Related papers: Multiple References with Meaningful Variations Imp…

Annotation projection is an important area in NLP that can greatly contribute to creating language resources for low-resource languages. Word alignment plays a key role in this setting. However, most of the existing word alignment methods…

In an attempt to improve overall translation quality, there has been an increasing focus on integrating more linguistic elements into Machine Translation (MT). While significant progress has been achieved, especially recently with neural…

The remarkable understanding and generation capabilities of large language models (LLMs) have greatly improved translation performance. However, incorrect understanding of the sentence to be translated can degrade translation quality. To…

Document-level machine translation manages to outperform sentence level models by a small margin, but have failed to be widely adopted. We argue that previous research did not make a clear use of the global context, and propose a new…

Machine Translation (MT) between linguistically dissimilar languages is challenging, especially due to the scarcity of parallel corpora. Prior works suggest that pivoting through a high-resource language can help translation into a related…

Compared to sentence-level systems, document-level neural machine translation (NMT) models produce a more consistent output across a document and are able to better resolve ambiguities within the input. There are many works on…

Human languages are full of metaphorical expressions. Metaphors help people understand the world by connecting new concepts and domains to more familiar ones. Large pre-trained language models (PLMs) are therefore assumed to encode…

The quality of a Neural Machine Translation system depends substantially on the availability of sizable parallel corpora. For low-resource language pairs this is not the case, resulting in poor translation quality. Inspired by work in…

In-context learning (ICL) allows large language models (LLMs) to adapt to new tasks from a few examples, making it promising for languages underrepresented in pre-training. Recent work on many-shot ICL suggests that modern LLMs can further…

Multilingual large language models (LLMs) often demonstrate a performance gap between English and non-English languages, particularly in low-resource settings. Aligning these models to low-resource languages is essential yet challenging due…

Recent progress in semantic parsing scarcely considers languages other than English but professional translation can be prohibitively expensive. We adapt a semantic parser trained on a single language, such as English, to new languages and…

As research on machine translation moves to translating text beyond the sentence level, it remains unclear how effective automatic evaluation metrics are at scoring longer translations. In this work, we first propose a method for creating…

Large Language Models (LLMs) such as GPT-3 have emerged as general-purpose language models capable of addressing many natural language generation or understanding tasks. On the task of Machine Translation (MT), multiple works have…

Simultaneous machine translation (SiMT) aims to translate a continuous input text stream into another language with the lowest latency and highest quality possible. The translation thus has to start with an incomplete source text, which is…

We propose a novel data synthesis method to generate diverse error-corrected sentence pairs for improving grammatical error correction, which is based on a pair of machine translation models of different qualities (i.e., poor and good). The…

Machine translation (MT) has benefited from using synthetic training data originating from translating monolingual corpora, a technique known as backtranslation. Combining backtranslated data from different sources has led to better results…

The lack of parallel data for many language pairs is an important challenge to statistical machine translation (SMT). One common solution is to pivot through a third language for which there exist parallel corpora with the source and target…

While sentence simplification is an active research topic in NLP, its adjacent tasks of sentence complexification and same-level paraphrasing are not. To train models on all three tasks, we present two new unsupervised datasets. We compare…

Alignment with human preferences is an important step in developing accurate and safe large language models. This is no exception in machine translation (MT), where better handling of language nuances and context-specific variations leads…

Large language models (LLMs) are often equipped with multi-sample decoding strategies. An LLM implicitly defines an arithmetic code book, facilitating efficient and embarrassingly parallelizable \textbf{arithmetic sampling} to produce…