Related papers: Modeling Target-Side Inflection in Neural Machine …

In biomedical literature, it is common for entity boundaries to not align with word boundaries. Therefore, effective identification of entity spans requires approaches capable of considering tokens that are smaller than words. We introduce…

One of possible ways of obtaining continuous-space sentence representations is by training neural machine translation (NMT) systems. The recent attention mechanism however removes the single point in the neural network from which the source…

We propose a new model for learning bilingual word representations from non-parallel document-aligned data. Following the recent advances in word representation learning, our model learns dense real-valued word vectors, that is, bilingual…

Multi-source translation systems translate from multiple languages to a single target language. By using information from these multiple sources, these systems achieve large gains in accuracy. To train these systems, it is necessary to have…

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…

Machine Translation is one of the major oldest and the most active research area in Natural Language Processing. Currently, Statistical Machine Translation (SMT) dominates the Machine Translation research. Statistical Machine Translation is…

Tying the weights of the target word embeddings with the target word classifiers of neural machine translation models leads to faster training and often to better translation quality. Given the success of this parameter sharing, we…

We present MLQE-PE, a new dataset for Machine Translation (MT) Quality Estimation (QE) and Automatic Post-Editing (APE). The dataset contains eleven language pairs, with human labels for up to 10,000 translations per language pair in the…

Tokenization underlies every large language model, yet it remains an under-theorized and inconsistently designed component. Common subword approaches such as Byte Pair Encoding (BPE) offer scalability but often misalign with linguistic…

Regularization of neural machine translation is still a significant problem, especially in low-resource settings. To mollify this problem, we propose regressing word embeddings (ReWE) as a new regularization technique in a system that is…

Lemmatization of standard languages is concerned with (i) abstracting over morphological differences and (ii) resolving token-lemma ambiguities of inflected words in order to map them to a dictionary headword. In the present paper we aim to…

Multilingual automatic speech recognition (ASR) requires tokenization that efficiently covers many writing systems. Byte-level BPE (BBPE) using UTF-8 is widely adopted for its language-agnostic design and full Unicode coverage, but its…

Recent studies have revealed a number of pathologies of neural machine translation (NMT) systems. Hypotheses explaining these mostly suggest there is something fundamentally wrong with NMT as a model or its training algorithm, maximum…

Recently, numbers of works shows that the performance of neural machine translation (NMT) can be improved to a certain extent with using visual information. However, most of these conclusions are drawn from the analysis of experimental…

This paper introduces Dynamic Programming Encoding (DPE), a new segmentation algorithm for tokenizing sentences into subword units. We view the subword segmentation of output sentences as a latent variable that should be marginalized out…

A sentence can be translated into more than one correct sentences. However, most of the existing neural machine translation models only use one of the correct translations as the targets, and the other correct sentences are punished as the…

Classical translation models constrain the space of possible outputs by selecting a subset of translation rules based on the input sentence. Recent work on improving the efficiency of neural translation models adopted a similar strategy by…

Multilingual neural machine translation with a single model has drawn much attention due to its capability to deal with multiple languages. However, the current multilingual translation paradigm often makes the model tend to preserve the…

The choice of token vocabulary affects the performance of machine translation. This paper aims to figure out what is a good vocabulary and whether one can find the optimal vocabulary without trial training. To answer these questions, we…

This paper discusses the methods that we used for our submissions to the WMT 2023 Terminology Shared Task for German-to-English (DE-EN), English-to-Czech (EN-CS), and Chinese-to-English (ZH-EN) language pairs. The task aims to advance…