Related papers: Trans-Zero: Self-Play Incentivizes Large Language …

Multilingual machine translation (MMT), trained on a mixture of parallel and monolingual data, is key for improving translation in low-resource language pairs. However, the literature offers conflicting results on the performance of…

This paper proposes a technique for adding a new source or target language to an existing multilingual NMT model without re-training it on the initial set of languages. It consists in replacing the shared vocabulary with a small…

Finding an agreement among diverse opinions is a challenging topic in multiagent systems. Recently, large language models (LLMs) have shown great potential in addressing this challenge due to their remarkable capabilities in comprehending…

Back-translation is a critical component of Unsupervised Neural Machine Translation (UNMT), which generates pseudo parallel data from target monolingual data. A UNMT model is trained on the pseudo parallel data with translated source, and…

Preservation of domain knowledge from the source to target is crucial in any translation workflow. It is common in the translation industry to receive highly specialized projects, where there is hardly any parallel in-domain data. In such…

Advances in automated essay scoring (AES) have traditionally relied on labeled essays, requiring tremendous cost and expertise for their acquisition. Recently, large language models (LLMs) have achieved great success in various tasks, but…

In the current machine translation (MT) landscape, the Transformer architecture stands out as the gold standard, especially for high-resource language pairs. This research delves into its efficacy for low-resource language pairs including…

This paper illustrates our approach to the shared task on large-scale multilingual machine translation in the sixth conference on machine translation (WMT-21). This work aims to build a single multilingual translation system with a…

Inference-time scaling strategies, particularly Monte Carlo Tree Search (MCTS), have significantly enhanced the reasoning capabilities of Large Language Models (LLMs). However, current approaches remain predominantly stateless, discarding…

Multilingual Large Language Models (LLMs) can process many languages, yet how they internally represent this diversity remains unclear. Do they form shared multilingual representations with language-specific decoding, and if so, why does…

Monte Carlo Tree Search (MCTS), most famously used in game-play artificial intelligence (e.g., the game of Go), is a well-known strategy for constructing approximate solutions to sequential decision problems. Its primary innovation is the…

Beam search is the go-to method for decoding auto-regressive machine translation models. While it yields consistent improvements in terms of BLEU, it is only concerned with finding outputs with high model likelihood, and is thus agnostic to…

Large Language Models (LLMs) have remarkable capabilities across NLP tasks. However, their performance in multilingual contexts, especially within the mental health domain, has not been thoroughly explored. In this paper, we evaluate…

Decoder-only large language models (LLMs) have recently demonstrated impressive capabilities in text generation and reasoning. Nonetheless, they have limited applications in simultaneous machine translation (SiMT), currently dominated by…

Neural Machine Translation (NMT) has obtained state-of-the art performance for several language pairs, while only using parallel data for training. Target-side monolingual data plays an important role in boosting fluency for phrase-based…

While large language models (LLMs) have been pre-trained on multilingual corpora, their performance still lags behind in most languages compared to a few resource-rich languages. One common approach to mitigate this issue is to translate…

Large Language Models (LLMs) are rapidly reshaping machine translation (MT), particularly by introducing instruction-following, in-context learning, and preference-based alignment into what has traditionally been a supervised…

LLMs have been shown to perform well in machine translation (MT) with the use of in-context learning (ICL), rivaling supervised models when translating into high-resource languages (HRLs). However, they lag behind when translating into…

Zero-shot cross-lingual transfer is when a multilingual model is trained to perform a task in one language and then is applied to another language. Although the zero-shot cross-lingual transfer approach has achieved success in various…

Large language models (LLMs) face significant challenges when balancing multiple high-level objectives, such as generating coherent, relevant, and high-quality responses while maintaining efficient task adaptation across diverse tasks. To…