paper-with-me

홈 › Papers

An Auto-Encoder Matching Model for Learning Utterance-Level Semantic Dependency in Dialogue Generation

2018-08-27 · EMNLP 2018 10 · Liangchen Luo, Jingjing Xu, Junyang Lin, Qi Zeng, Xu sun

Generating semantically coherent responses is still a major challenge in dialogue generation. Different from conventional text generation tasks, the mapping between inputs and responses in conversations is more complicated, which highly demands the understanding of utterance-level semantic dependency, a relation between the whole meanings of inputs and outputs. To address this problem, we propose an Auto-Encoder Matching (AEM) model to learn such dependency. The model contains two auto-encoders and one mapping module. The auto-encoders learn the semantic representations of inputs and responses, and the mapping module learns to connect the utterance-level representations. Experimental results from automatic and human evaluations demonstrate that our model is capable of generating responses of high coherence and fluency compared to baseline models. The code is available at https://github.com/lancopku/AMM

📄 PDF Abstract BibTeX arXiv:1808.08795

Code (1)

lancopku/AMM 공식 구현 tf

Tasks

Dialogue GenerationText Generation

Similar Papers 제목 키워드 기반

Modeling Personalization in Continuous Space for Response Generation via Augmented Wasserstein Autoencoders

2019-11-01 · IJCNLP 2019 11 · Zhangming Chan, Juntao Li, Xiaopeng Yang, Xiuying Chen 외

Variational autoencoders (VAEs) and Wasserstein autoencoders (WAEs) have achieved noticeable progress in open-domain response generation. Through introducing latent variables in continuous space, these models are capable…

Response Generation

Discovering Dialog Structure Graph for Open-Domain Dialog Generation

2020-12-31 · Jun Xu, Zeyang Lei, Haifeng Wang, Zheng-Yu Niu 외

Learning interpretable dialog structure from human-human dialogs yields basic insights into the structure of conversation, and also provides background knowledge to facilitate dialog generation. In this paper, we conduct…

Graph Neural NetworkOpen-Domain Dialog

Towards the Next Frontier in Speech Representation Learning Using Disentanglement

2024-07-02 · Varun Krishna, Sriram Ganapathy

The popular frameworks for self-supervised learning of speech representations have largely focused on frame-level masked prediction of speech regions. While this has shown promising downstream task performance for speech…

DisentanglementRepresentation LearningSelf-Supervised Learningspeech-recognition+2

Dynamic Semantic Matching and Aggregation Network for Few-shot Intent Detection

2020-10-06 · Findings of the Association for Computational Linguistics 2020 · Hoang Nguyen, Chenwei Zhang, Congying Xia, Philip S. Yu

Few-shot Intent Detection is challenging due to the scarcity of available annotated utterances. Although recent works demonstrate that multi-level matching plays an important role in transferring learned knowledge from s…

Few-Shot LearningGeneralized Few-Shot LearningIntent Detection

Learning to Respond with Stickers: A Framework of Unifying Multi-Modality in Multi-Turn Dialog

2020-03-10 · Shen Gao, Xiuying Chen, Chang Liu, Li Liu 외

Stickers with vivid and engaging expressions are becoming increasingly popular in online messaging apps, and some works are dedicated to automatically select sticker response by matching text labels of stickers with prev…