Lingua Custodia Lab publishes their latest research on NLP
Today, Lingua Custodia Lab team present their NLP research article “Approach to integrating terminology constraints into neural translation models” which has been selected for publication at the TALN-RECITAL conference 2022 in Avignon, France.
From 27 June to 1 July 2022, the French Computer Science and Systems Laboratory (“LIS”) and the Computer Laboratory from Avignon University (“LIA”), alongside the Association for Natural Language Processing (ATALA) jointly organise the 29th conference about NLP (TALN in French) and the 24th meeting of Students Researchers in Computer Science for NLP (RECITAL in French).
TALN RECITAL conference program 2022
Preparing Machine Translation Conference WMT 2022
For the third year in a row, the Lingua Custodia Lab will be participating to a shared task at the seventh conference on Machine Translation – WMT 2022 – which will be held in Abu Dhabi in December.
https://statmt.org/wmt22/word-autocompletion.html
For the fourth year in a row, they also helped prepare the General Machine Translation shared task by providing test sets, alongside Microsoft, Facebook, NTT, the University of Tokyo, and Webinterpret this year.
https://statmt.org/wmt22/translation-task.html
Past contribution and publication
January 2022 / Covid-19 MLIA Challenge
The Lingua Custodia Lab made it 1st in 4 out of 7 languages pairs in the 2nd round of Covid-19 MLIA Challenge – a European collaboration project supported by the European Commission, the European Language Resources Coordination (ELRC), and several other entities and universities.
The objective is to organise a community evaluation effort in order to accelerate the creation of resources and tools for improved Multilingual Information Access using Machine Learning technology.
November 2021 / Machine Translation Conference WMT
Lingua Custodia’s participation at WMT 2021 shared task on machine translation using terminologies.
https://arxiv.org/abs/2111.02120
July 2021 / ACL-IJCNLP Conference
Research paper “Encouraging Neural Machine Translation to Satisfy Terminology Constraints” has been accepted for publication at the 59th Annual Meeting of the Association for Computational Linguistics (ACL) and the 11th International Joint Conference in Natural Language Processing.
This recognition confirms the Lab’s position as a leader in the NLP field, alongside most prestigious companies: Google Research, Facebook AI or Amazon Sciences.
A propos de Lingua Custodia
Lingua Custodia is a Fintech company leader in Natural Language Processing (NLP) for Finance. It was created in 2011 by finance professionals to initially offer specialised machine translation.
Leveraging its state-of-the-art NLP expertise, the company now offers a growing range of applications: Speech-to-Text automation, Document classification, Linguistic data extraction from unstructured documents, Mass web crawling and data collection, … and achieves superior quality thanks to highly domain-focused machine learning algorithms.
Its cutting-edge technology has been regularly rewarded and recognised by both the industry and clients: Investment houses, custody or investment banks, private banks, financial divisions within major corporations and service providers for financial institutions.