Phrase Table Research Articles

Human-Computer Interaction Environment Monitoring and Collaborative Translation Mode Exploration Using Artificial Intelligence Technology.

Artificial intelligence now plays a significant role in both daily life and scientific research because of the rapid advancement of this technology in recent years. Making full use of the phrases in the translation phrase table for translation is challenging since the phrase matching is too accurate when the translation machine decodes. Fully automatic machine translation struggles to meet the expectations of its users since there are more or less translation faults brought on by data bottlenecks. Therefore, we require collaborative assisted translation technology for human-computer interaction. This work strengthens the research on collaborative translation techniques and ways for monitoring the human-computer interaction environment in order to further improve translation quality. This essay investigates and discusses human-computer translation techniques as well as related ideas in collaborative translation and human-computer interaction. The translation similarity model is incorporated into the translation system model together with an overall qualitative knowledge and logical reasoning capability of human-computer interaction to offer fresh strategies and methods for collaborative translation between humans and computers. According to the experimental findings, the accuracy rate of the collaborative translation system for human-computer interaction based on artificial intelligence technology can achieve 98.2% and 95.6%. The quality of the translation is enhanced after human-computer interaction, and the editing gap between the incorrect and auxiliary translations is narrowed, demonstrating the efficiency of the system and demonstrating its viability. In order to enhance the accuracy of system translation and the effectiveness of system operation, it is important to investigate the collaborative translation mode of human-computer interaction based on artificial intelligence technology.

Source-side Reordering to Improve Machine Translation between Languages with Distinct Word Orders

English and Hindi have significantly different word orders. English follows the subject-verb-object (SVO) order, while Hindi primarily follows the subject-object-verb (SOV) order. This difference poses challenges to modeling this pair of languages for translation. In phrase-based translation systems, word reordering is governed by the language model, the phrase table, and reordering models. Reordering in such systems is generally achieved during decoding by transposing words within a defined window. These systems can handle local reorderings, and while some phrase-level reorderings are carried out during the formation of phrases, they are weak in learning long-distance reorderings. To overcome this weakness, researchers have used reordering as a step in pre-processing to render the reordered source sentence closer to the target language in terms of word order. Such approaches focus on using parts-of-speech (POS) tag sequences and reordering the syntax tree by using grammatical rules, or through head finalization. This study shows that mere head finalization is not sufficient for the reordering of sentences in the English-Hindi language pair. It describes various grammatical constructs and presents a comparative evaluation of reorderings with the original and the head-finalized representations. The impact of the reordering on the quality of translation is measured through the BLEU score in phrase-based statistical systems and neural machine translation systems. A significant gain in BLEU score was noted for reorderings in different grammatical constructs.

Experience of neural machine translation between Indian languages

In this paper we explore neural machine translation (NMT) for Indian languages. Reported work on Indian language Statistical Machine Translation (SMT) demonstrated good performance within the Indo-Aryan family, but relatively poor performance within the Dravidian family as well as between the two families. Interestingly, by common observation NMT generates more fluent output than SMT. This led us to investigate NMT’s potential for translation involving Indian languages. The current practice in NMT is to train the models with subword units. Among subwording methods, byte pair encoding (BPE) is a popular choice. We conduct extensive experiments with BPE-based NMT models for Indian languages. An interesting outcome of our study is the finding that the optimal value for BPE merge for Indian language pairs seems to be falling in the range of 0–5000 which is fairly low compared to that observed for European Languages. Additionally, we apply other techniques such as phrase table injection and linguistic feature based enhancements on corpora, plus BERT augmented NMT to boost performance. To the best of our knowledge, this is the first comprehensive study on Indian language NMT (ILNMT) covering major languages in India. As an empirical paper, we expect this work could serve as a benchmark for ILNMT research.

Unsupervised Statistical Text Simplification

Most recent approaches for Text Simplification (TS) have drawn on insights from machine translation to learn simplification rewrites from the monolingual parallel corpus of complex and simple sentences, yet their effectiveness strongly relies on large amounts of parallel sentences. However, there has been a serious problem haunting TS for decades, that is, the availability of parallel TS corpora is scarce or not fit for the learning task. In this paper, we will focus on one especially useful and challenging problem of unsupervised TS without a single parallel sentence. To the best of our knowledge, we present the first unsupervised text simplification system based on phrase-based machine translation system, which leverages a careful initialization of phrase tables and language models. On the widely used WikiLarge and WikiSmall benchmarks, our system respectively obtains 39.08 and 25.12 SARI points, even outperforms some supervised baselines.

Phrase Table Combination Based on Symmetrization of Word Alignment for Low-Resource Languages

Phrase table combination in pivot approaches can be an effective method to deal with low-resource language pairs. The common practice to generate phrase tables in pivot approaches is to use standard symmetrization, i.e., grow-diag-final-and. Although some researchers found that the use of non-standard symmetrization could improve bilingual evaluation understudy (BLEU) scores, the use of non-standard symmetrization has not been commonly employed in pivot approaches. In this study, we propose a strategy that uses the non-standard symmetrization of word alignment in phrase table combination. The appropriate symmetrization is selected based on the highest BLEU scores in each direct translation of source–target, source–pivot, and pivot–target of Kazakh–English (Kk–En) and Japanese–Indonesian (Ja–Id). Our experiments show that our proposed strategy outperforms the direct translation in Kk–En with absolute improvements of 0.35 (a 11.3% relative improvement) and 0.22 (a 6.4% relative improvement) BLEU points for 3-gram and 5-gram, respectively. The proposed strategy shows an absolute gain of up to 0.11 (a 0.9% relative improvement) BLEU points compared to direct translation for 3-gram in Ja–Id. Our proposed strategy using a small phrase table obtains better BLEU scores than a strategy using a large phrase table. The size of the target monolingual and feature function weight of the language model (LM) could reduce perplexity scores.

Lexical Simplification by Unsupervised Machine Translation

In recent years, simple Japanese has been attracting attention as information transmission for foreigners. Automatic text simplification aims to reduce the complexity of vocabulary and expressions in a sentence while retaining its original meaning. This paper aims at compressing vocabulary, focusing on lexical simplification. Since the construction or expansion of a simplification corpus is very costly, we construct a simplification model by unsupervised learning that does not require a parallel corpus for simplification. We construct a simplification model that does not require a parallel corpus using Unsupervised Statistical Machine Translation. Based on a predetermined vocabulary, a pseudo-corpus for simplification is constructed from a web corpus and we learn the simplification model by the pseudo-corpus. We only need a vocabulary and a plain text corpus to train the simplification model. Moreover, we propose to clean the phrase table by WordNet, which improves the performance in BLEU and SARI metrics. By suppressing distant paraphrasing with WordNet, it became easier to select the correct paraphrase candidate.

Neural Semantic Parsing in Low-Resource Settings with Back-Translation and Meta-Learning

Neural semantic parsing has achieved impressive results in recent years, yet its success relies on the availability of large amounts of supervised data. Our goal is to learn a neural semantic parser when only prior knowledge about a limited number of simple rules is available, without access to either annotated programs or execution results. Our approach is initialized by rules, and improved in a back-translation paradigm using generated question-program pairs from the semantic parser and the question generator. A phrase table with frequent mapping patterns is automatically derived, also updated as training progresses, to measure the quality of generated instances. We train the model with model-agnostic meta-learning to guarantee the accuracy and stability on examples covered by rules, and meanwhile acquire the versatility to generalize well on examples uncovered by rules. Results on three benchmark datasets with different domains and programs show that our approach incrementally improves the accuracy. On WikiSQL, our best model is comparable to the state-of-the-art system learned from denotations.

Phrase table re-adjustment for statistical machine translation

Neither assigning similar priority to all phrases nor pruning out the incorrect phrases from the phrase table can improve the accuracy of machine translation. In this paper, we present a novel method for weight re-adjustment of phrase table in a statistical machine translation system. It learns the correct and incorrect phrases from bilingual corpora. Based on the syntactic phrase-level information, phrase table is updated with the weights estimated using probability distribution. Evaluation on English–Hindi technical domain corpora shows that our proposed method is more effective in producing better output in terms of BLEU, RIBES and NIST metrics. We shows that the proposed methods works well for other language pairs like Hindi–Konkani and Bengali–Hindi. Finally, we realised that this minor probabilistic change can improve the accuracy of the machine translation system a lot.

Использование текстовых признаков для улучшения качества статистического машинного перевода

In this paper we investigate the technique of extending the Moses Statistical Machine Translation (SMT) system default set of features using shallow linguistic information from source and target phrases. Although a typical SMT system uses a phrase table with 5 default features, most systems are scalable and support any number of additional features. We assume that linguistic information extracted from the source and target phrases can improve the overall translation quality, i. e. make the system more robust and reduce the number of instances of incorrect word choice, punctuation mistakes and other problems SMT systems are prone to. First, we build a baseline SMT system. Then we extract shallow linguistic features directly from source and target phrases of the baseline system’s phrase table. The features are precomputed and stored in the phrase table, so they can be regarded as stateless dense features. We develop and examine 19 features incorporating information from source and target phrases. We explore features commonly used in monolingual and parallel data filtering techniques. The features we investigate include source and target phrase lengths, word, number and punctuation symbol count, word frequencies according to large monolingual corpora etc. For each feature, we build and evaluate a separate SMT system. We conduct a series of experiments on the English-Russian language pair and obtain statistically significant improvements of up to 0.4 BLEU compared to baseline configuration.

Unsupervised Neural Machine Translation with SMT as Posterior Regularization

Without real bilingual corpus available, unsupervised Neural Machine Translation (NMT) typically requires pseudo parallel data generated with the back-translation method for the model training. However, due to weak supervision, the pseudo data inevitably contain noises and errors that will be accumulated and reinforced in the subsequent training process, leading to bad translation performance. To address this issue, we introduce phrase based Statistic Machine Translation (SMT) models which are robust to noisy data, as posterior regularizations to guide the training of unsupervised NMT models in the iterative back-translation process. Our method starts from SMT models built with pre-trained language models and word-level translation tables inferred from cross-lingual embeddings. Then SMT and NMT models are optimized jointly and boost each other incrementally in a unified EM framework. In this way, (1) the negative effect caused by errors in the iterative back-translation process can be alleviated timely by SMT filtering noises from its phrase tables; meanwhile, (2) NMT can compensate for the deficiency of fluency inherent in SMT. Experiments conducted on en-fr and en-de translation tasks show that our method outperforms the strong baseline and achieves new state-of-the-art unsupervised machine translation performance.

Non-Autoregressive Neural Machine Translation with Enhanced Decoder Input

Non-autoregressive translation (NAT) models, which remove the dependence on previous target tokens from the inputs of the decoder, achieve significantly inference speedup but at the cost of inferior accuracy compared to autoregressive translation (AT) models. Previous work shows that the quality of the inputs of the decoder is important and largely impacts the model accuracy. In this paper, we propose two methods to enhance the decoder inputs so as to improve NAT models. The first one directly leverages a phrase table generated by conventional SMT approaches to translate source tokens to target tokens, which are then fed into the decoder as inputs. The second one transforms source-side word embeddings to target-side word embeddings through sentence-level alignment and word-level adversary learning, and then feeds the transformed word embeddings into the decoder as inputs. Experimental results show our method largely outperforms the NAT baseline (Gu et al. 2017) by 5.11 BLEU scores on WMT14 English-German task and 4.72 BLEU scores on WMT16 English-Romanian task.

A unified framework and models for integrating translation memory into phrase-based statistical machine translation

Since statistical machine translation (SMT) and translation memory (TM) complement each other in TM matched and unmatched regions, a unified framework for integrating TM into phrase-based SMT is proposed in this paper. Unlike previous two-stage pipeline approaches, which directly merge TM results into the input sentences and subsequently let the SMT only translates those unmatched regions, the proposed framework refers to the corresponding TM information associated with each phrase at the SMT decoding. Under this unified framework, several integrated models are proposed to incorporate different types of information extracted from TM to guide the SMT decoding. We thus let SMT implicitly and indirectly utilize global context with a local dependency model. Furthermore, the SMT phrase table is dynamically enhanced with TM phrase pairs when the TM database and the SMT training set are different.On a Chinese–English TM database, our experiments show that the proposed Model-I significantly improves over both SMT and TM when the SMT training set is also adopted as the TM database and when the fuzzy match score is over 0.4 (overall 3.5 BLEU points improvement and 2.6 TER points reduction). In addition, the proposed Model-II is significantly better than the TM and the SMT systems when the SMT training set and the TM database are different. Furthermore, the proposed Model-III outperforms both the TM and the SMT systems even when the SMT training set and the TM database are from different domains. Additionally, the proposed Model-IV further achieves significant improvements with the help of Top-N TM sentence pairs. Lastly, all our models significantly outperform those state-of-the-art approaches under all test conditions.

Efficient Phrase Table pruning for Hindi to English machine translation through syntactic and marker-based filtering and hybrid similarity measurement

AbstractFor a given training corpus of parallel sentences, the quality of the output produced by a translation system relies heavily on the underlying similarity measurement criteria. A phrase-based machine translation system derives its output through a generative process using a Phrase Table comprising source and target language phrases. As a consequence, the more effective the Phrase Table is, in terms of its size and the output that may be derived out of it, the better is the expected outcome of the underlying translation system. However, finding the most similar phrase(s) from a given training corpus that can help generate a good quality translation poses a serious challenge. In practice, often there are many parallel phrase entries in a Phrase Table that are either redundant, or do not contribute to the translation results effectively. Identifying these candidate entries and removing them from the Phrase Table will not only reduce the size of the Phrase Table, but should also help in improving the processing speed for generating the translations. The present paper develops a scheme based on syntactic structure and the marker hypothesis (Green 1979, The necessity of syntax markers: two experiments with artificial languages, Journal of Verbal Learning and Behavior) for reducing the size of a Phrase Table, without compromising much on the translation quality of the output, by retaining the non-redundant and meaningful parallel phrases only. The proposed scheme is complemented with an appropriate similarity measurement scheme to achieve maximum efficiency in terms of BLEU scores. Although designed for Hindi to English machine translation, the overall approach is quite general, and is expected to be easily adaptable for other language pairs as well.

MTIL2017: Machine Translation Using Recurrent Neural Network on Statistical Machine Translation

Abstract Machine translation (MT) is the automatic translation of the source language to its target language by a computer system. In the current paper, we propose an approach of using recurrent neural networks (RNNs) over traditional statistical MT (SMT). We compare the performance of the phrase table of SMT to the performance of the proposed RNN and in turn improve the quality of the MT output. This work has been done as a part of the shared task problem provided by the MTIL2017. We have constructed the traditional MT model using Moses toolkit and have additionally enriched the language model using external data sets. Thereafter, we have ranked the phrase tables using an RNN encoder-decoder module created originally as a part of the GroundHog project of LISA lab.

Phrase Table Induction Using Monolingual Data for Low-Resource Statistical Machine Translation

We propose a new method for inducing a phrase-based translation model from a pair of unrelated monolingual corpora. Our method is able to deal with phrases of arbitrary length and to find phrase pairs that are useful for statistical machine translation, without requiring large parallel or comparable corpora. First, our method generates phrase pairs through coupling source and target phrases separately collected from respective monolingual data. Then, for each phrase pair, we compute features using the monolingual data and a small quantity of parallel sentences. Finally, incorrect phrase pairs are pruned, and a phrase table is made using the remaining phrase pairs. In our experiments on French--Japanese and Spanish--Japanese translation tasks under low-resource conditions, we observe that incorporating a phrase table induced by our method to the machine translation system leads to large improvements in translation quality. Furthermore, we show that a phrase table induced by our method can also be useful in a wide range of configurations, including configurations where we have already access to large parallel corpora and configurations where only small monolingual corpora are available.

Minimum Bayes-Risk Phrase Table Pruning for Pivot-Based Machine Translation in Internet of Things

Machine translation, which will be used widely in human-computer interaction services to Internet of Things (IoT), is a key technology in artificial intelligence field. This paper presents a minimum Bayes-risk (MBR) phrase table pruning method for pivot-based statistical machine translation (SMT). The SMT system requires a great amount of bilingual data to build a high-performance translation model. For some language pairs, such as Chinese-English, massive bilingual data are available on the web. However, for most language pairs, large-scale bilingual data are hard to obtain. Pivot-based SMT is proposed to solve the data scarcity problem: it introduces a pivot language to bridge the source language and the target language. Therefore, a source-target translation model based on well-trained source-pivot and pivot-target translation models can be derived with the pivot-based approach. However, due to the ambiguities of the pivot language, source and target phrases with different meanings may be wrongly matched. Consequently, the derived source-target phrase table may contain incorrect phrase pairs. To alleviate this problem, we apply the MBR method to prune the phrase table. The MBR pruning method removes the phrase pairs with the lowest risk from the phrase table. Experimental results on Europarl data show that the proposed method can both reduce the size of phrase tables and improve the performance of translations. This study also gives a useful reference to many IoT research field and smart web services.

Phrase Table Induction Using In-Domain Monolingual Data for Domain Adaptation in Statistical Machine Translation

We present a new framework to induce an in-domain phrase table from in-domain monolingual data that can be used to adapt a general-domain statistical machine translation system to the targeted domain. Our method first compiles sets of phrases in source and target languages separately and generates candidate phrase pairs by taking the Cartesian product of the two phrase sets. It then computes inexpensive features for each candidate phrase pair and filters them using a supervised classifier in order to induce an in-domain phrase table. We experimented on the language pair English–French, both translation directions, in two domains and obtained consistently better results than a strong baseline system that uses an in-domain bilingual lexicon. We also conducted an error analysis that showed the induced phrase tables proposed useful translations, especially for words and phrases unseen in the parallel data used to train the general-domain baseline system.

A system for terminology extraction and translation equivalent detection in real time

In this paper we present a system for automatic terminology extraction and automatic detection of the equivalent terms in the target language to be used alongside a computer assisted translation (CAT) tool that provides term candidates and their translations in an automatic way each time the translator goes from one segment to the next one. The system uses several sources of information: the text from the segment being translated and from the whole translation project, the translation memories assigned to the project and a translation phrase table from a statistical machine translation system. It also uses the terminological database assigned to the project in order to avoid presenting already known terms. The use of translation phrase tables allows us to use very large parallel corpora in a very efficient way. We have used Moses to calculate and to consult the translation phrase tables. The program is written in Python and it can be used with any CAT tool. In our experiments we have used OmegaT, a well-known open source CAT tool. Evaluation results for English–Spanish and for three subjects (politics, finance, and medicine) are presented.

A Comparison of Phrase Based and Word based Language Model for Punjabi

A language model provides connection to the decoding process to determine a precise word from several available options in the information base or phrase table. The language model can be generated using n-gram approach. Various language models and smoothing procedures are there to determine this model, like unigram, bigram, trigram, interpolation, backoff language model etc. We have done some experiments with different language models where we have used phrases in place of words as the smallest unit. Experiments have shown that phrase based language model yield more accurate results as compared to simple word based mode. We have also done some experiments with machine translation system where we have used phrase based language model rather than word based model and system yield great improvement.

Hierarchical Back-off Modeling of Hiero Grammar based on Non-parametric Bayesian Model

In hierarchical phrase-based machine translation, a rule table is automatically learned by heuristically extracting synchronous rules from a parallel corpus. As a result, spuriously many rules are extracted which may be composed of various incorrect rules. The larger rule table incurs more run time for decoding and may result in lower translation quality. To resolve the problems, we propose a hierarchical back-off model for Hiero grammar, an instance of a synchronous context free grammar (SCFG), on the basis of the hierarchical Pitman-Yor process. The model can extract a compact rule and phrase table without resorting to any heuristics by hierarchically backing off to smaller phrases under SCFG. Inference is efficiently carried out using two-step synchronous parsing of Xiao et al., (2012) combined with slice sampling. In our experiments, the proposed model achieved higher or at least comparable translation quality against a previous Bayesian model on various language pairs; German/French/Spanish/JapaneseEnglish. When compared against heuristic models, our model achieved comparable translation quality on a full size GermanEnglish language pair in Europarl v7 corpus with significantly smaller grammar size; less than 10% of that for heuristic model.