Elamur Research⌕
☰
home / authors / Hua He

Hua He

Hua He studies semantic similarity between sentences, the scoring task behind paraphrase detection and graded relatedness judgments. Their papers here, from 2015 to 2017, come at it from two sides. One is the design of neural networks that compare sentences in fine detail rather than reducing each one to a single vector. The other is the construction of annotated paraphrase resources from social media text.

The most cited of these, Multi-Perspective Sentence Similarity Modeling with Convolutional Neural Networks (2015), proposed a Siamese convolutional network. Each branch encodes a sentence through several filter types, window widths and pooling operations. A structured layer then matches local regions of the two encodings using multiple distance measures. Pairwise Word Interaction Modeling (2016) shifted to word-by-word comparison. Similarities between contextual encoder states are arranged as a multi-channel grid, and a deep convolutional network reads that grid much as it would read an image. Ablations showed that comparing contexts, not raw embeddings, mattered most.

The latest work turns from models to data. A Continuously Growing Dataset of Sentential Paraphrases (2017) gathers candidate pairs from tweets that share a link to the same news article. This avoids both a trained selector and hand-picked topics. Crowd workers then label the pairs, and the resulting corpus contains realistic non-paraphrases alongside several reference sentences for each source. Collaborators on these papers include Jimmy Lin, who appears more than once, as well as Kevin Gimpel, Wei Xu and Wuwei Lan.

Hua He has 3 papers in our library, in 2015–2017; often with Jimmy Lin, Kevin Gimpel, Wei Xu.

3 papers in our library · 2015–2017

OpenAlex · ORCID · Wikidata · h-index 34 · 169 works · 5,811 citations OpenAlex, 2026-10-14

📄 3 works in our library · 🔗 Cited 248 times in our library · 1 more in our library without a page yet · ⭐ Paper Stars ranking: #2196

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🎓China University of Petroleum, East ChinaQingdao · China2008–2026 · 65 papersEmployment since 2008current🔬State Key Laboratory of Heavy OilBeijing · China2012–2026 · 57 paperscurrent🏛️Chinese Academy of SciencesBeijing · China2013–2022 · 8 papers🎓University of Maryland, College ParkCollege Park · United States2015–2017 · 8 papers🎓Xi’an University of Posts and TelecommunicationsXi'an · China2012–2025 · 6 papers🔬Xishuangbanna Tropical Botanical GardenMengla · China2013–2022 · 6 papers🎓Sichuan Agricultural UniversityYa'an · China2016–2023 · 5 papers🎓Sun Yat-sen UniversityGuangzhou · China1999–2005 · 5 papers🎓Xi'an University of TechnologyXi'an · China2009–2011 · 4 papers🎓Shanghai Jiao Tong UniversityShanghai · China2005–2008 · 4 papersEducation 2005–2008

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 22 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.

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 3 worksArts and Humanities · 3 worksComputer Science · 3 worksLanguage and Linguistics · 3 works

💡 Concepts 1Key ideas and methods explained on our concept pages.Semantic similarity · 2 works

 Works by year

2010s

20171 paperHua He's papers of 201720161 paperHua He's papers of 201620151 paperHua He's papers of 2015

 Papers

The most cited first (OpenAlex and our library).

  1. Multi-Perspective Sentence Similarity Modeling with Convolutional Neural Networks (2015 · 450 citations)
    The paper tackles sentence similarity: given two sentences, produce a score that can drive paraphrase detection or graded relatedness.
  2. Pairwise Word Interaction Modeling with Deep Neural Networks for Semantic Similarity Measurement (2016 · 295 citations)
    The paper tackles semantic textual similarity (STS), which means scoring how close two sentences are in meaning. The authors argue that the dominant neural "Siamese" approach compresses each sentence into a single fixed-length vector and loses word-level detail. Instead, they compare the two sentences word by word.
  3. A Continuously Growing Dataset of Sentential Paraphrases (2017 · 265 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…

All works

4 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them.

  1. Multi-Perspective Sentence Similarity Modeling with Convolutional Neural NetworksConference on Empirical Methods in Natural Language Processing (EMNLP)Hua He, Kevin Gimpel, Jimmy Lin2015 · 450 citations
  2. Pairwise Word Interaction Modeling with Deep Neural Networks for Semantic Similarity MeasurementConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Hua He, Jimmy Lin2016 · 295 citations
  3. A Continuously Growing Dataset of Sentential ParaphrasesConference on Empirical Methods in Natural Language Processing (EMNLP)Wuwei Lan, Siyu Qiu, Hua He, et al.2017 · 265 citations
  4. Gappy Pattern Matching on GPUs for On-Demand Extraction of Hierarchical Translation Grammars ↗Transactions of the Association for Computational Linguistics · no summary yetHua He, Jimmy Lin, Adam Lopez2015 · 7 citations

 Co-authors here

4 co-authors with a page, the most papers together first.

Venues

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

 Cited by

Papers of our library cite their works 248 times (of the 141,840 papers whose bibliographies we read); 24 citing papers with a page here →.

Updated

↑ back to top

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