paper-with-me

홈 › Papers

How Sequence-to-Sequence Models Perceive Language Styles?

2019-08-16 · Ruozi Huang, Mi Zhang, Xudong Pan, Beina Sheng

Style is ubiquitous in our daily language uses, while what is language style to learning machines? In this paper, by exploiting the second-order statistics of semantic vectors of different corpora, we present a novel perspective on this question via style matrix, i.e. the covariance matrix of semantic vectors, and explain for the first time how Sequence-to-Sequence models encode style information innately in its semantic vectors. As an application, we devise a learning-free text style transfer algorithm, which explicitly constructs a pair of transfer operators from the style matrices for style transfer. Moreover, our algorithm is also observed to be flexible enough to transfer out-of-domain sentences. Extensive experimental evidence justifies the informativeness of style matrix and the competitive performance of our proposed style transfer algorithm with the state-of-the-art methods.

📄 PDF Abstract BibTeX arXiv:1908.05947

Code (0)

등록된 구현이 없습니다.

Tasks

InformativenessStyle TransferText Style Transfer

Similar Papers 제목 키워드 기반

ARTalk: Speech-Driven 3D Head Animation via Autoregressive Model

2025-02-27 · Xuangeng Chu, Nabarun Goswami, Ziteng Cui, Hanqin Wang 외

Speech-driven 3D facial animation aims to generate realistic lip movements and facial expressions for 3D head models from arbitrary audio clips. Although existing diffusion-based methods are capable of producing natural …

Facial Emotion Recognition does not detect feeling unsafe in automated driving

2025-09-01 · Abel van Elburg, Konstantinos Gkentsidis, Mathieu Sarrazin, Sarah Barendswaard 외 arxiv

Trust and perceived safety play a crucial role in the public acceptance of automated vehicles. To understand perceived risk, an experiment was conducted using a driving simulator under two automated driving styles and op…

Facial Expression RecognitionFacial Emotion Recognition

Chinese Poetry Generation with Flexible Styles

2018-07-17 · Jiyuan Zhang, Dong Wang

Research has shown that sequence-to-sequence neural models, particularly those with the attention mechanism, can successfully generate classical Chinese poems. However, neural models are not capable of generating poems t…

Talking Drums: Generating drum grooves with neural networks

2017-06-29 · P. Hutchings

Presented is a method of generating a full drum kit part for a provided kick-drum sequence. A sequence to sequence neural network model used in natural language translation was adopted to encode multiple musical styles a…

Translation

SemPOI-RL: Aligning LLM Semantic Reasoning for Interpretable Out-of-Town POI Sequential Generation

2026-08-31 · Yunqi Liu, Yang Zhang, Ruixing Zhang, Liangzhe Han 외 arxiv

Large language models (LLMs) exhibit strong semantic reasoning and open-ended generation abilities, but aligning these abilities with structured sequential generation remains challenging. This challenge is particularly e…

Reinforcement Learning