Related papers: Toward Machine Interpreting: Lessons from Human In…
Neural machine translation is a recently proposed approach to machine translation. Unlike the traditional statistical machine translation, the neural machine translation aims at building a single neural network that can be jointly tuned to…
Recent studies on interpreting the hidden states of speech models have shown their ability to capture speaker-specific features, including gender. Does this finding also hold for speech translation (ST) models? If so, what are the…
Machine translation (MT) is an important task in natural language processing (NLP) as it automates the translation process and reduces the reliance on human translators. With the resurgence of neural networks, the translation quality…
Sentiment classification has been crucial for many natural language processing (NLP) applications, such as the analysis of movie reviews, tweets, or customer feedback. A sufficiently large amount of data is required to build a robust…
Enabling a machine to read and comprehend the natural language documents so that it can answer some questions remains an elusive challenge. In recent years, the popularity of deep learning and the establishment of large-scale datasets have…
In this work, we systematically investigate how well current models of coherence can capture aspects of text implicated in discourse organisation. We devise two datasets of various linguistic alterations that undermine coherence and test…
Direct speech-to-text translation systems encounter an important drawback in data scarcity. A common solution consists on pretraining the encoder on automatic speech recognition, hence losing efficiency in the training process. In this…
As conversational agents become integral parts of many aspects of our lives, current approaches are reaching bottlenecks of performance that require increasing amounts of data or increasingly powerful models. It is also becoming clear that…
With information systems becoming larger scale, recommendation systems are a topic of growing interest in machine learning research and industry. Even though progress on improving model design has been rapid in research, we argue that many…
Improvements in text generation technologies such as machine translation have necessitated more costly and time-consuming human evaluation procedures to ensure an accurate signal. We investigate a simple way to reduce cost by reducing the…
The goal of building dialogue agents that can converse with humans naturally has been a long-standing dream of researchers since the early days of artificial intelligence. The well-known Turing Test proposed to judge the ultimate validity…
Machine-learned language models have transformed everyday life: they steer us when we study, drive, manage money. They have the potential to transform our civilization. But they hallucinate. Their realities are virtual. This note provides a…
Remarkable advancements in modern generative foundation models have enabled the development of sophisticated and highly capable autonomous agents that can observe their environment, invoke tools, and communicate with other agents to solve…
Machine-learning models have demonstrated great success in learning complex patterns that enable them to make predictions about unobserved data. In addition to using models for prediction, the ability to interpret what a model has learned…
Automatic metrics are fundamental for the development and evaluation of machine translation systems. Judging whether, and to what extent, automatic metrics concur with the gold standard of human evaluation is not a straightforward problem.…
We investigate the behavior of maps learned by machine translation methods. The maps translate words by projecting between word embedding spaces of different languages. We locally approximate these maps using linear maps, and find that they…
Neural Machine Translation (NMT) methodologies have burgeoned from using simple feed-forward architectures to the state of the art; viz. BERT model. The use cases of NMT models have been broadened from just language translations to…
We introduce a dataset comprising commercial machine translations, gathered weekly over six years across 12 translation directions. Since human A/B testing is commonly used, we assume commercial systems improve over time, which enables us…
Transfer learning is a vital technique that generalizes models trained for one setting or task to other settings or tasks. For example in speech recognition, an acoustic model trained for one language can be used to recognize speech in…
Unlike classical lexical overlap metrics such as BLEU, most current evaluation metrics for machine translation (for example, COMET or BERTScore) are based on black-box large language models. They often achieve strong correlations with human…