Related papers: Translation procedures in descriptive inner model …

While achieving state-of-the-art results in multiple tasks and languages, translation-based cross-lingual transfer is often overlooked in favour of massively multilingual pre-trained encoders. Arguably, this is due to its main limitations:…

Models of neural machine translation are often from a discriminative family of encoderdecoders that learn a conditional distribution of a target sentence given a source sentence. In this paper, we propose a variational model to learn this…

Outside of the left-c.e. reals, Solovay reducibility is considered to be behaved badly [10.1007/978-0-387-68441-3]. Proposals for variants of Solovay reducibility that are better suited for the investigation of arbitrary, not necessarily…

While large language models (LLMs) demonstrate remarkable success in multilingual translation, their internal core translation mechanisms, even at the fundamental word level, remain insufficiently understood. To address this critical gap,…

The Transformer model is widely used in various application areas of machine learning, such as natural language processing. This paper investigates the approximation of the H\"older continuous function class…

It is a classical result in matrix algebra that any square matrix over a field can be conjugated to its transpose by a symmetric matrix. For $F$ a non-Archimedean local field, Tupan used this to give an elementary proof that transpose…

Variational Neural Machine Translation (VNMT) is an attractive framework for modeling the generation of target translations, conditioned not only on the source sentence but also on some latent random variables. The latent variable modeling…

This manuscript explores multimodal alignment, translation, fusion, and transference to enhance machine understanding of complex inputs. We organize the work into five chapters, each addressing unique challenges in multimodal machine…

In this work, we investigate methods for the challenging task of translating between low-resource language pairs that exhibit some level of similarity. In particular, we consider the utility of transfer learning for translating between…

Theory of tree transducers provides a foundation for understanding expressiveness and complexity of analysis problems for specification languages for transforming hierarchically structured data such as XML documents. We introduce streaming…

Assessing performance in Natural Language Processing is becoming increasingly complex. One particular challenge is the potential for evaluation datasets to overlap with training data, either directly or indirectly, which can lead to skewed…

When trained on language data, do transformers learn some arbitrary computation that utilizes the full capacity of the architecture or do they learn a simpler, tree-like computation, hypothesized to underlie compositional meaning systems…

Deep motion forecasting models have achieved great success when trained on a massive amount of data. Yet, they often perform poorly when training data is limited. To address this challenge, we propose a transfer learning approach for…

This paper presents statistical language and translation models based on collections of small finite state machines we call ``head automata''. The models are intended to capture the lexical sensitivity of N-gram models and direct…

We introduce a category-theoreticabstraction of a syntax with auxiliary functions, called an admissiblemonad morphism. Relying on an abstract form of structural recursion,we then design generic tools to construct admissible monad…

Large language models (LLMs) have demonstrated promising potential in various downstream tasks, including machine translation. However, prior work on LLM-based machine translation has mainly focused on better utilizing training data,…

While it has become common to perform automated translations on natural language, performing translations between different representations of mathematical formulae has thus far not been possible. We implemented the first translator for…

End-to-end speech-to-text translation models are often initialized with pre-trained speech encoder and pre-trained text decoder. This leads to a significant training gap between pre-training and fine-tuning, largely due to the modality…

Reasoning-oriented large language models (RLMs) achieve strong gains on tasks such as mathematics and coding by generating explicit intermediate reasoning. However, their impact on machine translation (MT) remains underexplored. We…

This paper describes our submission to the First Workshop on Reordering for Statistical Machine Translation. We have decided to build a reordering system based on tree-to-string model, using only publicly available tools to accomplish this…