--- title: "Gholamreza Haffari — author profile and papers" description: "Gholamreza Haffari, National University of Singapore: 7 papers on Elamur Research (2017–2020), h-index 38 — affiliations, topics, co-authors and who…" canonical: "https://research.elamur.ai/free/en/authors/gholamreza-haffari/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/gholamreza-haffari/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Gholamreza Haffari # Gholamreza Haffari 7 papers on this site · 2017–2020 current affiliation [National University of Singapore](https://ror.org/01tgyzw49), Singapore, Singapore; [Monash University](https://ror.org/02bfwt286), Melbourne, Australia Gholamreza Haffari has 7 papers on this site, in 2017–2020, most of them on [Machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/), [Speech act theory](https://md.research.elamur.ai/free/en/topics/speech-act-theory/), [Dialogue systems](https://md.research.elamur.ai/free/en/topics/dialogue-systems/); often with [Sameen Maruf](https://md.research.elamur.ai/free/en/authors/sameen-maruf/), [André F. T. Martins](https://md.research.elamur.ai/free/en/authors/andre-f-t-martins/), [Ingrid Zukerman](https://md.research.elamur.ai/free/en/authors/ingrid-zukerman/). [OpenAlex](https://openalex.org/A5081525024) · [ORCID](https://orcid.org/0000-0001-7326-8380) · [**h-index 38**](https://openalex.org/authors/A5081525024) · [304 works](https://openalex.org/works?filter=author.id:A5081525024) · [13 767 citations](https://openalex.org/works?filter=author.id:A5081525024&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [7 works on this site](https://md.research.elamur.ai/free/en/authors/gholamreza-haffari/#papers) · [787 citations in our library](https://md.research.elamur.ai/free/en/authors/gholamreza-haffari/cited-by/) · 22 more works in our library 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=Gholamreza+Haffari) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Gholamreza+Haffari) · [dblp](https://dblp.org/search?q=Gholamreza+Haffari) · [ACL Anthology](https://aclanthology.org/search/?q=Gholamreza+Haffari) ## Affiliations - [Monash University](https://ror.org/02bfwt286) · Melbourne, Australia —current · 2011–2026 on 224 papers · employment 2011–2015: Lecturer, Faculty of Information Technology (ORCID) · employment from 2016: Senior Lecturer, Faculty of Information Technology (ORCID) - [National University of Singapore](https://ror.org/01tgyzw49) · Singapore, Singapore —current · 2026 on 1 paper - [The University of Melbourne](https://ror.org/01ej9dk98) · Melbourne, Australia —2015–2025 on 6 papers - [eBay (United States)](https://ror.org/05cnabr44) · San Jose, United States —2022 on 2 papers - [IITB-Monash Research Academy](https://ror.org/02r3nf527) · Mumbai, India —2016–2021 on 3 papers - [Indian Institute of Technology Bombay](https://ror.org/02qyf5152) · Mumbai, India —2016–2021 on 3 papers - [The University of Queensland](https://ror.org/00rqy9422) · Brisbane, Australia —2020 on 2 papers - [Simon Fraser University](https://ror.org/0213rcc28) · Burnaby, Canada —2004–2012 on 13 papers · education 2004–2010: PhD, Computer Science (ORCID) - [BC Cancer Agency](https://ror.org/03sfybe47) · Vancouver, Canada —2011–2012 on 4 papers - [University of British Columbia](https://ror.org/03rmrcq20) · Vancouver, Canada —2010–2012 on 4 papers · employment 2010–2011: Postdoctoral Fellow, Molecular Oncology (ORCID) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 12 more institutions on single bylines are not listed. ## Topics [Machine translation 4](https://md.research.elamur.ai/free/en/topics/machine-translation/) · [Speech act theory 2](https://md.research.elamur.ai/free/en/topics/speech-act-theory/) · [Dialogue systems 2](https://md.research.elamur.ai/free/en/topics/dialogue-systems/) · [Evaluation & benchmarks 1](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) ## Papers The most cited first (OpenAlex and our library). 1. **[Graph-to-Sequence Learning using Gated Graph Neural Networks](https://md.research.elamur.ai/free/en/papers/beck-2018-graph-sequence-learning-gated-graph/)** *(2018 · 456 citations)* Many NLP tasks require turning a graph into text. Examples include generating sentences from semantic graphs or translating a source sentence annotated with a syntactic tree. Earlier methods had drawbacks. Grammar-based systems need node–token alignments, and linearising the graph throws away structure. Earlier… 2. **[Iterative Back-Translation for Neural Machine Translation](https://md.research.elamur.ai/free/en/papers/hoang-2018-iterative-back-translation-neural-machine/)** *(2018 · 420 citations)* Neural machine translation (NMT) can use target-language monolingual text by back-translating it into the source language. 3. **[Selective Attention for Context-aware Neural Machine Translation](https://md.research.elamur.ai/free/en/papers/maruf-2019-selective-attention-context-aware-neural/)** *(2019 · 263 citations)* Most context-aware neural MT systems look only at a handful of preceding sentences. This limits how well they handle discourse phenomena that depend on the wider document, and it makes them hard to scale. Maruf, Martins and Haffari address this with a memory-efficient context module for the Transformer that can draw… 4. **[Document Context Neural Machine Translation with Memory Networks](https://md.research.elamur.ai/free/en/papers/maruf-2018-document-context-neural-machine-translation/)** *(2018 · 236 citations)* Most neural MT systems translate each sentence in isolation. This ignores discourse phenomena such as pronoun reference and consistent word choice, which can depend on context far beyond the neighbouring sentences. Maruf and Haffari treat document translation as structured prediction. Their factor graph links each… 5. **[A Hierarchical Neural Model for Learning Sequences of Dialogue Acts](https://md.research.elamur.ai/free/en/papers/tran-2017-hierarchical-neural-model-learning-sequences/)** *(2017 · 44 citations)* The paper addresses dialogue act (DA) classification: assigning a DA label to each utterance in a conversation, where the label must be predicted immediately, without access to later turns. 6. **[Findings of the WMT 2020 Shared Task on Chat Translation](https://md.research.elamur.ai/free/en/papers/farajian-2020-findings-wmt-2020-shared-task/)** *(2020 · 29 citations)* This report presents the inaugural WMT competition devoted to translating chat. Its focus is bilingual customer-support conversations in which a German-speaking customer and an English-speaking agent each write in their own language. Such chat text is short, informal, noisy and heavy in pronouns, and public data for… 7. **[Preserving Distributional Information in Dialogue Act Classification](https://md.research.elamur.ai/free/en/papers/tran-2017-preserving-distributional-information-dialogue-act/)** *(2017 · 22 citations)* The paper addresses online dialogue act (DA) classification, where each utterance must be labeled as it arrives, without seeing future turns. ## Also in our library 22 more works of theirs are in our library without a page here yet; they will appear as we publish them. ## Co-authors here 8 co-authors with a page, the most papers together first. - [Sameen Maruf](https://md.research.elamur.ai/free/en/authors/sameen-maruf/) ×3 - [André F. T. Martins](https://md.research.elamur.ai/free/en/authors/andre-f-t-martins/) ×2 - [Ingrid Zukerman](https://md.research.elamur.ai/free/en/authors/ingrid-zukerman/) ×2 - [Quan Hung Tran](https://md.research.elamur.ai/free/en/authors/quan-hung-tran/) ×2 - [Trevor Cohn](https://md.research.elamur.ai/free/en/authors/trevor-cohn/) ×2 - [António V. Lopes](https://md.research.elamur.ai/free/en/authors/antonio-v-lopes/) - [Mohammad Amin Farajian](https://md.research.elamur.ai/free/en/authors/mohammad-amin-farajian/) - [Philipp Koehn](https://md.research.elamur.ai/free/en/authors/philipp-koehn/) ## Cited by Papers of our library cite their works 787 times (of the 140 884 papers whose bibliographies we read); [60 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/gholamreza-haffari/cited-by/).