Related papers: Fast Lexically Constrained Decoding with Dynamic B…
This paper is devoted to the prediction of solutions to a stochastic discrete optimization problem. Through an application, we illustrate how we can use a state-of-the-art neural machine translation (NMT) algorithm to predict the solutions…
In the encoder-decoder architecture for neural machine translation (NMT), the hidden states of the recurrent structures in the encoder and decoder carry the crucial information about the sentence.These vectors are generated by parameters…
Neural machine translation is a recently proposed approach to machine translation. Unlike the traditional statistical machine translation, the neural machine translation aims at building a single neural network that can be jointly tuned to…
In this paper, we propose a simple, fast decoding algorithm that fosters diversity in neural generation. The algorithm modifies the standard beam search algorithm by adding an inter-sibling ranking penalty, favoring choosing hypotheses from…
Machine translation systems are expected to cope with various types of constraints in many practical scenarios. While neural machine translation (NMT) has achieved strong performance in unconstrained cases, it is non-trivial to impose…
We present a novel scheme to combine neural machine translation (NMT) with traditional statistical machine translation (SMT). Our approach borrows ideas from linearised lattice minimum Bayes-risk decoding for SMT. The NMT score is combined…
Neural machine translation (NMT) models are typically trained with fixed-size input and output vocabularies, which creates an important bottleneck on their accuracy and generalization capability. As a solution, various studies proposed…
Despite advances in neural machine translation (NMT) quality, rare words continue to be problematic. For humans, the solution to the rare-word problem has long been dictionaries, but dictionaries cannot be straightforwardly incorporated…
Recently, the development of neural machine translation (NMT) has significantly improved the translation quality of automatic machine translation. While most sentences are more accurate and fluent than translations by statistical machine…
The evolution of Neural Machine Translation (NMT) has been significantly influenced by six core challenges (Koehn and Knowles, 2017), which have acted as benchmarks for progress in this field. This study revisits these challenges, offering…
We address the problem of simultaneous translation by modifying the Neural MT decoder to operate with dynamically built encoder and attention. We propose a tunable agent which decides the best segmentation strategy for a user-defined BLEU…
Lexically-constrained NMT (LNMT) aims to incorporate user-provided terminology into translations. Despite its practical advantages, existing work has not evaluated LNMT models under challenging real-world conditions. In this paper, we focus…
For machine translation to tackle discourse phenomena, models must have access to extra-sentential linguistic context. There has been recent interest in modelling context in neural machine translation (NMT), but models have been principally…
Controlling Large Language Models (LLMs) to prevent the generation of undesirable content, such as profanity and personally identifiable information (PII), has become increasingly critical. While earlier approaches relied on post-processing…
Lexically constrained text generation aims to control the generated text by incorporating some pre-specified keywords into the output. Previous work injects lexical constraints into the output by controlling the decoding process or refining…
It has been previously noted that neural machine translation (NMT) is very sensitive to domain shift. In this paper, we argue that this is a dual effect of the highly lexicalized nature of NMT, resulting in failure for sentences with large…
Neural machine translation (NMT) models typically operate with a fixed vocabulary, but translation is an open-vocabulary problem. Previous work addresses the translation of out-of-vocabulary words by backing off to a dictionary. In this…
Current approaches to incorporating terminology constraints in machine translation (MT) typically assume that the constraint terms are provided in their correct morphological forms. This limits their application to real-world scenarios…
A neural machine translation (NMT) system is expensive to train, especially with high-resource settings. As the NMT architectures become deeper and wider, this issue gets worse and worse. In this paper, we aim to improve the efficiency of…
Despite some empirical success at correcting exposure bias in machine translation, scheduled sampling algorithms suffer from a major drawback: they incorrectly assume that words in the reference translations and in sampled sequences are…