--- title: "Hao Fang — author profile and papers" description: "Hao Fang, Shandong University: 2 papers on Elamur Research (2015–2020), h-index 16 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/hao-fang/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/hao-fang/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Hao Fang # Hao Fang Hao Fang's papers here sit where language meets other kinds of structure: images in one case, executable programs in the other. The two works span 2015 to 2020. They share a concern with how systems that produce or interpret natural language should be built and judged, whether that means describing a photograph in words or tracking what a user wants across a conversation. The most cited of these is [Microsoft COCO Captions](https://md.research.elamur.ai/free/en/papers/chen-2015-microsoft-coco-captions-data-collection/) (2015). It assembled a large collection of crowd-written descriptions for everyday scenes from Microsoft COCO, written under fixed guidelines. It also set up a shared server that scores captioning systems with one consistent set of metrics, so that results from different groups can be compared directly. The second paper, [Task-Oriented Dialogue as Dataflow Synthesis](https://md.research.elamur.ai/free/en/papers/andreas-2020-task-oriented-dialogue-as-dataflow/) (2020), offers an alternative to both fixed slot-based states and opaque neural ones. It represents the state of a conversation as a growing graph, and each user turn is translated into a small program that extends that graph. The later work thus moves from vision-and-language evaluation toward [dialogue systems](https://md.research.elamur.ai/free/en/topics/dialogue-systems/) and semantic parsing into programs. Collaborators on these papers include [Jacob Andreas](https://md.research.elamur.ai/free/en/authors/jacob-andreas/), [Jason Eisner](https://md.research.elamur.ai/free/en/authors/jason-eisner/), [Xinlei Chen](https://md.research.elamur.ai/free/en/authors/xinlei-chen/) and [C. Lawrence Zitnick](https://md.research.elamur.ai/free/en/authors/c-lawrence-zitnick/). Bylines connect Fang with the [University of Washington](https://md.research.elamur.ai/free/en/universities/university-of-washington/) in Seattle, and more recently with [Shandong University](https://md.research.elamur.ai/free/en/universities/shandong-university/) in Jinan. 2 papers on this site · 2015–2020 current affiliation [Shandong University](https://md.research.elamur.ai/free/en/universities/shandong-university/), Jinan, China Hao Fang has 2 papers on this site, in 2015–2020, most of them on [Dialogue systems](https://md.research.elamur.ai/free/en/topics/dialogue-systems/); often with [C. Lawrence Zitnick](https://md.research.elamur.ai/free/en/authors/c-lawrence-zitnick/), [Jacob Andreas](https://md.research.elamur.ai/free/en/authors/jacob-andreas/), [Jason Eisner](https://md.research.elamur.ai/free/en/authors/jason-eisner/). [OpenAlex](https://openalex.org/A5068398083) · [ORCID](https://orcid.org/0000-0002-8846-8294) · [**h-index 16**](https://openalex.org/authors/A5068398083) · [35 works](https://openalex.org/works?filter=author.id:A5068398083) · [2 447 citations](https://openalex.org/works?filter=author.id:A5068398083&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [2 works on this site](https://md.research.elamur.ai/free/en/authors/hao-fang/#papers) · [496 citations in our library](https://md.research.elamur.ai/free/en/authors/hao-fang/cited-by/) · [⭐ Paper Star rank #1198](https://md.research.elamur.ai/free/en/paper-stars/page/12/#star-1198) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Hao+Fang) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Hao+Fang) · [dblp](https://dblp.org/search?q=Hao+Fang) · [ACL Anthology](https://aclanthology.org/search/?q=Hao+Fang) ## Affiliations - [Shandong University](https://md.research.elamur.ai/free/en/universities/shandong-university/) · Jinan, China —current · 2023–2026 on 14 papers - [Fudan University](https://md.research.elamur.ai/free/en/universities/fudan-university/) · Shanghai, China —2025 on 2 papers - [University of Washington](https://md.research.elamur.ai/free/en/universities/university-of-washington/) · Seattle, United States —2015–2024 on 2 papers - [Zhejiang University](https://md.research.elamur.ai/free/en/universities/zhejiang-university/) · Hangzhou, China —2020–2021 on 3 papers - [Hangzhou Dianzi University](https://md.research.elamur.ai/free/en/universities/hangzhou-dianzi-university/) · Hangzhou, China —2021 on 2 papers - [Shenzhen University](https://ror.org/01vy4gh70) · Shenzhen, China —2021 on 2 papers From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 7 more institutions on single bylines are not listed. ## Topics [Dialogue systems 1](https://md.research.elamur.ai/free/en/topics/dialogue-systems/) ## Works by year ### 2020s [**2020** 1 paper](https://md.research.elamur.ai/free/en/papers/andreas-2020-task-oriented-dialogue-as-dataflow/) ### 2010s [**2015** 1 paper](https://md.research.elamur.ai/free/en/papers/chen-2015-microsoft-coco-captions-data-collection/) ## Papers The most cited first (OpenAlex and our library). 1. **[Microsoft COCO Captions: Data Collection and Evaluation Server](https://md.research.elamur.ai/free/en/papers/chen-2015-microsoft-coco-captions-data-collection/)** *(2015 · 1 859 citations)* Comparing image captioning systems was difficult because researchers used different metrics, and even different implementations of the same metric. 2. **[Task-Oriented Dialogue as Dataflow Synthesis](https://md.research.elamur.ai/free/en/papers/andreas-2020-task-oriented-dialogue-as-dataflow/)** *(2020 · 119 citations)* Task-oriented dialogue systems often force a choice between rigid slot-filling states, which are easy to learn but limited, and opaque neural states, which are flexible but hard to train. ## Co-authors here 7 co-authors with a page, the most papers together first. - [C. Lawrence Zitnick](https://md.research.elamur.ai/free/en/authors/c-lawrence-zitnick/) - [Jacob Andreas](https://md.research.elamur.ai/free/en/authors/jacob-andreas/) - [Jason Eisner](https://md.research.elamur.ai/free/en/authors/jason-eisner/) - [Piotr Dollar](https://md.research.elamur.ai/free/en/authors/piotr-dollar/) - [Ramakrishna Vedantam](https://md.research.elamur.ai/free/en/authors/ramakrishna-vedantam/) - [Tsung-Yi Lin](https://md.research.elamur.ai/free/en/authors/tsung-yi-lin/) - [Xinlei Chen](https://md.research.elamur.ai/free/en/authors/xinlei-chen/) ## Cited by Papers of our library cite their works 496 times (of the 140 884 papers whose bibliographies we read); [59 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/hao-fang/cited-by/).