🧑‍🔬 Wei Hong Xu

🏛️ Affiliations

🎓Georgia Institute of TechnologyAtlanta · United States2020–2025 · 43 papersEmployment · Associate Professorcurrent🎓Tsinghua UniversityBeijing · China2006–2025 · 34 paperscurrent🎓Renmin University of ChinaBeijing · China2019–2025 · 8 paperscurrent🎓Nanjing University of Information Science and TechnologyNanjing · China2013–2025 · 3 paperscurrent🎓Binzhou Medical UniversityYantai · China2025 · 1 papercurrent🎓Central South UniversityChangsha · China2025 · 1 papercurrent🏥First Hospital of Jilin UniversityChangchun · China2025 · 1 papercurrent🏢Guangzhou Automobile GroupGuangzhou · China2025 · 1 papercurrent🎓Huazhong University of Science and TechnologyWuhan · China2025 · 1 papercurrent🔬NARI GroupNanjing · China2025 · 1 papercurrent

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 39 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

📄 Papers

The most cited first (OpenAlex and our library).

1 2 next →

1. Bidirectional LSTM-CRF Models for Sequence Tagging (2015 · 3,822 citations)
   Part-of-speech tagging, chunking and named entity recognition had mostly been handled by linear statistical models (HMM, MEMM, CRF) and, more recently, by the convolutional Conv-CRF of Collobert et al.
2. Optimizing Statistical Machine Translation for Text Simplification (2016 · 954 citations)
   The paper adapts a syntax-based statistical translation system to simplify sentences. Its paraphrase rules come from large bilingual paraphrase tables (PPDB), which are easier to get than manually simplified text, and they are ranked with simplicity-specific features. The main contribution is the metric SARI. It…
3. Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN) (2014 · 715 citations)
   The paper addresses automatic image captioning. Many earlier systems picked captions from a fixed sentence database and so could not describe unseen combinations of objects and scenes. The authors propose m-RNN, a generative model that estimates the probability of each next word given the preceding words and the…
4. Problems in Current Text Simplification Research: New Data Can Help (2015 · 659 citations)
   For several years, text simplification research has depended on the PWKP corpus. PWKP pairs sentences from Normal and Simple English Wikipedia using automatic alignment. In this opinion paper, the authors argue that the resource is badly flawed and should no longer be the standard benchmark. They hand-check a random…
5. End-to-end learning of semantic role labeling using recurrent neural networks (2015 · 466 citations)
   Zhou and Xu ask whether semantic role labeling (SRL) can be done well without syntactic parsing. Earlier strong systems relied on parse trees, hand-crafted feature templates and combinations of several parsers, and the earlier parser-free neural attempt by Collobert et al. (2011) fell short. The authors build an…
6. Shared Tasks of the 2015 Workshop on Noisy User-generated Text: Twitter Lexical Normalization and Named Entity Recognition (2015 · 286 citations)
   This paper reports on the two shared tasks organized with the W-NUT 2015 workshop: lexical normalization of English tweets and named entity recognition (NER) on Twitter.
7. Having Beer after Prayer? Measuring Cultural Bias in Large Language Models (2023 · 272 citations)
   Large language models are deployed worldwide, yet even in Arabic they often fall back on Western cultural content.
8. A Continuously Growing Dataset of Sentential Paraphrases (2017 · 267 citations)
   Paraphrase research suffers from a shortage of parallel corpora. Earlier resources such as MSRP and PIT-2015 also depended on a classifier or on manual topic selection to pick candidate pairs before annotation. Lan et al. propose a simpler candidate source: tweets that link to the same URL, mostly news articles…
9. Deep Recurrent Models with Fast-Forward Connections for Neural Machine Translation (2016 · 265 citations)
   Before this work, single neural machine translation models trailed the strongest phrase-based systems on WMT'14 English-to-French.
10. Doc2EDAG: An End-to-End Document-level Framework for Chinese Financial Event Extraction (2019 · 246 citations)
    Most event extraction (EE) systems only find event arguments within a single sentence. In financial documents, however, the arguments of one event are often spread over several sentences, and one document may describe several events. This work targets document-level EE (DEE) on Chinese financial announcements…
11. SemEval-2015 Task 1: Paraphrase and Semantic Similarity in Twitter (PIT) (2015 · 231 citations)
    This shared task asks how well systems can judge whether two tweets mean the same thing, given that Twitter text is short, noisy and full of lexical variation.
12. Neural CRF Model for Sentence Alignment in Text Simplification (2020 · 227 citations)
    Modern text simplification systems learn from pairs of complex and simplified sentences, and those pairs are only as good as the alignment between parallel articles.
13. Paraphrasing for Style (2012 · 196 citations)
    The paper asks whether a paraphrase system can be steered toward a writing style. Its testbed is Shakespeare's plays paired with their modern prose translations, aligned into roughly 21,000 sentence pairs from one source and about 10,000 from another. A phrase-based statistical MT system is trained in the…
14. Knowledge Conflicts for LLMs: A Survey (2024 · 182 citations)
    This survey examines a recurring problem in large language models: the knowledge stored in a model's weights can disagree with information supplied at inference time, and supplied sources can disagree with each other.
15. 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…
16. Controllable Text Simplification with Explicit Paraphrasing (2021 · 164 citations)
    Most recent text simplification systems are end-to-end seq2seq models. They mainly shorten sentences by dropping words, rarely split or rephrase, and give users little control over the output for different audiences. The authors propose a hybrid pipeline instead. First, the rule-based DisSim system and a…
17. An Empirical Study of Pre-trained Transformers for Arabic Information Extraction (2020 · 107 citations)
    Multilingual encoders such as mBERT and XLM-RoBERTa can be fine-tuned on English labels and then applied to Arabic.
18. LENS: A Learnable Evaluation Metric for Text Simplification (2023 · 104 citations)
    Automatic scoring of text simplification is unreliable. SARI rewards n-gram overlap with references, so it penalizes valid rewordings. BERTScore barely punishes outputs that copy the input or invent content while reusing its words. The authors build the first supervised metric for the task, LENS, by fine-tuning a…
19. Having Beer after Prayer? Measuring Cultural Bias in Large Language Models (2024 · 96 citations)
    Language models now serve users worldwide, but it is seldom checked whether they adapt to the cultural setting a non-English prompt implies.
20. From Shakespeare to Twitter: What are Language Styles all about? (2017 · 29 citations)
    This is a position and survey paper, not a method paper. It names seven language styles that the author thinks matter: simple and short text, historical and evolving language, instructional and robotic language, colloquial and internet language, gendered and personalized language, polite and abusive language, and…
21. Stanceosaurus: Classifying Stance Towards Multicultural Misinformation (2022 · 16 citations)
    Stanceosaurus is a Twitter corpus for detecting how posts relate to false claims. Earlier misinformation stance datasets mostly covered Western events or a handful of topics. This one contains 28,033 tweets in English, Hindi and Arabic. Each tweet is manually labeled for its stance toward one of 251 claims drawn from…
22. On The Origin of Cultural Biases in Language Models: From Pre-training Data to Linguistic Phenomena (2025 · 15 citations)
    Earlier work found that multilingual LMs handle Western entities better than Arab ones when working in Arabic.
23. DebateQA: Evaluating Question Answering on Debatable Knowledge (2026 · 7 citations)
    Standard QA benchmarks assume one correct answer, so they cannot judge how chatbots handle contested questions such as how crop circles form.
24. Faithfulness vs. Safety: Evaluating LLM Behavior Under Counterfactual Medical Evidence (2026)
    The paper asks what LLMs do when the evidence supplied in context for a medical question is false, implausible, or harmful.
25. GeoRC: A Benchmark for Geolocation Reasoning Chains (2026)
    GeoRC addresses a gap between how well vision-language models (VLMs) guess where a photo was taken and how well they justify those guesses.

1 2 next →

All works

44 works of theirs in our library, the most cited first; 26 with a page here, the others link their original until we summarise them.

1. Bidirectional LSTM-CRF Models for Sequence TaggingarXiv:1508.01991Zhiheng Huang, Wei Xu, Kai Yu2015 · 3,822 citations
2. CNN-RNN: A Unified Framework for Multi-label Image Classification ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetJiang Wang et al.2016 · 1,218 citations
3. Optimizing Statistical Machine Translation for Text SimplificationWei Xu, Courtney Napoles, Ellie Pavlick, et al.Machine translation · 954 citations
4. Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)International Conference on Learning Representations (ICLR)Junhua Mao, Wei Xu, Yi Yang, et al.2014 · 715 citations
5. Problems in Current Text Simplification Research: New Data Can HelpTransactions of the Association for Computational Linguistics (TACL)Wei Xu, Chris Callison-Burch, Courtney Napoles2015 · 659 citations
6. End-to-end learning of semantic role labeling using recurrent neural networksAnnual Meeting of the Association for Computational Linguistics (ACL)Jie Zhou, Wei Xu2015 · 466 citations
7. Shared Tasks of the 2015 Workshop on Noisy User-generated Text: Twitter Lexical Normalization and Named Entity RecognitionWorkshop on Noisy User-generated TextTimothy Baldwin, Marie Catherine de Marneffe, Bo Han, et al.2015 · 286 citations
8. Having Beer after Prayer? Measuring Cultural Bias in Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Tarek Naous, Michael J. Ryan, Alan Ritter, et al.2023 · 272 citations
9. A Continuously Growing Dataset of Sentential ParaphrasesConference on Empirical Methods in Natural Language Processing (EMNLP)Wuwei Lan, Siyu Qiu, Hua He, et al.2017 · 267 citations
10. Deep Recurrent Models with Fast-Forward Connections for Neural Machine TranslationTransactions of the Association for Computational Linguistics (TACL)Jie Zhou, Ying Cao, Xuguang Wang, et al.2016 · 265 citations
11. Doc2EDAG: An End-to-End Document-level Framework for Chinese Financial Event ExtractionConference on Empirical Methods in Natural Language Processing (EMNLP)Shun Zheng, Wei Cao, Wei Xu, et al.2019 · 246 citations
12. SemEval-2015 Task 1: Paraphrase and Semantic Similarity in Twitter (PIT)International Workshop on Semantic Evaluation (SemEval)Wei Xu, Chris Callison-Burch, Bill Dolan2015 · 231 citations
13. Neural CRF Model for Sentence Alignment in Text SimplificationAnnual Meeting of the Association for Computational Linguistics (ACL)Chao Jiang, Mounica Maddela, Wuwei Lan, et al.2020 · 227 citations
14. Paraphrasing for StyleWei Xu, Alan Ritter, Bill Dolan, et al.Machine translation · 196 citations
15. Knowledge Conflicts for LLMs: A SurveyConference on Empirical Methods in Natural Language Processing (EMNLP)Rongwu Xu, Zehan Qi, Zhijiang Guo, et al.2024 · 182 citations
16. CAMEL: A Weakly Supervised Learning Framework for Histopathology Image Segmentation ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetGang Xu et al.2019 · 182 citations
17. 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
18. CFO: Conditional Focused Neural Question Answering with Large-scale Knowledge Bases ↗Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetZihang Dai, Lei Li, Wei Xu2016 · 167 citations
19. Extracting Lexically Divergent Paraphrases from Twitter ↗Transactions of the Association for Computational Linguistics · no summary yetWei Xu et al.2014 · 166 citations
20. Controllable Text Simplification with Explicit ParaphrasingConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Mounica Maddela, Fernando Alva-Manchego, Wei Xu2021 · 164 citations
21. Neural Network Models for Paraphrase Identification, Semantic Textual Similarity, Natural Language Inference, and Question Answering ↗Proceedings of the 27th International Conference on Computational Linguistics · no summary yetWuwei Lan, Wei Xu2018 · 143 citations
22. Code and Named Entity Recognition in StackOverflow ↗Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · no summary yetJeniya Tabassum et al.2020 · 123 citations
23. A Word-Complexity Lexicon and A Neural Readability Ranking Model for Lexical Simplification ↗Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · no summary yetMounica Maddela, Wei Xu2018 · 108 citations
24. An Empirical Study of Pre-trained Transformers for Arabic Information ExtractionConference on Empirical Methods in Natural Language Processing (EMNLP)Wuwei Lan, Yang Chen, Wei Xu, et al.2020 · 107 citations
25. LENS: A Learnable Evaluation Metric for Text SimplificationAnnual Meeting of the Association for Computational Linguistics (ACL)Mounica Maddela, Yao Dou, David Heineman, et al.2023 · 104 citations

See all 44 works by Wei Hong Xu →

🤝 Co-authors here

12 of 48 co-authors with a page, the most papers together first.

• Alan Ritter ×7
• Tarek Naous ×4
• Chris Callison-Burch ×3
• Mounica Maddela ×3
• Wuwei Lan ×3
• Bill Dolan ×2
• Courtney Napoles ×2
• Jie Zhou ×2
• Michael J. Ryan ×2
• Rongwu Xu ×2
• Zehan Qi ×2
• Zhiheng Huang ×2

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) ×13: ACL 2026 ×2, ACL 2024, ACL 2023 ×2, ACL 2020, ACL 2016, ACL 2015
• Conference on Empirical Methods in Natural Language Processing (EMNLP) ×8: EMNLP 2024, EMNLP 2022, EMNLP 2020, EMNLP 2019, EMNLP 2017
• Transactions of the Association for Computational Linguistics (TACL) ×4: Transactions of the Association for Computational Linguistics (TACL) 2016 ×2, Transactions of the Association for Computational Linguistics (TACL) 2015
• International Conference on Computational Linguistics (COLING) ×2: COLING 2012
• Findings of the Association for Computational Linguistics ×2: Findings of the Association for Computational Linguistics 2026 ×2
• Conference of the North American Chapter of the Association for Computational Linguistics (NAACL) ×2: NAACL 2025, NAACL 2021
• Workshop on Generation, Evaluation and Metrics (GEM)
• International Conference on Learning Representations (ICLR): ICLR 2014
• International Workshop on Semantic Evaluation (SemEval): SemEval 2015
• Workshop on Noisy User-generated Text: Workshop on Noisy User-generated Text 2015
• Workshop on Stylistic Variation: Workshop on Stylistic Variation 2017
• Findings of the Association for Computational Linguistics: ACL 2023

🔗 Cited by

Papers of our library cite their works 3,606 times (of the 149,439 papers whose bibliographies we read); 477 citing papers with a page here →.

Updated 2 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/wei-hong-xu/