitions between user-specified phrases.

📄 PDF Abstract BibTeX arXiv:2206.09248

Code (0)

등록된 구현이 없습니다.

Tasks

ArticlesText Generation

Similar Papers 제목 키워드 기반

SceneFactor: Factored Latent 3D Diffusion for Controllable 3D Scene Generation

2024-12-02 · CVPR 2025 1 · Alexey Bokhovkin, Quan Meng, Shubham Tulsiani, Angela Dai

We present SceneFactor, a diffusion-based approach for large-scale 3D scene generation that enables controllable generation and effortless editing. SceneFactor enables text-guided 3D scene synthesis through our factored …

Scene Generation

Pay Attention when you Pay the Bills. A Multilingual Corpus with Dependency-based and Semantic Annotation of Collocations.

2019-07-01 · ACL 2019 7 · Marcos Garcia, Marcos Garc{\'\i}a Salido, Susana Sotelo, Estela Mosqueira 외

This paper presents a new multilingual corpus with semantic annotation of collocations in English, Portuguese, and Spanish. The whole resource contains 155k tokens and 1,526 collocations labeled in context. The annotated…

Natural Language UnderstandingText Generation

MReD: A Meta-Review Dataset for Structure-Controllable Text Generation

2021-11-16 · ACL ARR November 2021 11 · Anonymous

When directly using existing text generation datasets for controllable generation, we are facing the problem of not having the domain knowledge and thus the aspects that could be controlled are limited. A typical example…

Text GenerationText Summarization

MReD: A Meta-Review Dataset for Structure-Controllable Text Generation

2021-10-14 · Findings (ACL) 2022 5 · Chenhui Shen, Liying Cheng, Ran Zhou, Lidong Bing 외

When directly using existing text generation datasets for controllable generation, we are facing the problem of not having the domain knowledge and thus the aspects that could be controlled are limited. A typical example…

Text GenerationText Summarization

PG-CE: A Progressive Generation Dataset with Constraint Enhancement for Controllable Text Generation

2025-09-22 · Yan Zhuang, Yuan Sun arxiv

With the rapid development of Large Language Models (LLMs), Controllable Text Generation (CTG) has become a critical technology for enhancing system reliability and user experience. Addressing the limitations of traditio…

Text GenerationType prediction