Related papers: Average Token Delay: A Latency Metric for Simultan…
Although proper handling of discourse significantly contributes to the quality of machine translation (MT), these improvements are not adequately measured in common translation quality metrics. Recent works in context-aware MT attempt to…
Token repetition is a typical form of multi-modal problem in fully non-autoregressive translation (NAT). In this work, we revisit the multi-modal problem in recently proposed NAT models. Our study reveals that these advanced models have…
Adjusting the latency, power, and accuracy of natural language understanding models is a desirable objective of an efficient architecture. This paper proposes an efficient Transformer architecture that adjusts the inference computational…
Literary translation is a culturally significant task, but it is bottlenecked by the small number of qualified literary translators relative to the many untranslated works published around the world. Machine translation (MT) holds potential…
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…
Large language models (LLMs) have achieved remarkable performance across a wide range of tasks, but their increasing parameter sizes significantly slow down inference. Speculative decoding mitigates this issue by leveraging a smaller draft…
We argue that translation quality alone is not a sufficient metric for measuring knowledge transfer in multilingual neural machine translation. To support this claim, we introduce Representational Transfer Potential (RTP), which measures…
To alleviate the data scarcity problem in End-to-end speech translation (ST), pre-training on data for speech recognition and machine translation is considered as an important technique. However, the modality gap between speech and text…
Lexical semantic change detection (LSCD) increasingly relies on contextualised language model embeddings, yet most approaches still quantify change using a small set of semantic change metrics, primarily Average Pairwise Distance (APD) and…
Recent work in speech-to-speech translation (S2ST) has focused primarily on offline settings, where the full input utterance is available before any output is given. This, however, is not reasonable in many real-world scenarios. In…
With the increased applications of automatic speech recognition (ASR) in recent years, it is essential to automatically insert punctuation marks and remove disfluencies in transcripts, to improve the readability of the transcripts as well…
The construction of high-quality parallel corpora for translation research has increasingly evolved from simple sentence alignment to complex, multi-layered annotation tasks. This methodological shift presents significant challenges for…
Latency is inherent in almost all real-world networked applications. In this paper, we propose a distributed allocation strategy over multi-agent networks with delayed communications. The state of each agent (or node) represents its share…
Automatic metrics for evaluating translation quality are typically validated by measuring how well they correlate with human assessments. However, correlation methods tend to capture only the ability of metrics to differentiate between good…
We have reached a practical and realistic phase in human-support dialogue agents by developing a large language model (LLM). However, when requiring expert knowledge or anticipating the utterance content using the massive size of the…
Current direct speech-to-speech translation methods predominantly employ speech tokens as intermediate representations. However, a single speech token is not dense in semantics, so we generally need multiple tokens to express a complete…
To translate speech for automatic dubbing, machine translation needs to be isochronous, i.e. translated speech needs to be aligned with the source in terms of speech durations. We introduce target factors in a transformer model to predict…
Temporal-difference (TD) learning is highly effective at controlling and evaluating an agent's long-term outcomes. Most approaches in this paradigm implement a semi-gradient update to boost the learning speed, which consists of ignoring the…
Pretraining and multitask learning are widely used to improve the speech to text translation performance. In this study, we are interested in training a speech to text translation model along with an auxiliary text to text translation task.…
A problem with many current Large Language Model (LLM) driven spoken dialogues is the response time. Some efforts such as Groq address this issue by lightning fast processing of the LLM, but we know from the cognitive psychology literature…