🧑‍🔬 Hua Ren Wu

🏛️ Affiliations

🎓North China Electric Power UniversityBeijing · China2011–2026 · 20 paperscurrent🏢BaiduBeijing · China2010–2025 · 132 papers🎓China University of Petroleum, BeijingBeijing · China2019–2024 · 7 papers🏢ToshibaTokyo · Japan2004–2009 · 7 papers🎓Northwestern Polytechnical UniversityXi'an · China2024–2025 · 2 papers🎓Harbin Institute of TechnologyHarbin · China2013–2014 · 2 papers🎓Nanjing Normal UniversityNanjing · China2014 · 2 papers🎓Beihang UniversityBeijing · China2007–2010 · 2 papers🎓Queen's University BelfastBelfast · United Kingdom2007 · 2 papers🏢Microsoft Research AsiaBeijing · China2003 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 11 more institutions on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

2010s

2000s

📄 Papers

The most cited first (OpenAlex and our library).

1 2 next →

1. ERNIE 2.0: A Continual Pre-training Framework for Language Understanding (2019 · 995 citations)
   Pre-trained language models such as BERT and XLNet mostly learn from word and sentence co-occurrence. They leave aside other signals in raw text, including named entities, sentence structure and discourse relations. The Baidu authors propose ERNIE 2.0, a framework that lets new self-supervised or weakly supervised…
2. ERNIE: Enhanced Representation through Knowledge Integration (2019 · 962 citations)
   Masked language models like BERT hide single characters or words. They can often guess the missing piece from the rest of the same name, without using what the sentence says about it. ERNIE, from Baidu, changes what is hidden. Training runs through three masking stages: random basic units (Chinese characters), then…
3. Multi-Task Learning for Multiple Language Translation (2015 · 796 citations)
   The paper asks whether one neural model can translate a single source language (English) into several target languages at once, and whether this helps target languages with little parallel data.
4. RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering (2021 · 603 citations)
   Open-domain QA systems often fetch candidate passages with a dual-encoder retriever, which embeds questions and passages separately and matches them by dot product.
5. Minimum Risk Training for Neural Machine Translation (2015 · 583 citations)
   Standard neural machine translation is trained with maximum likelihood. This rewards predicting the next correct word, yet systems are judged on sentence-level metrics such as BLEU, and at test time they build on their own possibly wrong outputs. Shen et al. replace that objective with minimum risk training (MRT)…
6. Multi-Turn Response Selection for Chatbots with Deep Attention Matching Network (2018 · 410 citations)
   The paper addresses multi-turn response selection: given a multi-utterance conversation history, a retrieval-based chatbot must pick the most suitable reply from a set of candidates.
7. STACL: Simultaneous Translation with Implicit Anticipation and Controllable Latency using Prefix-to-Prefix Framework (2019 · 350 citations)
   Simultaneous machine translation must produce output while the speaker is still talking. Word-order mismatches make this hard: when translating an SOV language such as German into an SVO language such as English, the system may need to wait for a verb at the end of the sentence. Earlier systems, such as the…
8. SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment Analysis (2020 · 333 citations)
   Pre-trained language models such as BERT and RoBERTa learn general representations through word-level objectives.
9. PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable (2020 · 323 citations)
   PLATO addresses why general-purpose pre-trained models like BERT transfer poorly to open-domain dialogue generation.
10. UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning (2021 · 308 citations)
    Existing pre-trained models usually serve only one side. Text-only and vision-only models such as BERT or ResNet cannot handle vision-language inputs. Multi-modal models such as ViLBERT and UNITER learn only from scarce image-text pairs and perform poorly when moved to pure language tasks. The authors (Baidu) propose…
11. Pivot Language Approach for Phrase-Based Statistical Machine Translation (2007 · 296 citations)
    The paper tackles phrase-based SMT for language pairs with little or no direct parallel data. The authors route through a third, well-resourced pivot language. They train separate source–pivot and pivot–target phrase models and combine them into a source–target "pivot model". Phrase probabilities are obtained by…
12. RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking (2021 · 256 citations)
    Retrieve-then-rerank pipelines pair a fast dual-encoder retriever with a stronger cross-encoder re-ranker.
13. Towards Conversational Recommendation over Multi-Type Dialogs (2020 · 230 citations)
    Earlier conversational recommender research mostly handles one kind of dialog and assumes the user knows the conversation's purpose from the start.
14. Proactive Human-Machine Conversation with Explicit Conversation Goal (2019 · 206 citations)
    Most dialogue systems simply react to the user and do not steer the exchange. This Baidu paper defines a task in which an agent must actively guide a chat toward a preset target: a two-hop path "[start] → topic a → topic b", where each topic is an entity in a knowledge graph. The authors crawled movie and film-star…
15. DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applications (2017 · 170 citations)
    Existing machine reading comprehension (MRC) benchmarks often rely on artificial setups such as cloze deletion, exam-style multiple choice, or questions written by crowdworkers after reading a passage.
16. Semi-Supervised Learning for Neural Machine Translation (2016 · 168 citations)
    Standard NMT systems learn only from parallel text. Parallel data is scarce, narrow in domain and uneven in quality, while monolingual text is plentiful. The authors propose a semi-supervised scheme that trains a source-to-target model and a target-to-source model together. The training objective adds…
17. ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation (2020 · 163 citations)
    ERNIE-GEN, from Baidu, is a sequence-to-sequence framework that covers both pre-training and fine-tuning for text generation tasks.
18. ERNIE-ViL: Knowledge Enhanced Vision-Language Representations Through Scene Graph (2020 · 152 citations)
    Most vision-language pre-training models mask sub-words at random. As a result, they give generic words and content-bearing words equal weight and learn fine-grained correspondences between image and text poorly. ERNIE-ViL, from Baidu, addresses this by injecting structured knowledge from scene graphs.
19. PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learning (2021 · 145 citations)
    PLATO-2 addresses the difficulty of scaling an open-domain chatbot that explicitly models the one-to-many nature of dialogue, where a single context can have many valid replies.
20. ERNIE-M: Enhanced Multilingual Representation by Aligning Cross-lingual Semantics with Monolingual Corpora (2020 · 128 citations)
    Cross-lingual pre-trained encoders gain a lot from parallel data, but bilingual corpora are scarce, particularly for low-resource languages, which limits how well such models align meaning across languages.
21. Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation (2025 · 101 citations)
    This COLING 2025 study asks whether large language models know where their factual knowledge ends, and how retrieval augmentation changes that self-awareness in open-domain QA.
22. DuSQL: A Large-Scale and Pragmatic Chinese Text-to-SQL Dataset (2020 · 64 citations)
    Most text-to-SQL resources (ATIS, WikiSQL, Spider) are English. Their SQL queries are designed around syntactic coverage, not around what users actually ask. DuSQL fills this gap with a cross-domain Chinese text-to-SQL dataset of 200 databases, 813 tables and 23,797 question/SQL pairs.
23. ERNIE-ViLG: Unified Generative Pre-training for Bidirectional Vision-Language Generation (2021 · 33 citations)
    Image captioning and text-to-image synthesis are two directions of the same mapping between vision and language, yet they have usually been handled by separate, task-specific architectures.
24. ERNIE-Code: Beyond English-Centric Cross-lingual Pretraining for Programming Languages (2022 · 32 citations)
    Most pretrained code models link source code only with English comments and documentation. This leaves out developers who work in other languages. ERNIE-Code addresses the gap with a single T5-style encoder-decoder trained jointly on 116 natural languages and 6 programming languages. Pretraining combines two…
25. DuReader_retrieval: A Large-scale Chinese Benchmark for Passage Retrieval from Web Search Engine (2022 · 27 citations)
    Dense passage retrieval depends on large, human-annotated training and evaluation data. Such resources are plentiful for English but scarce for Chinese, where existing sets are tiny (TianGong-PDR), machine-translated (mMARCO), or built only from click logs (Sougou-QCL). The authors present DuReader_retrieval, a…

1 2 next →

All works

49 works of theirs in our library, the most cited first; 34 with a page here, the others link their original until we summarise them.

1. ERNIE 2.0: A Continual Pre-training Framework for Language UnderstandingProceedings of the AAAI Conference on Artificial IntelligenceYu Sun, Shuohuan Wang, Yukun Li, et al.2019 · 995 citations
2. ERNIE: Enhanced Representation through Knowledge IntegrationarXiv:1904.09223Yu Sun, Shuohuan Wang, Yukun Li, et al.2019 · 962 citations
3. Multi-Task Learning for Multiple Language TranslationAnnual Meeting of the Association for Computational Linguistics (ACL)Daxiang Dong, Hua Wu, Wei He, et al.2015 · 796 citations
4. Unified Structure Generation for Universal Information Extraction ↗Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetYaojie Lu et al.2022 · 613 citations
5. RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question AnsweringConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Yingqi Qu, Yuchen Ding, Jing Liu, et al.2021 · 603 citations
6. Minimum Risk Training for Neural Machine TranslationAnnual Meeting of the Association for Computational Linguistics (ACL)Shiqi Shen, Yong Cheng, Zhongjun He, et al.2015 · 583 citations
7. An End-to-End Model for Question Answering over Knowledge Base with Cross-Attention Combining Global Knowledge ↗Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetYanchao Hao et al.2017 · 418 citations
8. Multi-Turn Response Selection for Chatbots with Deep Attention Matching NetworkAnnual Meeting of the Association for Computational Linguistics (ACL)Xiangyang Zhou, Lu Li, Daxiang Dong, et al.2018 · 410 citations
9. STACL: Simultaneous Translation with Implicit Anticipation and Controllable Latency using Prefix-to-Prefix FrameworkAnnual Meeting of the Association for Computational Linguistics (ACL)Mingbo Ma, Liang Huang, Hao Xiong, et al.2019 · 350 citations
10. SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment AnalysisAnnual Meeting of the Association for Computational Linguistics (ACL)Hao Tian, Can Gao, Xinyan Xiao, et al.2020 · 333 citations
11. PLATO: Pre-trained Dialogue Generation Model with Discrete Latent VariableAnnual Meeting of the Association for Computational Linguistics (ACL)Siqi Bao, Huang He, Fan Wang, et al.2020 · 323 citations
12. UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive LearningAnnual Meeting of the Association for Computational Linguistics (ACL)Wei Li, Can Gao, Guocheng Niu, et al.2021 · 308 citations
13. Pivot Language Approach for Phrase-Based Statistical Machine TranslationAnnual Meeting of the Association for Computational Linguistics (ACL)Hua Wu, Haifeng Wang2007 · 296 citations
14. Multi-view Response Selection for Human-Computer Conversation ↗Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · no summary yetXiangyang Zhou et al.2016 · 273 citations
15. Learning to Select Knowledge for Response Generation in Dialog Systems ↗International Joint Conference on Artificial Intelligence · no summary yetRongzhong Lian et al.2019 · 261 citations
16. RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-rankingConference on Empirical Methods in Natural Language Processing (EMNLP)Ruiyang Ren, Yingqi Qu, Jing Liu, et al.2021 · 256 citations
17. ERNIE-ViL: Knowledge Enhanced Vision-Language Representations through Scene Graphs ↗Proceedings of the AAAI Conference on Artificial Intelligence · no summary yetFei Richard Yu et al.2021 · 252 citations
18. Towards Conversational Recommendation over Multi-Type DialogsAnnual Meeting of the Association for Computational Linguistics (ACL)Zeming Liu, Haifeng Wang, Zheng-Yu Niu, et al.2020 · 230 citations
19. Proactive Human-Machine Conversation with Explicit Conversation GoalAnnual Meeting of the Association for Computational Linguistics (ACL)Wenquan Wu, Zhen Guo, Xiangyang Zhou, et al.2019 · 206 citations
20. Enhancing Pre-Trained Language Representations with Rich Knowledge for Machine Reading Comprehension ↗Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · no summary yetAn Yang et al.2019 · 195 citations
21. DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world ApplicationsarXiv:1711.05073Wei He, Kai Liu, Jing Liu, et al.2017 · 170 citations
22. Leveraging Graph to Improve Abstractive Multi-Document Summarization ↗Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · no summary yetWei Li et al.2020 · 168 citations
23. Semi-Supervised Learning for Neural Machine TranslationAnnual Meeting of the Association for Computational Linguistics (ACL)Yong Cheng, Wei Xu, Zhongjun He, et al.2016 · 168 citations
24. ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language GenerationInternational Joint Conference on Artificial IntelligenceDongling Xiao, Han Zhang, Yukun Li, et al.2020 · 163 citations
25. ERNIE-ViL: Knowledge Enhanced Vision-Language Representations Through Scene GrapharXiv:2006.16934Fei Yu, Jiji Tang, Weichong Yin, et al.2020 · 152 citations

See all 49 works by Hua Ren Wu →

🤝 Co-authors here

12 of 86 co-authors with a page, the most papers together first.

• Haifeng Wang ×27
• Yu Sun ×13
• Hao Tian ×10
• Jing Liu ×8
• Shuohuan Wang ×8
• Han Zhang ×4
• Ruiyang Ren ×4
• Wayne Xin Zhao ×4
• Wei He ×4
• Yingqi Qu ×4
• Zhongjun He ×4
• Daxiang Dong ×3

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Annual Meeting of the Association for Computational Linguistics (ACL) ×23: ACL 2026 ×3, ACL 2025 ×2, ACL 2021, ACL 2020 ×3, ACL 2019 ×2, ACL 2018, ACL 2016, ACL 2015 ×2, ACL 2007
• Conference on Empirical Methods in Natural Language Processing (EMNLP) ×6: EMNLP 2022, EMNLP 2021, EMNLP 2020 ×2
• Proceedings of the AAAI Conference on Artificial Intelligence ×3: Proceedings of the AAAI Conference on Artificial Intelligence 2019
• International Joint Conference on Artificial Intelligence ×2: International Joint Conference on Artificial Intelligence 2020
• International Conference on Computational Linguistics (COLING): COLING 2025
• Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2021
• Conference of the North American Chapter of the Association for Computational Linguistics (NAACL): NAACL 2021
• COLING 2004: Proceedings of the 20th International Conference on Computational Linguistics
• Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021
• Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

🔗 Cited by

Papers of our library cite their works 3,374 times (of the 149,439 papers whose bibliographies we read); 398 citing papers with a page here →.

Updated 1 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/hua-ren-wu/