--- title: "Iulian Vlad Serban — author profile and papers" description: "Iulian Vlad Serban: 6 papers on Elamur Research (2015–2019), h-index 26 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/iulian-vlad-serban/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/iulian-vlad-serban/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Iulian Vlad Serban # Iulian Vlad Serban Iulian Vlad Serban works on open-domain dialogue systems, with papers here spanning 2015–2019. The work keeps returning to three questions: how conversational agents can learn directly from large collections of human exchanges, how their replies can be made less generic, and how anyone can tell whether a reply is good. The methods are mostly hierarchical recurrent neural networks and latent-variable generative models, applied to large scraped or crowdsourced corpora and checked against human ratings gathered on Mechanical Turk. Among the most cited papers is [Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models](https://md.research.elamur.ai/free/en/papers/serban-2015-building-end-end-dialogue-systems/) (2015). It recasts conversation as generative modelling by adapting the hierarchical recurrent encoder-decoder (HRED), originally built for query suggestion. In this setup one network reads each utterance, a second tracks the dialogue across turns, and a decoder writes the next reply. The paper also released the MovieTriples dataset. [The Ubuntu Dialogue Corpus](https://md.research.elamur.ai/free/en/papers/lowe-2015-ubuntu-dialogue-corpus-large-dataset/) (2015) tackled the shortage of public conversational data by extracting multi-turn exchanges from Ubuntu support channels on IRC, separating interleaved threads with a heuristic. [A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues](https://md.research.elamur.ai/free/en/papers/serban-2016-hierarchical-latent-variable-encoder-decoder/) (2016) introduced VHRED. This model extends HRED with a Gaussian latent variable, drawn once per utterance and trained through a variational bound, so that replies stay tied to the wider conversation. The later papers turn toward evaluation. [Towards an Automatic Turing Test](https://md.research.elamur.ai/free/en/papers/lowe-2017-towards-automatic-turing-test-learning/) (2017) frames the scoring of responses as a learning problem. Its model, ADEM, is trained on human appropriateness judgments of Twitter replies and compares context, reference and candidate to predict a human-like score, rather than counting shared words as BLEU does. [ConvAI2](https://md.research.elamur.ai/free/en/papers/dinan-2019-second-conversational-intelligence-challenge-convai2/) (2019) describes a NeurIPS 2018 competition built on Persona-Chat. It offered chit-chat research a shared benchmark that paired automatic metrics with human judging. Serban's papers here were written at the [Université de Montréal](https://md.research.elamur.ai/free/en/universities/universite-de-montreal/) (2015–2020), with some later bylines also at [Mila - Quebec Artificial Intelligence Institute](https://md.research.elamur.ai/free/en/labs/mila-quebec-artificial-intelligence-institute/). Frequent co-authors include [Joelle Pineau](https://md.research.elamur.ai/free/en/authors/joelle-pineau/), [Ryan Lowe](https://md.research.elamur.ai/free/en/authors/ryan-lowe/) and [Yoshua Bengio](https://md.research.elamur.ai/free/en/authors/yoshua-bengio/), along with Aaron Courville and Alessandro Sordoni. All of the work belongs to the topic of [dialogue systems](https://md.research.elamur.ai/free/en/topics/dialogue-systems/). Iulian Vlad Serban has 6 papers in our library, in 2015–2019, most of them on [Dialogue systems](https://md.research.elamur.ai/free/en/topics/dialogue-systems/), [Evaluation & benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/); often with [Joelle Pineau](https://md.research.elamur.ai/free/en/authors/joelle-pineau/), [Ryan Lowe](https://md.research.elamur.ai/free/en/authors/ryan-lowe/), [Yoshua Bengio](https://md.research.elamur.ai/free/en/authors/yoshua-bengio/). 6 papers in our library · 2015–2019 [OpenAlex](https://openalex.org/A5034688833) · [**h-index 26**](https://openalex.org/authors/A5034688833) · [47 works](https://openalex.org/works?filter=author.id:A5034688833) · [8,963 citations](https://openalex.org/works?filter=author.id:A5034688833&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 6 works in our library](https://md.research.elamur.ai/free/en/authors/iulian-vlad-serban/#papers) · [🔗 1,816 citations in our library](https://md.research.elamur.ai/free/en/authors/iulian-vlad-serban/cited-by/) · [1 more in our library without a page yet](#also) · [⭐ Paper Star rank #842](https://md.research.elamur.ai/free/en/paper-stars/page/9/#star-842) 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=Iulian+Vlad+Serban) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Iulian+Vlad+Serban) · [dblp](https://dblp.org/search?q=Iulian+Vlad+Serban) · [ACL Anthology](https://aclanthology.org/search/?q=Iulian+Vlad+Serban) ## Affiliations [🎓**Université de Montréal** Montreal · Canada 2015–2020 · 21 papers](https://md.research.elamur.ai/free/en/universities/universite-de-montreal/) · [🔬**Mila - Quebec Artificial Intelligence Institute** Montreal · Canada 2018–2020 · 2 papers](https://md.research.elamur.ai/free/en/labs/mila-quebec-artificial-intelligence-institute/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 more institutions on single bylines are not listed. ## Topics [Dialogue systems (6)](https://md.research.elamur.ai/free/en/topics/dialogue-systems/) · [Evaluation & benchmarks (1)](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) ## Works by year ### 2010s [**2019** 1 paper](https://md.research.elamur.ai/free/en/papers/dinan-2019-second-conversational-intelligence-challenge-convai2/) · [**2017** 1 paper](https://md.research.elamur.ai/free/en/papers/lowe-2017-towards-automatic-turing-test-learning/) · [**2016** 2 papers](https://md.research.elamur.ai/free/en/authors/iulian-vlad-serban/year/2016/) · [**2015** 2 papers](https://md.research.elamur.ai/free/en/authors/iulian-vlad-serban/year/2015/) ## Papers The most cited first (OpenAlex and our library). 1. **[The Second Conversational Intelligence Challenge (ConvAI2)](https://md.research.elamur.ai/free/en/papers/dinan-2019-second-conversational-intelligence-challenge-convai2/)** *(2019 · 525 citations)* ConvAI2 was a NeurIPS 2018 competition designed to give open-domain chit-chat research a common benchmark and evaluation protocol, which the field had lacked. 2. **[Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models](https://md.research.elamur.ai/free/en/papers/serban-2015-building-end-end-dialogue-systems/)** *(2015 · 524 citations)* Open-domain chatbots of this era either retrieved existing responses or relied on hand-built state and action representations, which made them expensive to build and tied to narrow domains. 3. **[A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues](https://md.research.elamur.ai/free/en/papers/serban-2016-hierarchical-latent-variable-encoder-decoder/)** *(2016 · 518 citations)* Standard RNN-based dialogue generators, including RNNLM and HRED, introduce randomness only when each output token is sampled. 4. **[How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation](https://md.research.elamur.ai/free/en/papers/liu-2016-how-not-evaluate-your-dialogue/)** *(2016 · 500 citations)* The paper examines whether automatic metrics can be trusted when evaluating unsupervised dialogue models, that is, chatbots that generate a response based solely on the conversation context. 5. **[Towards an Automatic Turing Test: Learning to Evaluate Dialogue Responses](https://md.research.elamur.ai/free/en/papers/lowe-2017-towards-automatic-turing-test-learning/)** *(2017 · 486 citations)* Open-domain chatbots are still commonly scored with word-overlap metrics such as BLEU, which often disagree with human ratings. 6. **[The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems](https://md.research.elamur.ai/free/en/papers/lowe-2015-ubuntu-dialogue-corpus-large-dataset/)** *(2015 · 474 citations)* Neural dialogue systems have advanced more slowly than vision or speech systems. The authors attribute this mainly to the lack of large public conversational datasets. Slot-filling corpora such as DSTC are small, and Twitter/Weibo collections are mostly unreleased and dominated by very short exchanges. To address… ## Also in our library 1 more work of theirs is in our library without a page here yet; it will appear as we publish them. ## Co-authors here 12 of 15 co-authors with a page, the most papers together first. - [Joelle Pineau](https://md.research.elamur.ai/free/en/authors/joelle-pineau/) ×5 - [Ryan Lowe](https://md.research.elamur.ai/free/en/authors/ryan-lowe/) ×5 - [Yoshua Bengio](https://md.research.elamur.ai/free/en/authors/yoshua-bengio/) ×3 - [Aaron Courville](https://md.research.elamur.ai/free/en/authors/aaron-courville/) ×2 - [Alessandro Sordoni](https://md.research.elamur.ai/free/en/authors/alessandro-sordoni/) ×2 - [Laurent Charlin](https://md.research.elamur.ai/free/en/authors/laurent-charlin/) ×2 - [Alan W Black](https://md.research.elamur.ai/free/en/authors/alan-w-black/) - [Alexander Miller](https://md.research.elamur.ai/free/en/authors/alexander-miller/) - [Arthur Szlam](https://md.research.elamur.ai/free/en/authors/arthur-szlam/) - [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/) ## Cited by Papers of our library cite their works 1,816 times (of the 140,884 papers whose bibliographies we read); [103 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/iulian-vlad-serban/cited-by/).