Search Results for author:
Found 78 papers, 29 papers with code
Pretrained Speech Encoders and Efficient Fine-tuning Methods for Speech Translation: UPC at IWSLT 2022
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).
Multilingual Neural Machine Translation: Case-study for Catalan, Spanish and Portuguese Romance Languages
We made use of different techniques to improve the translation between these languages.
The IPN-CIC team system submission for the WMT 2020 similar language task
This paper describes the participation of the NLP research team of the IPN Computer Research center in the WMT 2020 Similar Language Translation Task.
The TALP-UPC System Description for WMT20 News Translation Task: Multilingual Adaptation for Low Resource MT
In this article, we describe the TALP-UPC participation in the WMT20 news translation shared task for Tamil-English.
Findings of the First Shared Task on Lifelong Learning Machine Translation
A lifelong learning system can adapt to new data without forgetting previously acquired knowledge.
E-Commerce Content and Collaborative-based Recommendation using K-Nearest Neighbors and Enriched Weighted Vectors
In this paper, we present two productive and functional recommender methods to improve the ac- curacy of predicting the right product for the user.
Fine-tuning Neural Machine Translation on Gender-Balanced Datasets
Misrepresentation of certain communities in datasets is causing big disruptions in artificial intelligence applications.
Large Concept Models: Language Modeling in a Sentence Representation Space
In this paper, we present an attempt at an architecture which operates on an explicit higher-level semantic representation, which we name a concept.
LCFO: Long Context and Long Form Output Dataset and Benchmarking
The primary motivation behind providing summaries of different lengths is to establish a controllable framework for generating long texts from shorter inputs, i. e. summary expansion.
2M-BELEBELE: Highly Multilingual Speech and American Sign Language Comprehension Dataset
We introduce the first highly multilingual speech and American Sign Language (ASL) comprehension dataset by extending BELEBELE.
Y-NQ: English-Yorùbá Evaluation dataset for Open-Book Reading Comprehension and Text Generation
The purpose of this work is to share an English-Yor\`ub\'a evaluation dataset for open-book reading comprehension and text generation to assess the performance of models both in a high- and a low- resource language.
On the Role of Speech Data in Reducing Toxicity Detection Bias
Text toxicity detection systems exhibit significant biases, producing disproportionate rates of false positives on samples mentioning demographic groups.
On the Similarity of Circuits across Languages: a Case Study on the Subject-verb Agreement Task
Notably, this subject number signal is represented as a direction in the residual stream space, and is language-independent.
Unveiling the Role of Pretraining in Direct Speech Translation
Hence, we hypothesize that this issue stems from the difficulty of effectively training an encoder for direct speech translation.
Linguini: A benchmark for language-agnostic linguistic reasoning
We propose a new benchmark to measure a language model's linguistic reasoning skills without relying on pre-existing language-specific knowledge.
Towards Massive Multilingual Holistic Bias
In the current landscape of automatic language generation, there is a need to understand, evaluate, and mitigate demographic biases as existing models are becoming increasingly multilingual.
A Primer on the Inner Workings of Transformer-based Language Models
The rapid progress of research aimed at interpreting the inner workings of advanced language models has highlighted a need for contextualizing the insights gained from years of work in this area.
Pushing the Limits of Zero-shot End-to-End Speech Translation
The speech encoder seamlessly integrates with the MT model at inference, enabling direct translation from speech to text, across all languages supported by the MT model.
Towards Red Teaming in Multimodal and Multilingual Translation
Assessing performance in Natural Language Processing is becoming increasingly complex.
MuTox: Universal MUltilingual Audio-based TOXicity Dataset and Zero-shot Detector
Research in toxicity detection in natural language processing for the speech modality (audio-based) is quite limited, particularly for languages other than English.
Seamless: Multilingual Expressive and Streaming Speech Translation
In this work, we introduce a family of models that enable end-to-end expressive and multilingual translations in a streaming fashion.
automatic-speech-translation
Multimodal Machine Translation
+2
Added Toxicity Mitigation at Inference Time for Multimodal and Massively Multilingual Translation
MinTox uses a toxicity detection classifier which is multimodal (speech and text) and works in languages at scale.
SpeechAlign: a Framework for Speech Translation Alignment Evaluation
In doing so, we contribute to the ongoing research progress within the fields of Speech-to-Speech and Speech-to-Text translation.
Gender-specific Machine Translation with Large Language Models
While machine translation (MT) systems have seen significant improvements, it is still common for translations to reflect societal biases, such as gender bias.
The Gender-GAP Pipeline: A Gender-Aware Polyglot Pipeline for Gender Characterisation in 55 Languages
We showcase it to report gender representation in WMT training data and development data for the News task, confirming that current data is skewed towards masculine representation.
SeamlessM4T: Massively Multilingual & Multimodal Machine Translation
What does it take to create the Babel Fish, a tool that can help individuals translate speech between any two languages?
Ranked #1 on
Speech-to-Speech Translation
on CVSS
(using extra training data)
Automatic Speech Recognition
Speech-to-Speech Translation
+4
Speech Translation with Foundation Models and Optimal Transport: UPC at IWSLT23
Our Speech Translation systems utilize foundation models for speech (wav2vec 2. 0) and text (mBART50).
Multilingual Holistic Bias: Extending Descriptors and Patterns to Unveil Demographic Biases in Languages at Scale
Our initial findings show that translation quality for EN-to-XX translations is an average of 8 spBLEU better when evaluating with the masculine human reference compared to feminine.
Explaining How Transformers Use Context to Build Predictions
Language Generation Models produce words based on the previous context.
HalOmi: A Manually Annotated Benchmark for Multilingual Hallucination and Omission Detection in Machine Translation
Hallucinations in machine translation are translations that contain information completely unrelated to the input.
ReSeTOX: Re-learning attention weights for toxicity mitigation in machine translation
Our proposed method, ReSeTOX (REdo SEarch if TOXic), addresses the issue of Neural Machine Translation (NMT) generating translation outputs that contain toxic words not present in the input.
SegAugment: Maximizing the Utility of Speech Translation Data with Segmentation-based Augmentations
End-to-end Speech Translation is hindered by a lack of available data resources.
BLASER: A Text-Free Speech-to-Speech Translation Evaluation Metric
In this paper, we propose a text-free evaluation metric for end-to-end S2ST, named BLASER, to avoid the dependency on ASR systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Detecting and Mitigating Hallucinations in Machine Translation: Model Internal Workings Alone Do Well, Sentence Similarity Even Better
We propose to use a method that evaluates the percentage of the source contribution to a generated translation.
Efficient Speech Translation with Dynamic Latent Perceivers
Transformers have been the dominant architecture for Speech Translation in recent years, achieving significant improvements in translation quality.
Toxicity in Multilingual Machine Translation at Scale
We evaluate and analyze added toxicity when translating a large evaluation dataset (HOLISTICBIAS, over 472k sentences, covering 13 demographic axes) from English into 164 languages.
No Language Left Behind: Scaling Human-Centered Machine Translation
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.
Ranked #1 on
Machine Translation
on IWSLT2017 French-English
(SacreBLEU metric)
Towards Opening the Black Box of Neural Machine Translation: Source and Target Interpretations of the Transformer
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).
Multiformer: A Head-Configurable Transformer-Based Model for Direct Speech Translation
Different approaches have been proposed to overcome these problems, such as the use of efficient attention mechanisms.
On the Locality of Attention in Direct Speech Translation
Transformers have achieved state-of-the-art results across multiple NLP tasks.
Measuring the Mixing of Contextual Information in the Transformer
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.
A multi-task semi-supervised framework for Text2Graph & Graph2Text
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.
SHAS: Approaching optimal Segmentation for End-to-End Speech Translation
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.
Attention Weights in Transformer NMT Fail Aligning Words Between Sequences but Largely Explain Model Predictions
This work proposes an extensive analysis of the Transformer architecture in the Neural Machine Translation (NMT) setting.
Efficient Transformer for Direct Speech Translation
When working with speech, we must face a problem: the sequence length of an audio input is not suitable for the Transformer.
End-to-End Speech Translation with Pre-trained Models and Adapters: UPC at IWSLT 2021
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)
Impact of Gender Debiased Word Embeddings in Language Modeling
Gender, race and social biases have recently been detected as evident examples of unfairness in applications of Natural Language Processing.
How to Write a Bias Statement: Recommendations for Submissions to the Workshop on Gender Bias in NLP
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.
Sparsely Factored Neural Machine Translation
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.
Gender Bias in Multilingual Neural Machine Translation: The Architecture Matters
Multilingual Neural Machine Translation architectures mainly differ in the amount of sharing modules and parameters among languages.
Continual Lifelong Learning in Natural Language Processing: A Survey
However, it is difficult for existing deep learning architectures to learn a new task without largely forgetting previously acquired knowledge.
Findings of the 2020 Conference on Machine Translation (WMT20)
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.
Enabling Zero-shot Multilingual Spoken Language Translation with Language-Specific Encoders and Decoders
On the other hand, Multilingual Neural Machine Translation (MultiNMT) approaches rely on higher-quality and more massive data sets.
Evaluating Gender Bias in Speech Translation
WinoST is the speech version of WinoMT which is a MT challenge set and both follow an evaluation protocol to measure gender accuracy.
Training Multilingual Machine Translation by Alternately Freezing Language-Specific Encoders-Decoders
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.
MT-Adapted Datasheets for Datasets: Template and Repository
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).
Enhancing Word Embeddings with Knowledge Extracted from Lexical Resources
In this work, we present an effective method for semantic specialization of word vector representations.
Enriching the Transformer with Linguistic Factors for Low-Resource Machine Translation
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.
Multilingual Machine Translation: Closing the Gap between Shared and Language-specific Encoder-Decoders
State-of-the-art multilingual machine translation relies on a universal encoder-decoder, which requires retraining the entire system to add new languages.
Syntax-driven Iterative Expansion Language Models for Controllable Text Generation
The dominant language modeling paradigm handles text as a sequence of discrete tokens.
Refinement of Unsupervised Cross-Lingual Word Embeddings
In this paper, we propose a self-supervised method to refine the alignment of unsupervised bilingual word embeddings.
Bilingual Lexicon Induction
Cross-Lingual Word Embeddings
+1
Automatic Spanish Translation of the SQuAD Dataset for Multilingual Question Answering
We then used this dataset to train Spanish QA systems by fine-tuning a Multilingual-BERT model.
GeBioToolkit: Automatic Extraction of Gender-Balanced Multilingual Corpus of Wikipedia Biographies
We introduce GeBioToolkit, a tool for extracting multilingual parallel corpora at sentence level, with document and gender information from Wikipedia biographies.
The TALP-UPC System for the WMT Similar Language Task: Statistical vs Neural Machine Translation
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.
Multilingual, Multi-scale and Multi-layer Visualization of Intermediate Representations
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.
From Bilingual to Multilingual Neural Machine Translation by Incremental Training
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.
Joint Source-Target Self Attention with Locality Constraints
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
Towards Interlingua Neural Machine Translation
By adding and forcing this interlingual loss, we are able to train multiple encoders and decoders for each language, sharing a common intermediate representation.
Evaluating the Underlying Gender Bias in Contextualized Word Embeddings
Gender bias is highly impacting natural language processing applications.
Equalizing Gender Biases in Neural Machine Translation with Word Embeddings Techniques
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.
(Self-Attentive) Autoencoder-based Universal Language Representation for Machine Translation
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.
A Neural Approach to Language Variety Translation
In this paper we present the first neural-based machine translation system trained to translate between standard national varieties of the same language.
English-Catalan Neural Machine Translation in the Biomedical Domain through the cascade approach
This paper describes the methodology followed to build a neural machine translation system in the biomedical domain for the English-Catalan language pair.
Character-level Intra Attention Network for Natural Language Inference
Natural language inference (NLI) is a central problem in language understanding.
Morphology Generation for Statistical Machine Translation using Deep Learning Techniques
In this paper, we propose to de-couple machine translation from morphology generation in order to better deal with the problem.
Character-based Neural Machine Translation
Neural Machine Translation (MT) has reached state-of-the-art results.
Evaluating Indirect Strategies for Chinese-Spanish Statistical Machine Translation
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.
