We made use of different techniques to improve the translation between these languages.
In this paper, we present two productive and functional recommender methods to improve the ac- curacy of predicting the right product for the user.
We further investigate the suitability of different speech encoders (wav2vec 2. 0, HuBERT) for our models and the impact of knowledge distillation from the Machine Translation model that we use for the decoder (mBART).
A lifelong learning system can adapt to new data without forgetting previously acquired knowledge.
In this article, we describe the TALP-UPC participation in the WMT20 news translation shared task for Tamil-English.
This paper describes the participation of the NLP research team of the IPN Computer Research center in the WMT 2020 Similar Language Translation Task.
1 code implementation • • Marta R. Costa-jussà, James Cross, Onur Çelebi, Maha Elbayad, Kenneth Heafield, Kevin Heffernan, Elahe Kalbassi, Janice Lam, Daniel Licht, Jean Maillard, Anna Sun, Skyler Wang, Guillaume Wenzek, Al Youngblood, Bapi Akula, Loic Barrault, Gabriel Mejia Gonzalez, Prangthip Hansanti, John Hoffman, Semarley Jarrett, Kaushik Ram Sadagopan, Dirk Rowe, Shannon Spruit, Chau Tran, Pierre Andrews, Necip Fazil Ayan, Shruti Bhosale, Sergey Edunov, Angela Fan, Cynthia Gao, Vedanuj Goswami, Francisco (Paco) Guzmán, Philipp Koehn, Alexandre Mourachko, Christophe Ropers, Safiyyah Saleem, Holger Schwenk, Jeff Wang
Driven by the goal of eradicating language barriers on a global scale, machine translation has solidified itself as a key focus of artificial intelligence research today.
In Neural Machine Translation (NMT), each token prediction is conditioned on the source sentence and the target prefix (what has been previously translated at a decoding step).
Different approaches have been proposed to overcome these problems, such as the use of efficient attention mechanisms.
The Transformer architecture aggregates input information through the self-attention mechanism, but there is no clear understanding of how this information is mixed across the entire model.
The proposed solution, a T5 architecture, is trained in a multi-task semi-supervised environment, with our collected non-parallel data, following a cycle training regime.
Speech translation datasets provide manual segmentations of the audios, which are not available in real-world scenarios, and existing segmentation methods usually significantly reduce translation quality at inference time.
This work proposes an extensive analysis of the Transformer architecture in the Neural Machine Translation (NMT) setting.
Our submission also uses a custom segmentation algorithm that employs pre-trained Wav2Vec 2. 0 for identifying periods of untranscribable text and can bring improvements of 2. 5 to 3 BLEU score on the IWSLT 2019 test set, as compared to the result with the given segmentation.
Ranked #2 on Speech-to-Text Translation on MuST-C EN->DE (using extra training data)
Gender, race and social biases have recently been detected as evident examples of unfairness in applications of Natural Language Processing.
At the Workshop on Gender Bias in NLP (GeBNLP), we'd like to encourage authors to give explicit consideration to the wider aspects of bias and its social implications.
The standard approach to incorporate linguistic information to neural machine translation systems consists in maintaining separate vocabularies for each of the annotated features to be incorporated (e. g. POS tags, dependency relation label), embed them, and then aggregate them with each subword in the word they belong to.
Multilingual Neural Machine Translation architectures mainly differ in the amount of sharing modules and parameters among languages.
However, it is difficult for existing deep learning architectures to learn a new task without largely forgetting previously acquired knowledge.
no code implementations • • Loïc Barrault, Magdalena Biesialska, Ondřej Bojar, Marta R. Costa-jussà, Christian Federmann, Yvette Graham, Roman Grundkiewicz, Barry Haddow, Matthias Huck, Eric Joanis, Tom Kocmi, Philipp Koehn, Chi-kiu Lo, Nikola Ljubešić, Christof Monz, Makoto Morishita, Masaaki Nagata, Toshiaki Nakazawa, Santanu Pal, Matt Post, Marcos Zampieri
In the news task, participants were asked to build machine translation systems for any of 11 language pairs, to be evaluated on test sets consisting mainly of news stories.
On the other hand, Multilingual Neural Machine Translation (MultiNMT) approaches rely on higher-quality and more massive data sets.
WinoST is the speech version of WinoMT which is a MT challenge set and both follow an evaluation protocol to measure gender accuracy.
We propose a modular architecture of language-specific encoder-decoders that constitutes a multilingual machine translation system that can be incrementally extended to new languages without the need for retraining the existing system when adding new languages.
In this report we are taking the standardized model proposed by Gebru et al. (2018) for documenting the popular machine translation datasets of the EuroParl (Koehn, 2005) and News-Commentary (Barrault et al., 2019).
In this work, we present an effective method for semantic specialization of word vector representations.
Introducing factors, that is to say, word features such as linguistic information referring to the source tokens, is known to improve the results of neural machine translation systems in certain settings, typically in recurrent architectures.
State-of-the-art multilingual machine translation relies on a universal encoder-decoder, which requires retraining the entire system to add new languages.
The dominant language modeling paradigm handles text as a sequence of discrete tokens.
In this paper, we propose a self-supervised method to refine the alignment of unsupervised bilingual word embeddings.
We then used this dataset to train Spanish QA systems by fine-tuning a Multilingual-BERT model.
We introduce GeBioToolkit, a tool for extracting multilingual parallel corpora at sentence level, with document and gender information from Wikipedia biographies.
Although the problem of similar language translation has been an area of research interest for many years, yet it is still far from being solved.
In this context, RNN's, CNN's and Transformer have most commonly been used as an encoder-decoder architecture with multiple layers in each module.
Multilingual Neural Machine Translation approaches are based on the use of task-specific models and the addition of one more language can only be done by retraining the whole system.
The dominant neural machine translation models are based on the encoder-decoder structure, and many of them rely on an unconstrained receptive field over source and target sequences.
Ranked #10 on Machine Translation on WMT2014 English-French
By adding and forcing this interlingual loss, we are able to train multiple encoders and decoders for each language, sharing a common intermediate representation.
We take advantage of the fact that word embeddings are used in neural machine translation to propose a method to equalize gender biases in neural machine translation using these representations.
Preliminary results on the WMT 2017 Turkish/English task shows that the proposed architecture is capable of learning a universal language representation and simultaneously training both translation directions with state-of-the-art results.
In this paper we present the first neural-based machine translation system trained to translate between standard national varieties of the same language.
This paper describes the methodology followed to build a neural machine translation system in the biomedical domain for the English-Catalan language pair.
In this paper, we propose to de-couple machine translation from morphology generation in order to better deal with the problem.
Although, Chinese and Spanish are two of the most spoken languages in the world, not much research has been done in machine translation for this language pair.