paper-with-me

Papers

Variational Transformers for Diverse Response Generation

2020-03-28 · Zhaojiang Lin, Genta Indra Winata, Peng Xu, Zihan Liu, Pascale Fung

Despite the great promise of Transformers in many sequence modeling tasks (e.g., machine translation), their deterministic nature hinders them from generalizing to high entropy tasks such as dialogue response generation. Previous work proposes to capture the variability of dialogue responses with a recurrent neural network (RNN)-based conditional variational autoencoder (CVAE). However, the autoregressive computation of the RNN limits the training efficiency. Therefore, we propose the Variational Transformer (VT), a variational self-attentive feed-forward sequence model. The VT combines the parallelizability and global receptive field of the Transformer with the variational nature of the CVAE by incorporating stochastic latent variables into Transformers. We explore two types of the VT: 1) modeling the discourse-level diversity with a global latent variable; and 2) augmenting the Transformer decoder with a sequence of fine-grained latent variables. Then, the proposed models are evaluated on three conversational datasets with both automatic metric and human evaluation. The experimental results show that our models improve standard Transformers and other baselines in terms of diversity, semantic relevance, and human judgment.

📄 PDF Abstract BibTeX arXiv:2003.12738

Code (2)

zlinao/Variational-Transformer 공식 구현 pytorch
ruiyiw/VT-summ pytorch

Tasks

DecoderDiversityMachine TranslationResponse GenerationTranslation

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
cVAE 설명 없음
Solana Customer Service Number +1-833-534-1729 설명 없음
Residual Connection 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

Towards Diverse, Relevant and Coherent Open-Domain Dialogue Generation via Hybrid Latent Variables

2022-12-02 · Bin Sun, Yitong Li, Fei Mi, Weichao Wang 외

Conditional variational models, using either continuous or discrete latent variables, are powerful for open-domain dialogue response generation. However, previous works show that continuous latent variables tend to reduc…

Dialogue GenerationResponse Generation

Improving Contextual Coherence in Variational Personalized and Empathetic Dialogue Agents

2022-02-12 · Jing Yang Lee, Kong Aik Lee, Woon Seng Gan

In recent years, latent variable models, such as the Conditional Variational Auto Encoder (CVAE), have been applied to both personalized and empathetic dialogue generation. Prior work have largely focused on generating d…

Dialogue GenerationResponse Generation

Knowledge-Grounded Response Generation with Deep Attentional Latent-Variable Model

2019-03-23 · Hao-Tong Ye, Kai-Ling Lo, Shang-Yu Su, Yun-Nung Chen

End-to-end dialogue generation has achieved promising results without using handcrafted features and attributes specific for each task and corpus. However, one of the fatal drawbacks in such approaches is that they are u…

Dialogue GenerationResponse Generation

Many Minds from One Model: Bayesian-Inspired Transformers for Population Diversity

2025-12-31 · Diji Yang, Yi Zhang arxiv

Despite their scale and success, modern transformers are usually trained as single-minded systems: optimization produces a deterministic set of parameters, representing a single functional hypothesis about the data. Moti…

Reinforcement Learning

Dior-CVAE: Pre-trained Language Models and Diffusion Priors for Variational Dialog Generation

2023-05-24 · Tianyu Yang, Thy Thy Tran, Iryna Gurevych

Current variational dialog models have employed pre-trained language models (PLMs) to parameterize the likelihood and posterior distributions. However, the Gaussian assumption made on the prior distribution is incompatib…

DecoderDiversityOpen-Domain DialogResponse Generation