paper-with-me

Papers

Rhetorically Controlled Encoder-Decoder for Modern Chinese Poetry Generation

2019-07-01 · ACL 2019 7 · Zhi-Qiang Liu, Zuohui Fu, Jie Cao, Gerard de Melo, Yik-Cheung Tam, Cheng Niu, Jie zhou

Rhetoric is a vital element in modern poetry, and plays an essential role in improving its aesthetics. However, to date, it has not been considered in research on automatic poetry generation. In this paper, we propose a rhetorically controlled encoder-decoder for modern Chinese poetry generation. Our model relies on a continuous latent variable as a rhetoric controller to capture various rhetorical patterns in an encoder, and then incorporates rhetoric-based mixtures while generating modern Chinese poetry. For metaphor and personification, an automated evaluation shows that our model outperforms state-of-the-art baselines by a substantial margin, while human evaluation shows that our model generates better poems than baseline methods in terms of fluency, coherence, meaningfulness, and rhetorical aesthetics.

📄 PDF Abstract BibTeX

Code (1)

Lucien-qiang/Rhetoric-Generator 공식 구현 tf

Tasks

Decoder

Similar Papers 제목 키워드 기반

Full Glyph Images Beat Token Embeddings: A Controlled Study for Transformers

2026-07-04 · Shuyang Xiang, Hao Guan arxiv

Modern language models generally represent text as sequences of discrete token embeddings, an assumption deeply rooted in current practice but rarely questioned. We challenge this representation, especially for Chinese, …

ModernGBERT: German-only 1B Encoder Model Trained from Scratch

2025-05-19 · Anton Ehrmanntraut, Julia Wunderle, Jan Pfister, Fotis Jannidis 외

Despite the prominence of decoder-only language models, encoders remain crucial for resource-constrained applications. We introduce ModernGBERT (134M, 1B), a fully transparent family of German encoder models trained from…

DecoderNatural Language Understanding

Chinese ModernBERT with Whole-Word Masking

2025-10-14 · Zeyu Zhao, Ningtao Wang, Xing Fu, Yu Cheng arxiv

Encoder-only Transformers have advanced along three axes -- architecture, data, and systems -- yielding Pareto gains in accuracy, speed, and memory efficiency. Yet these improvements have not fully transferred to Chinese…

Generating Chinese Classical Poems with RNN Encoder-Decoder

2016-04-06 · Xiaoyuan Yi, Ruoyu Li, Maosong Sun

We take the generation of Chinese classical poem lines as a sequence-to-sequence learning problem, and build a novel system based on the RNN Encoder-Decoder structure to generate quatrains (Jueju in Chinese), with a topi…

Decoder

A New Approach to Accent Recognition and Conversion for Mandarin Chinese

2020-08-07 · Lin Ai, Shih-Ying Jeng, Homayoon Beigi

Two new approaches to accent classification and conversion are presented and explored, respectively. The first topic is Chinese accent classification/recognition. The second topic is the use of encoder-decoder models for…

Decoder