Unbabel Unbabel API Chat FAQs Tickets Video Facebook Instagram LinkedIn Twitter YouTube

Helena Moniz

Post-doc researcher at FLUL/INESC-ID and Quality Research

Helena Moniz is the Principal Investigator in the Quality Assurance Project between Unbabel and INESC-ID, Lisbon, charged with creating scalable processes to evaluate the performance of humans and MT systems in Unbabel’s translation pipeline. She recently implemented a new system to judge Unbabel’s translation quality through a new state-of-the-art metric - the Multidimensional Quality Metric (MQM), developed in QTLaunchPad -- a European Commission-funded collaborative research initiative (2012-2014). Since 2001, Helena has been a researcher at INESC-ID Lisbon and at the Linguistic Center of the University of Lisbon, where she has been involved in 13 national and international projects, including INTERACT with Unbabel (H2020 MSCA-RISE, 230K EUR), and as an independent researcher in INSIDE (CMUP-ERI/HCI/0051/2013, 600K EUR); in SpeDial EU Project (FP7-ICT- 2013-SME-DCA); she was also the INESC-ID coordinator in the national project VOCE. Her research interests include Speech Processing, Prosody, Paralinguistics, Natural Language Processing, Annotation criteria, and lately Human and Machine Translation, focusing on scalable Quality Assurance processes.

Papers published


The Interact Project and Crisis MT.

XVI Machine Translation Summit 2017


Bilingual experiments on automatic recovery of capitalization and punctuation of automatic speech transcripts.

IEEE Transactions on Audio, Speech, and Language Processing 2012


  • Unbabel Scribe

    Research & develop a solution for automatic transcription and translation of audiovisual content combined with a community of human translators (P2020 Co-Funded Project).

  • MT4ALL

    Contribute to the CEF Automated Translation Building block by enlarging its coverage for language pairs and domains for which parallel data does not exist (H2020 Co-Funded Project).