Related papers: Robustness of Multi-Source MT to Transcription Err…
Multilingual machine translation (MMT) benefits from cross-lingual transfer but is a challenging multitask optimization problem. This is partly because there is no clear framework to systematically learn language-specific parameters.…
In document-level neural machine translation (DocNMT), multi-encoder approaches are common in encoding context and source sentences. Recent studies \cite{li-etal-2020-multi-encoder} have shown that the context encoder generates noise and…
Although modern automatic speech recognition (ASR) systems can achieve high performance, they may produce errors that weaken readers' experience and do harm to downstream tasks. To improve the accuracy and reliability of ASR hypotheses, we…
Recent work on multilingual neural machine translation reported competitive performance with respect to bilingual models and surprisingly good performance even on (zeroshot) translation directions not observed at training time. We…
The quality of automatic speech recognition (ASR) is critical to Dialogue Systems as ASR errors propagate to and directly impact downstream tasks such as language understanding (LU). In this paper, we propose multi-task neural approaches to…
Encoder-decoder models have achieved remarkable success in speech and text tasks, yet efficiently adapting these models to diverse uni/multi-modal scenarios remains an open challenge. In this paper, we propose Whisper-UT, a unified and…
Learning multilingual and multi-domain translation model is challenging as the heterogeneous and imbalanced data make the model converge inconsistently over different corpora in real world. One common practice is to adjust the share of each…
Multilingual Language Models (MLLMs) exhibit robust cross-lingual transfer capabilities, or the ability to leverage information acquired in a source language and apply it to a target language. These capabilities find practical applications…
The paper describes the BUT's speech translation systems. The systems are English$\longrightarrow$German offline speech translation systems. The systems are based on our previous works \cite{Jointly_trained_transformers}. Though End-to-End…
Machine translation is a popular test bed for research in neural sequence-to-sequence models but despite much recent research, there is still a lack of understanding of these models. Practitioners report performance degradation with large…
While recent advances in deep learning led to significant improvements in machine translation, neural machine translation is often still not able to continuously adapt to the environment. For humans, as well as for machine translation,…
Machine translation (MT) of user-generated content (UGC) poses unique challenges, including handling slang, emotion, and literary devices like irony and sarcasm. Evaluating the quality of these translations is challenging as current metrics…
Lexically constrained machine translation allows the user to manipulate the output sentence by enforcing the presence or absence of certain words and phrases. Although current approaches can enforce terms to appear in the translation, they…
Machine translation is generally understood as generating one target text from an input source document. In this paper, we consider a stronger requirement: to jointly generate two texts so that each output side effectively depends on the…
We propose a simple solution to use a single Neural Machine Translation (NMT) model to translate between multiple languages. Our solution requires no change in the model architecture from our base system but instead introduces an artificial…
Despite the reported success of unsupervised machine translation (MT), the field has yet to examine the conditions under which these methods succeed, and where they fail. We conduct an extensive empirical evaluation of unsupervised MT using…
Recent research using pre-trained transformer models suggests that just 10 minutes of transcribed speech may be enough to fine-tune such a model for automatic speech recognition (ASR) -- at least if we can also leverage vast amounts of text…
Sequence-to-sequence neural translation models learn semantic and syntactic relations between sentence pairs by optimizing the likelihood of the target given the source, i.e., $p(y|x)$, an objective that ignores other potentially useful…
Neural Machine Translation (NMT) systems rely on large amounts of parallel data. This is a major challenge for low-resource languages. Building on recent work on unsupervised and semi-supervised methods, we present an approach that combines…
Across multiple language pairings (English $\to$ \{Spanish, French, German, Mandarin, Japanese, Urdu, Cantonese\}), we find reasoning errors in translation. To quantify how often these reasoning errors occur, we leverage an automated…