Display omitted
Decoding is an important part of machine translation systems, and the most popular inference algorithm used here is beam search. Beam search algorithm improves translation by allowing ...a larger search space to be traversed than greedy search. However, as the beam width increases, the translation performance declines after a certain point in neural machine translation (NMT). This problem is usually not observed in statistical machine translation (SMT) due to the decoding method. This paper proposes a hybrid system-based method that uses SMT predictions to prevent quality deterioration in the beam search algorithm used in NMT decoding. Our approach is based on the reranking n-best list of NMT according to the SMT system translation sentence. We propose two different algorithms for reranking NMT n-best lists. The first algorithm uses the length information of the SMT outputs. In contrast, the second uses a word-based similarity approach with the Jaccard Index, the Dice’s Coefficient, and the Overlap Coefficient. Experiments on three different language pairs show that the method we propose prevents the decrease in translation quality and produces a gain of 1.3 BLEU and 1.6 METEOR for different beam sizes and 1.8 BLEU and 2.1 METEOR average scores compared to the baseline results.
This letter, presents the compendium of eight unsupervised Machine Translation (MT) systems built from monolingual corpus of five Indian languages from the Indo-Aryan and Dravidian language families. ...Recent research has demonstrated outstanding results in completely unsupervised training of Phrase-based Statistical MT (PBSMT) systems using innovative and designs that rely solely on monolingual datasets. However, prior research has shown that Unsupervised Statistical MT (USMT) outperforms Unsupervised Neural MT (UNMT), particularly for language pairings that are not closely related. The purpose of this work is to investigate the architecture of the USMT system utilizing only monolingual dataset using four different Indian morphologically rich languages and one low-resource endangered Kangri language. The experimental results analysis are evaluated using different natural language toolkit tokenizers and analyzed for different language pair using various fully automatic MT evaluation metrics for different iterations.
Bilingual termbanks are important for many natural language processing applications, especially in translation workflows in industrial settings. In this paper, we apply a log-likelihood comparison ...method to extract monolingual terminology from the source and target sides of a parallel corpus. The initial candidate terminology list is prepared by taking all arbitrary n-gram word sequences from the corpus. Then, a well-known statistical measure (the Dice coefficient) is employed in order to remove any multi-word terms with weak associations from the candidate term list. Thereafter, the log-likelihood comparison method is applied to rank the phrasal candidate term list. Then, using a phrase-based statistical machine translation model, we create a bilingual terminology with the extracted monolingual term lists. We integrate an external knowledge source—the Wikipedia cross link databases—into the terminology extraction (TE) model to assist two processes: (a) the ranking of the extracted terminology list, and (b) the selection of appropriate target terms for a source term. First, we report the performance of our monolingual TE model compared to a number of the state-of-the-art TE models on English-to-Turkish and English-to-Hindi data sets. Then, we evaluate our novel bilingual TE model on an English-to-Turkish data set, and report the automatic evaluation results. We also manually evaluate our novel TE model on English-to-Spanish and English-to-Hindi data sets, and observe excellent performance for all domains.
In the domain of machine translation (MT) processing, end-to-end neural machine translation (NMT) has emerged as a remarkable breakthrough, surpassing the conventional statistical MT approaches. ...Inspired by the Internet of Things (IoT) technology, some researchers are exploring how to integrate device-to-device communication patterns into NMT to enhance translation efficiency. However, the current state-of-the-art NMT models predominantly adopt sequence-based representations for both the source language and target language sentences. The lack of natural language sentence structure attributes leads to problems such as unfaithful translation in NMT. To enhance lexical alignment in NMT, the paper proposes a new transformer MT model that incorporates vocabulary alignment structure. The model receives external lexical alignment information during each step of the decoding process in the decoder design to alleviate the problem of missing lexical alignment structures. During the decoding phase of the model, the statistical MT system plays a crucial role by supplying relevant lexical alignment information derived from the decoding information obtained from the NMT. Additionally, the model suggests vocabulary recommendations based on this lexical alignment information. The experimental results provide evidence that this approach successfully integrates the vocabulary knowledge derived from statistical MT, leading to improved translation performance.
To eliminate ambiguities in the existing methods to simplify Chinese pronunciation learning, we propose a model that can predict the pronunciation of Chinese characters automatically. The proposed ...model relies on a statistical machine translation (SMT) framework. In particular, we consider the components of Chinese characters as the basic unit and consider the pronunciation prediction as a machine translation procedure (the component sequence as a source sentence, the pronunciation, pinyin, as a target sentence). In addition to traditional features such as the bidirectional word translation and the n-gram language model, we also implement a component similarity feature to overcome some typos during practical use. We incorporate these features into a log-linear model. The experimental results show that our approach significantly outperforms other baseline models.
Machine translation and its evaluation: a study Mondal, Subrota Kumar; Zhang, Haoxi; Kabir, H. M. Dipu ...
The Artificial intelligence review,
09/2023, Letnik:
56, Številka:
9
Journal Article
Recenzirano
Machine translation (namely MT) has been one of the most popular fields in computational linguistics and Artificial Intelligence (AI). As one of the most promising approaches, MT can potentially ...break the language barrier of people from all over the world. Despite a number of studies in MT, there are few studies in summarizing and comparing MT methods. To this end, in this paper, we principally focus on presenting the two mainstream MT schemes: statistical machine translation (SMT) and neural machine translation (NMT), including their basic rationales and developments. Meanwhile, the detailed translation models are also presented, such as the word-based model, syntax-based model, and phrase-based model in statistical machine translation. Similarly, approaches in NMT, such as the recurrent neural network-based, attention mechanism-based, and transformer-based models are presented. Last but not least, the evaluation approaches also play an important role in helping developers to improve their methods better in MT. The prevailing machine translation evaluation methodologies are also presented in this article.
Role of Morphology Injection in SMT S, Sreelekha; Bhattacharyya, Pushpak
ACM transactions on Asian and low-resource language information processing,
03/2018, Letnik:
17, Številka:
1
Journal Article
Recenzirano
Phrase-based Statistical Machine Translation (PBSMT) is commonly used for automatic translation. However, PBSMT runs into difficulty when either or both of the source and target languages are ...morphologically rich. Factored models are found to be useful for such cases, as they consider word as a vector of factors. These factors can contain any information about the surface word and use it while translating. The objective of the current work is to handle morphological inflections in Hindi, Marathi, and Malayalam using Factored translation models when translating from English. Statistical MT approaches face the problem of data sparsity when translating to a morphologically rich language. It is very unlikely for a parallel corpus to contain all morphological forms of words. We propose a solution to generate these unseen morphological forms and inject them into the original training corpus. We propose a simple and effective solution based on enriching the input with various morphological forms of words. We observe that morphology injection improves the quality of translation in terms of both adequacy and fluency. We verify this with experiments on three morphologically rich languages when translating from English. From the detailed evaluations, we observed an order of magnitude improvement in translation quality.
We address the problem of simplifying Portuguese texts at the sentence level by treating it as a “translation task”. We use the Statistical Machine Translation (SMT) framework to learn how to ...translate from complex to simplified sentences. Given a parallel corpus of original and simplified texts, aligned at the sentence level, we train a standard SMT system and evaluate the “translations” produced using both standard SMT metrics like BLEU and manual inspection. Results are promising according to both evaluations, showing that while the model is usually overcautious in producing simplifications, the overall quality of the sentences is not degraded and certain types of simplification operations, mainly lexical, are appropriately captured.