Related papers: Embedding-Enhanced Giza++: Improving Alignment in …

With the rapid development of large language models (LLMs) and ever-evolving practical requirements, finding an efficient and effective alignment method has never been more critical. However, the tension between the complexity of current…

Many words have evolved in meaning as a result of cultural and social change. Understanding such changes is crucial for modelling language and cultural evolution. Low-dimensional embedding methods have shown promise in detecting words'…

Preference optimization techniques have become a standard final stage for training state-of-art large language models (LLMs). However, despite widespread adoption, the vast majority of work to-date has focused on first-class citizen…

Recent studies on reasoning models explore the meta-awareness of language models, the ability to know how to think by itself. We argue that large reasoning models lack this meta-awareness property by proving severe misalignment between true…

Recent techniques in Question Answering (QA) have gained remarkable performance improvement with some QA models even surpassed human performance. However, the ability of these models in truly understanding the language still remains dubious…

Increased adaptability of RNN language models leads to improved predictions that benefit many applications. However, current methods do not take full advantage of the RNN structure. We show that the most widely-used approach to adaptation…

We introduce a new proxy score for evaluating bitext mining based on similarity in a multilingual embedding space: xSIM++. In comparison to xSIM, this improved proxy leverages rule-based approaches to extend English sentences in any…

Contextualized embeddings are the preferred tool for modeling Lexical Semantic Change (LSC). Current evaluations typically focus on a specific task known as Graded Change Detection (GCD). However, performance comparison across work are…

This work exploits translation data as a source of semantically relevant learning signal for models of word representation. In particular, we exploit equivalence through translation as a form of distributed context and jointly learn how to…

Large Language Models (LLMs) have achieved remarkable performance across a wide range of Natural Language Processing (NLP) tasks. However, in long-context scenarios, they face two challenges: high computational cost and information…

The organization of latent token representations plays a crucial role in determining the stability, generalization, and contextual consistency of language models, yet conventional approaches to embedding refinement often rely on parameter…

The ability of generative large language models (LLMs) to perform in-context learning has given rise to a large body of research into how best to prompt models for various natural language processing tasks. In this paper, we focus on…

Practical sequence classification tasks in natural language processing often suffer from low training data availability for target classes. Recent works towards mitigating this problem have focused on transfer learning using embeddings…

This paper presents KIT's submissions to the IWSLT 2025 low-resource track. We develop both cascaded systems, consisting of Automatic Speech Recognition (ASR) and Machine Translation (MT) models, and end-to-end (E2E) Speech Translation (ST)…

Distributed language representation has become the most widely used technique for language representation in various natural language processing tasks. Most of the natural language processing models that are based on deep learning…

Large Language Models (LLMs) hold significant promise for mathematics education, yet they often struggle with complex mathematical reasoning. While Retrieval-Augmented Generation (RAG) mitigates these issues by grounding LLMs in external…

In recent years, neural machine translation (NMT) has become the dominant approach in automated translation. However, like many other deep learning approaches, NMT suffers from overfitting when the amount of training data is limited. This…

Transformer models, which leverage architectural improvements like self-attention, perform remarkably well on Natural Language Processing (NLP) tasks. The self-attention mechanism is position agnostic. In order to capture positional…

Word embedding techniques heavily rely on the abundance of training data for individual words. Given the Zipfian distribution of words in natural language texts, a large number of words do not usually appear frequently or at all in the…

Cross-lingual or cross-domain correspondences play key roles in tasks ranging from machine translation to transfer learning. Recently, purely unsupervised methods operating on monolingual embeddings have become effective alignment tools.…