Search Results for author: Hainan Zhang

Found 16 papers, 2 papers with code

Adaptive Bridge between Training and Inference for Dialogue Generation

no code implementations EMNLP 2021 Haoran Xu, Hainan Zhang, Yanyan Zou, Hongshen Chen, Zhuoye Ding, Yanyan Lan

Although exposure bias has been widely studied in some NLP tasks, it faces its unique challenges in dialogue response generation, the representative one-to-various generation scenario. In real human dialogue, there are many appropriate responses for the same context, not only with different expressions, but also with different topics.

Dialogue Generation NMT +1

Safely Learning with Private Data: A Federated Learning Framework for Large Language Model

no code implementations21 Jun 2024 JiaYing Zheng, Hainan Zhang, LingXiang Wang, Wangjie Qiu, Hongwei Zheng, Zhiming Zheng

An alternative, split learning, offloads most training parameters to the server while training embedding and output layers locally, making it more suitable for LLM.

Federated Learning Language Modelling +1

Defending Against Sophisticated Poisoning Attacks with RL-based Aggregation in Federated Learning

no code implementations20 Jun 2024 Yujing Wang, Hainan Zhang, Sijia Wen, Wangjie Qiu, Binghui Guo

Then, we use the maximum mean discrepancy (MMD) to calculate the pairwise similarity of the current local model data distribution, its historical data distribution, and global model data distribution.

Federated Learning Model Poisoning

Automatic Product Copywriting for E-Commerce

no code implementations15 Dec 2021 Xueying Zhang, Yanyan Zou, Hainan Zhang, Jing Zhou, Shiliang Diao, Jiajia Chen, Zhuoye Ding, Zhen He, Xueqi He, Yun Xiao, Bo Long, Han Yu, Lingfei Wu

It consists of two main components: 1) natural language generation, which is built from a transformer-pointer network and a pre-trained sequence-to-sequence model based on millions of training data from our in-house platform; and 2) copywriting quality control, which is based on both automatic evaluation and human screening.

Product Recommendation Text Generation

Adaptive Bridge between Training and Inference for Dialogue

no code implementations22 Oct 2021 Haoran Xu, Hainan Zhang, Yanyan Zou, Hongshen Chen, Zhuoye Ding, Yanyan Lan

Although exposure bias has been widely studied in some NLP tasks, it faces its unique challenges in dialogue response generation, the representative one-to-various generation scenario.

Dialogue Generation NMT +1

FCM: A Fine-grained Comparison Model for Multi-turn Dialogue Reasoning

no code implementations Findings (EMNLP) 2021 Xu Wang, Hainan Zhang, Shuai Zhao, Yanyan Zou, Hongshen Chen, Zhuoye Ding, Bo Cheng, Yanyan Lan

Furthermore, the consistency signals between each candidate and the speaker's own history are considered to drive a model to prefer a candidate that is logically consistent with the speaker's history logic.

Reading Comprehension

Topic-Aware Contrastive Learning for Abstractive Dialogue Summarization

1 code implementation Findings (EMNLP) 2021 Junpeng Liu, Yanyan Zou, Hainan Zhang, Hongshen Chen, Zhuoye Ding, Caixia Yuan, Xiaojie Wang

To capture the various topic information of a conversation and outline salient facts for the captured topics, this work proposes two topic-aware contrastive learning objectives, namely coherence detection and sub-summary generation objectives, which are expected to implicitly model the topic change and handle information scattering challenges for the dialogue summarization task.

Abstractive Dialogue Summarization Contrastive Learning +3

Augmenting Knowledge-grounded Conversations with Sequential Knowledge Transition

no code implementations NAACL 2021 Haolan Zhan, Hainan Zhang, Hongshen Chen, Zhuoye Ding, Yongjun Bao, Yanyan Lan

In particular, a sequential knowledge transition model equipped with a pre-trained knowledge-aware response generator (SKT-KG) formulates the high-level knowledge transition and fully utilizes the limited knowledge data.

Response Generation

Probing Product Description Generation via Posterior Distillation

no code implementations2 Mar 2021 Haolan Zhan, Hainan Zhang, Hongshen Chen, Lei Shen, Zhuoye Ding, Yongjun Bao, Weipeng Yan, Yanyan Lan

To tackle this problem, we propose an adaptive posterior network based on Transformer architecture that can utilize user-cared information from customer reviews.

User-Inspired Posterior Network for Recommendation Reason Generation

no code implementations16 Feb 2021 Haolan Zhan, Hainan Zhang, Hongshen Chen, Lei Shen, Yanyan Lan, Zhuoye Ding, Dawei Yin

A simple and effective way is to extract keywords directly from the knowledge-base of products, i. e., attributes or title, as the recommendation reason.

Question Answering

Modeling Topical Relevance for Multi-Turn Dialogue Generation

no code implementations27 Sep 2020 Hainan Zhang, Yanyan Lan, Liang Pang, Hongshen Chen, Zhuoye Ding, Dawei Yin

Therefore, an ideal dialogue generation models should be able to capture the topic information of each context, detect the relevant context, and produce appropriate responses accordingly.

Dialogue Generation Sentence

Neural or Statistical: An Empirical Study on Language Models for Chinese Input Recommendation on Mobile

no code implementations9 Jul 2019 Hainan Zhang, Yanyan Lan, Jiafeng Guo, Jun Xu, Xue-Qi Cheng

Chinese input recommendation plays an important role in alleviating human cost in typing Chinese words, especially in the scenario of mobile applications.

Language Modelling

Tailored Sequence to Sequence Models to Different Conversation Scenarios

no code implementations ACL 2018 Hainan Zhang, Yanyan Lan, Jiafeng Guo, Jun Xu, Xue-Qi Cheng

In this paper, we propose two tailored optimization criteria for Seq2Seq to different conversation scenarios, i. e., the maximum generated likelihood for specific-requirement scenario, and the conditional value-at-risk for diverse-requirement scenario.

Dialogue Generation Response Generation

Cannot find the paper you are looking for? You can Submit a new open access paper.