--- title: "Saizheng Zhang — author profile and papers" description: "Saizheng Zhang: 2 papers on Elamur Research (2018), h-index 19 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/saizheng-zhang/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/saizheng-zhang/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Saizheng Zhang # Saizheng Zhang Saizheng Zhang works in natural language processing, with a focus on building large crowdsourced English datasets that test what language systems can actually do. The two papers here, both from 2018, fall under [question answering](https://md.research.elamur.ai/free/en/topics/question-answering/) and [dialogue systems](https://md.research.elamur.ai/free/en/topics/dialogue-systems/). A shared concern runs through them: designing data collection so that models cannot get by on shallow word matching and must instead reason across sources or keep a consistent conversational identity. The more widely cited of the two is [HotpotQA](https://md.research.elamur.ai/free/en/papers/yang-2018-hotpotqa-dataset-diverse-explainable-multi/), a benchmark of roughly 113k question-answer pairs drawn from English Wikipedia. It targets questions that need evidence from more than one paragraph. Linked article introductions are paired through chosen bridge entities, and entity pairs from curated lists yield comparison questions, some answerable with yes or no. The dataset was built in response to earlier benchmarks that could often be solved from a single nearby sentence, were constrained by knowledge-base schemas, or gave no signal about which evidence backs an answer. The second paper, [Personalizing Dialogue Agents](https://md.research.elamur.ai/free/en/papers/zhang-2018-personalizing-dialogue-agents-i-have/), addresses chit-chat bots that sound generic and shift character from turn to turn. It conditions an agent on a few sentences describing a persona and introduces the PERSONA-CHAT corpus, in which pairs of crowdworkers were assigned random profiles and talked to get acquainted. Separate workers then paraphrased the profiles to block lexical shortcuts, and the paper compares retrieval, sequence-to-sequence and ranking models on predicting the next utterance. Both works are also the most recent here, so the newest direction is the same pairing of multi-hop question answering and persona-grounded conversation. Zhang's bylines are mostly from the [Université de Montréal](https://md.research.elamur.ai/free/en/universities/universite-de-montreal/) (2014–2018) and Mila – Quebec Artificial Intelligence Institute (2016–2018), with [Carnegie Mellon University](https://md.research.elamur.ai/free/en/universities/carnegie-mellon-university/) and [Stanford University](https://md.research.elamur.ai/free/en/universities/stanford-university/) appearing in 2018. The HotpotQA team included [Zhilin Yang](https://md.research.elamur.ai/free/en/authors/zhilin-yang/), [Peng Qi](https://md.research.elamur.ai/free/en/authors/peng-qi/), [Yoshua Bengio](https://md.research.elamur.ai/free/en/authors/yoshua-bengio/) and [Christopher D. Manning](https://md.research.elamur.ai/free/en/authors/christopher-d-manning/). The dialogue work was written with [Jason Weston](https://md.research.elamur.ai/free/en/authors/jason-weston/), Emily Dinan, Douwe Kiela and others. Saizheng Zhang has 2 papers in our library, in 2018, most of them on [Question answering](https://md.research.elamur.ai/free/en/topics/question-answering/), [Dialogue systems](https://md.research.elamur.ai/free/en/topics/dialogue-systems/); often with [Arthur Szlam](https://md.research.elamur.ai/free/en/authors/arthur-szlam/), [Christopher D. Manning](https://md.research.elamur.ai/free/en/authors/christopher-d-manning/), [Douwe Kiela](https://md.research.elamur.ai/free/en/authors/douwe-kiela/). 2 papers in our library · 2018 [OpenAlex](https://openalex.org/A5014123853) · [**h-index 19**](https://openalex.org/authors/A5014123853) · [28 works](https://openalex.org/works?filter=author.id:A5014123853) · [6,526 citations](https://openalex.org/works?filter=author.id:A5014123853&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 2 works in our library](https://md.research.elamur.ai/free/en/authors/saizheng-zhang/#papers) · [🔗 2,440 citations in our library](https://md.research.elamur.ai/free/en/authors/saizheng-zhang/cited-by/) · [⭐ Paper Star rank #483](https://md.research.elamur.ai/free/en/paper-stars/page/5/#star-483) 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=Saizheng+Zhang) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Saizheng+Zhang) · [dblp](https://dblp.org/search?q=Saizheng+Zhang) · [ACL Anthology](https://aclanthology.org/search/?q=Saizheng+Zhang) ## Affiliations [🎓**Université de Montréal** Montreal · Canada 2014–2018 · 15 papers](https://md.research.elamur.ai/free/en/universities/universite-de-montreal/) · [🔬**Mila - Quebec Artificial Intelligence Institute** Montreal · Canada 2016–2018 · 9 papers](https://md.research.elamur.ai/free/en/labs/mila-quebec-artificial-intelligence-institute/) · [🎓**Carnegie Mellon University** Pittsburgh · United States 2018 · 2 papers](https://md.research.elamur.ai/free/en/universities/carnegie-mellon-university/) · [🎓**Stanford University** Stanford · United States 2018 · 2 papers](https://md.research.elamur.ai/free/en/universities/stanford-university/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 3 more institutions on single bylines are not listed. ## Topics [Question answering (1)](https://md.research.elamur.ai/free/en/topics/question-answering/) · [Dialogue systems (1)](https://md.research.elamur.ai/free/en/topics/dialogue-systems/) ## Works by year ### 2010s [**2018** 2 papers](https://md.research.elamur.ai/free/en/authors/saizheng-zhang/year/2018/) ## Papers The most cited first (OpenAlex and our library). 1. **[HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://md.research.elamur.ai/free/en/papers/yang-2018-hotpotqa-dataset-diverse-explainable-multi/)** *(2018 · 3,489 citations)* Earlier QA benchmarks such as SQuAD, TriviaQA and SearchQA can mostly be solved by matching a question to one or a few nearby sentences. 2. **[Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://md.research.elamur.ai/free/en/papers/zhang-2018-personalizing-dialogue-agents-i-have/)** *(2018 · 1,839 citations)* Open-domain chit-chat bots often feel bland. Their personality shifts from turn to turn, they forget earlier context, and they fall back on vague replies. The authors address this by giving a dialogue agent an explicit text persona, a few short sentences describing who it is. They also release PERSONA-CHAT, a… ## Co-authors here 11 co-authors with a page, the most papers together first. - [Arthur Szlam](https://md.research.elamur.ai/free/en/authors/arthur-szlam/) - [Christopher D. Manning](https://md.research.elamur.ai/free/en/authors/christopher-d-manning/) - [Douwe Kiela](https://md.research.elamur.ai/free/en/authors/douwe-kiela/) - [Emily Dinan](https://md.research.elamur.ai/free/en/authors/emily-dinan/) - [Jack Urbanek](https://md.research.elamur.ai/free/en/authors/jack-urbanek/) - [Jason Weston](https://md.research.elamur.ai/free/en/authors/jason-weston/) - [Peng Qi](https://md.research.elamur.ai/free/en/authors/peng-qi/) - [Ruslan Salakhutdinov](https://md.research.elamur.ai/free/en/authors/ruslan-salakhutdinov/) - [William Cohen](https://md.research.elamur.ai/free/en/authors/william-cohen/) - [Yoshua Bengio](https://md.research.elamur.ai/free/en/authors/yoshua-bengio/) - [Zhilin Yang](https://md.research.elamur.ai/free/en/authors/zhilin-yang/) ## Cited by Papers of our library cite their works 2,440 times (of the 140,884 papers whose bibliographies we read); [196 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/saizheng-zhang/cited-by/).