Neural machine translation (NMT) has achieved impressive performance on machine translation task in recent years. However, in consideration of efficiency, a limited-size vocabulary that only contains the top-N highest frequency words are employed for model training, which leads to many rare and unknown words. It is rather difficult when translating from the low-resource and morphologically-rich agglutinative languages, which have complex morphology and large vocabulary. In this paper, we propose a morphological word segmentation method on the source-side for NMT that incorporates morphology knowledge to preserve the linguistic and semantic information in the word structure while reducing the vocabulary size at training time. It can be utilized as a preprocessing tool to segment the words in agglutinative languages for other natural language processing (NLP) tasks. Experimental results show that our morphologically motivated word segmentation method is better suitable for the NMT model, which achieves significant improvements on Turkish-English and Uyghur-Chinese machine translation tasks on account of reducing data sparseness and language complexity.
Middle East Technical University（中东技术大学）；Hacettepe University（哈杰泰佩大学）
In this paper, we build morphological chains for agglutinative languages by using a log-linear model for the morphological segmentation task. The model is based on the unsupervised morphological segmentation system called MorphoChains. We extend MorphoChains log linear model by expanding the candidate space recursively to cover more split points for agglutinative languages such as Turkish, whereas in the original model candidates are generated by considering only binary segmentation of each word. The results show that we improve the state-of-art Turkish scores by 12% having a F-measure of 72% …
English to Indian language machine translation poses the challenge of structural and morphological divergence. This paper describes English to Indian language statistical machine translation using pre-ordering and suffix separation. The pre-ordering uses rules to transfer the structure of the source sentences prior to training and translation. This syntactic restructuring helps statistical machine translation to tackle the structural divergence and hence better translation quality. The suffix separation is used to tackle the morphological divergence between English and highly agglutinative Ind…
University of Edinburgh（爱丁堡大学）；New York University（纽约大学）；Aalborg University（奥尔堡大学）
Theoretical work in morphological typology offers the possibility of measuring morphological diversity on a continuous scale. However, literature in Natural Language Processing (NLP) typically labels a whole language with a strict type of morphology, e.g. fusional or agglutinative. In this work, we propose to reduce the rigidity of such claims, by quantifying morphological typology at the word and segment level. We consider Payne (2017)'s approach to classify morphology using two indices: synthesis (e.g. analytic to polysynthetic) and fusion (agglutinative to fusional). For computing synthesis…
Beijing University of Posts and Telecommunications（北京邮电大学）；Xinjiang University（新疆大学）；Tsinghua University（清华大学）
Neural machine translation (NMT) has achieved notable performance recently. However, this approach has not been widely applied to the translation task between Chinese and Uyghur, partly due to the limited parallel data resource and the large proportion of rare words caused by the agglutinative nature of Uyghur. In this paper, we collect ~200,000 sentence pairs and show that with this middle-scale database, an attention-based NMT can perform very well on Chinese-Uyghur/Uyghur-Chinese translation. To tackle rare words, we propose a novel memory structure to assist the NMT inference. Our experime…
This paper discusses Centre for Development of Advanced Computing Mumbai's (CDACM) submission to the NLP Tools Contest on Statistical Machine Translation in Indian Languages (ILSMT) 2014 (collocated with ICON 2014). The objective of the contest was to explore the effectiveness of Statistical Machine Translation (SMT) for Indian language to Indian language and English-Hindi machine translation. In this paper, we have proposed that suffix separation and word splitting for SMT from agglutinative languages to Hindi significantly improves over the baseline (BL). We have also shown that the factored…
FBK（布鲁诺·凯斯勒基金会）；University of Trento（特伦托大学）；MMT Srl（MMT有限公司）
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 segmenting words into sub-word units and performing translation at the sub-lexical level. However, statistical word segmentation methods have recently shown to be prone to morphological errors, which can lead to inaccurate translations. In this paper, we propose to overcome this problem by replacing the source-language embedding layer of NMT with a bi-directiona…
Neural machine translation (NMT) systems operate primarily on words (or sub-words), ignoring lower-level patterns of morphology. We present a character-aware decoder designed to capture such patterns when translating into morphologically rich languages. We achieve character-awareness by augmenting both the softmax and embedding layers of an attention-based encoder-decoder model with convolutional neural networks that operate on the spelling of a word. To investigate performance on a wide variety of morphological phenomena, we translate English into 14 typologically diverse target languages usi…
Lexically constrained machine translation allows the user to manipulate the output sentence by enforcing the presence or absence of certain words and phrases. Although current approaches can enforce terms to appear in the translation, they often struggle to make the constraint word form agree with the rest of the generated output. Our manual analysis shows that 46% of the errors in the output of a baseline constrained model for English to Czech translation are related to agreement. We investigate mechanisms to allow neural machine translation to infer the correct word inflection given lemmatiz…
Phrase-based Statistical models are more commonly used as they perform optimally in terms of both, translation quality and complexity of the system. Hindi and in general all Indian languages are morphologically richer than English. Hence, even though Phrase-based systems perform very well for the less divergent language pairs, for English to Indian language translation, we need more linguistic information (such as morphology, parse tree, parts of speech tags, etc.) on the source side. Factored models seem to be useful in this case, as Factored models consider word as a vector of factors. These…
ADAPT Centre（ADAPT研究中心）；School of Computing（计算学院）；Dublin City University（都柏林城市大学）
Recently, neural machine translation (NMT) has emerged as a powerful alternative to conventional statistical approaches. However, its performance drops considerably in the presence of morphologically rich languages (MRLs). Neural engines usually fail to tackle the large vocabulary and high out-of-vocabulary (OOV) word rate of MRLs. Therefore, it is not suitable to exploit existing word-based models to translate this set of languages. In this paper, we propose an extension to the state-of-the-art model of Chung et al. (2016), which works at the character level and boosts the decoder with target…
Syntactic parsing is a necessary task which is required for NLP applications including machine translation. It is a challenging task to develop a qualitative parser for morphological rich and agglutinative languages. Syntactic analysis is used to understand the grammatical structure of a natural language sentence. It outputs all the grammatical information of each word and its constituent. Also issues related to it help us to understand the language in a more detailed way. This literature survey is groundwork to understand the different parser development for Indian languages and various appro…
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 where constraint terms are provided as lemmas. In this paper, we introduce a modular framework for incorporating lemma constraints in neural MT (NMT) in which linguistic knowledge and diverse types of NMT models can be flexibly applied. It is based on a novel cross-lingual inflection module that inflects the target lemma constraints based on the source context. …
The necessity of using a fixed-size word vocabulary in order to control the model complexity in state-of-the-art neural machine translation (NMT) systems is an important bottleneck on performance, especially for morphologically rich languages. Conventional methods that aim to overcome this problem by using sub-word or character-level representations solely rely on statistics and disregard the linguistic properties of words, which leads to interruptions in the word structure and causes semantic and syntactic losses. In this paper, we propose a new vocabulary reduction method for NMT, which can …
Indian Institute of Technology (IIT) Bombay（印度理工学院孟买分校）
When translating into morphologically rich languages, Statistical MT approaches face the problem of data sparsity. The severity of the sparseness problem will be high when the corpus size of morphologically richer language is less. Even though we can use factored models to correctly generate morphological forms of words, the problem of data sparseness limits their performance. In this paper, we describe a simple and effective solution which is based on enriching the input corpora with various morphological forms of words. We use this method with the phrase-based and factor-based experiments on…
A new tightly coupled speech and natural language integration model is presented for a TDNN-based large vocabulary continuous speech recognition system. Unlike the popular n-best techniques developed for integrating mainly HMM-based speech and natural language systems in word level, which is obviously inadequate for the morphologically complex agglutinative languages, our model constructs a spoken language system based on the phoneme-level integration. The TDNN-CYK spoken language architecture is designed and implemented using the TDNN-based diphone recognition module integrated with the table…
Machine translation has seen rapid progress with the advent of Transformer-based models. These models have no explicit linguistic structure built into them, yet they may still implicitly learn structured relationships by attending to relevant tokens. We hypothesize that this structural learning could be made more robust by explicitly endowing Transformers with a structural bias, and we investigate two methods for building in such a bias. One method, the TP-Transformer, augments the traditional Transformer architecture to include an additional component to represent structure. The second method…
The state of the art of handling rich morphology in neural machine translation (NMT) is to break word forms into subword units, so that the overall vocabulary size of these units fits the practical limits given by the NMT model and GPU memory capacity. In this paper, we compare two common but linguistically uninformed methods of subword construction (BPE and STE, the method implemented in Tensor2Tensor toolkit) and two linguistically-motivated methods: Morfessor and one novel method, based on a derivational dictionary. Our experiments with German-to-Czech translation, both morphologically rich…
Columbia University（哥伦比亚大学）；New York University Abu Dhabi（纽约大学阿布扎比分校）
The lack of parallel data for many language pairs is an important challenge to statistical machine translation (SMT). One common solution is to pivot through a third language for which there exist parallel corpora with the source and target languages. Although pivoting is a robust technique, it introduces some low quality translations especially when a poor morphology language is used as the pivot between rich morphology languages. In this paper, we examine the use of synchronous morphology constraint features to improve the quality of phrase pivot SMT. We compare hand-crafted constraints to t…
LMU Munich（慕尼黑大学）；Memsource；University of Stuttgart（斯图加特大学）
NMT systems have problems with large vocabulary sizes. Byte-pair encoding (BPE) is a popular approach to solving this problem, but while BPE allows the system to generate any target-side word, it does not enable effective generalization over the rich vocabulary in morphologically rich languages with strong inflectional phenomena. We introduce a simple approach to overcome this problem by training a system to produce the lemma of a word and its morphologically rich POS tag, which is then followed by a deterministic generation step. We apply this strategy for English-Czech and English-German tra…
University of Melbourne（墨尔本大学）；Monash University（莫纳什大学）
Dealing with the complex word forms in morphologically rich languages is an open problem in language processing, and is particularly important in translation. In contrast to most modern neural systems of translation, which discard the identity for rare words, in this paper we propose several architectures for learning word representations from character and morpheme level word decompositions. We incorporate these representations in a novel machine translation model which jointly learns word alignments and translations via a hard attention mechanism. Evaluating on translating from several morph…
Indonesian is an agglutinative language since it has a compounding process of word-formation. Therefore, the translation model of this language requires a mechanism that is even lower than the word level, referred to as the sub-word level. This compounding process leads to a rare word problem since the number of vocabulary explodes. We propose a strategy to address the unique word problem of the neural machine translation (NMT) system, which uses Indonesian as a pair language. Our approach uses a rule-based method to transform a word into its roots and accompanied affixes to retain its meaning…
University of Trento（特伦托大学）；University of Edinburgh（爱丁堡大学）；University of Zürich（苏黎世大学）；University of Amsterdam（阿姆斯特丹大学）
Translation into morphologically-rich languages challenges neural machine translation (NMT) models with extremely sparse vocabularies where atomic treatment of surface forms is unrealistic. This problem is typically addressed by either pre-processing words into subword units or performing translation directly at the level of characters. The former is based on word segmentation algorithms optimized using corpus-level statistics with no regard to the translation task. The latter learns directly from translation data but requires rather deep architectures. In this paper, we propose to translate w…
The number of word forms in agglutinative languages is theoretically infinite and this variety in word forms introduces sparsity in many natural language processing tasks. Part-of-speech tagging (PoS tagging) is one of these tasks that often suffers from sparsity. In this paper, we present an unsupervised Bayesian model using Hidden Markov Models (HMMs) for joint PoS tagging and stemming for agglutinative languages. We use stemming to reduce sparsity in PoS tagging. Two tasks are jointly performed to provide a mutual benefit in both tasks. Our results show that joint POS tagging and stemming i…
University of Stuttgart（斯图加特大学）；Universidad Nacional Autónoma de México（墨西哥国立自治大学）；University of Edinburgh（爱丁堡大学）；University of Colorado Boulder（科罗拉多大学博尔德分校）
Morphologically-rich polysynthetic languages present a challenge for NLP systems due to data sparsity, and a common strategy to handle this issue is to apply subword segmentation. We investigate a wide variety of supervised and unsupervised morphological segmentation methods for four polysynthetic languages: Nahuatl, Raramuri, Shipibo-Konibo, and Wixarika. Then, we compare the morphologically inspired segmentation methods against Byte-Pair Encodings (BPEs) as inputs for machine translation (MT) when translating to and from Spanish. We show that for all language pairs except for Nahuatl, an uns…
We propose a language-independent approach for improving statistical machine translation for morphologically rich languages using a hybrid morpheme-word representation where the basic unit of translation is the morpheme, but word boundaries are respected at all stages of the translation process. Our model extends the classic phrase-based model by means of (1) word boundary-aware morpheme-level phrase extraction, (2) minimum error-rate training for a morpheme-level translation model using word-level BLEU, and (3) joint scoring with morpheme- and word-level language models. Further improvements …
Bar Ilan University（巴伊兰大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
When translating from a language that does not morphologically mark information such as gender and number into a language that does, translation systems must "guess" this missing information, often leading to incorrect translations in the given context. We propose a black-box approach for injecting the missing information to a pre-trained neural machine translation system, allowing to control the morphological variations in the generated translations without changing the underlying model or training data. We evaluate our method on an English to Hebrew translation task, and show that it is effe…
Machine translation tools do not yet exist for the Yup'ik language, a polysynthetic language spoken by around 8,000 people who live primarily in Southwest Alaska. We compiled a parallel text corpus for Yup'ik and English and developed a morphological parser for Yup'ik based on grammar rules. We trained a seq2seq neural machine translation model with attention to translate Yup'ik input into English. We then compared the influence of different tokenization methods, namely rule-based, unsupervised (byte pair encoding), and unsupervised morphological (Morfessor) parsing, on BLEU score accuracy for…
Soochow University（苏州大学）；Alibaba Group（阿里巴巴集团）；Singapore University of Technology and Design（新加坡科技设计大学）
Neural machine translation (NMT) suffers a performance deficiency when a limited vocabulary fails to cover the source or target side adequately, which happens frequently when dealing with morphologically rich languages. To address this problem, previous work focused on adjusting translation granularity or expanding the vocabulary size. However, morphological information is relatively under-considered in NMT architectures, which may further improve translation quality. We propose a novel method, which can not only reduce data sparsity but also model morphology through a simple but effective mec…
Out of vocabulary (OOV) is a problem in the context of Machine Translation (MT) in low-resourced languages. When source and/or target languages are morphologically rich, it becomes even worse. Bilingual list integration is an approach to address the OOV problem. This allows more words to be translated than are in the training data. However, since bilingual lists contain words in the base form, it will not translate inflected forms for morphologically rich languages such as Sinhala and Tamil. This paper focuses on data augmentation techniques where bilingual lexicon terms are expanded based on …
Translation ambiguity, out of vocabulary words and missing some translations in bilingual dictionaries make dictionary-based Cross-language Information Retrieval (CLIR) a challenging task. Moreover, in agglutinative languages which do not have reliable stemmers, missing various lexical formations in bilingual dictionaries degrades CLIR performance. This paper aims to introduce a probabilistic translation model to solve the ambiguity problem, and also to provide most likely formations of a dictionary candidate. We propose Minimum Edit Support Candidates (MESC) method that exploits a monolingual…
The advent of the attention mechanism in neural machine translation models has improved the performance of machine translation systems by enabling selective lookup into the source sentence. In this paper, the efficiencies of translation using bidirectional encoder attention decoder models were studied with respect to translation involving morphologically rich languages. The English - Tamil language pair was selected for this analysis. First, the use of Word2Vec embedding for both the English and Tamil words improved the translation results by 0.73 BLEU points over the baseline RNNSearch model …
University of Zurich（苏黎世大学）；University of Edinburgh（爱丁堡大学）
Data-driven subword segmentation has become the default strategy for open-vocabulary machine translation and other NLP tasks, but may not be sufficiently generic for optimal learning of non-concatenative morphology. We design a test suite to evaluate segmentation strategies on different types of morphological phenomena in a controlled, semi-synthetic setting. In our experiments, we compare how well machine translation models trained on subword- and character-level can translate these morphological phenomena. We find that learning to analyse and generate morphologically complex surface represen…
This paper presents a scalable method for integrating compositional morphological representations into a vector-based probabilistic language model. Our approach is evaluated in the context of log-bilinear language models, rendered suitably efficient for implementation inside a machine translation decoder by factoring the vocabulary. We perform both intrinsic and extrinsic evaluations, presenting results on a range of languages which demonstrate that our model learns morphological representations that both perform well on word similarity tasks and lead to substantial reductions in perplexity. W…
Delhi Technological University (Formerly Delhi college of Engineering)（德里理工大学（原德里工程学院））
A large number of significant assets are available online in English, which is frequently translated into native languages to ease the information sharing among local people who are not much familiar with English. However, manual translation is a very tedious, costly, and time-taking process. To this end, machine translation is an effective approach to convert text to a different language without any human involvement. Neural machine translation (NMT) is one of the most proficient translation techniques amongst all existing machine translation systems. In this paper, we have applied NMT on two…
University of Helsinki（赫尔辛基大学）；Raamatun Tietokirja, Aika[media] Oy（Raamatun Tietokirja Aika[media]公司）
Twenty-five years ago, morphologically aligned Hebrew-Finnish and Greek-Finnish bitexts (texts accompanied by a translation) were constructed manually in order to create an analytical concordance (Luoto et al., 1997) for a Finnish Bible translation. The creators of the bitexts recently secured the publisher's permission to release its fine-grained alignment, but the alignment was still dependent on proprietary, third-party resources such as a copyrighted text edition and proprietary morphological analyses of the source texts. In this paper, we describe a nontrivial editorial process starting f…
While most of the speech and natural language systems which were developed for English and other Indo-European languages neglect the morphological processing and integrate speech and natural language at the word level, for the agglutinative languages such as Korean and Japanese, the morphological processing plays a major role in the language processing since these languages have very complex morphological phenomena and relatively simple syntactic functionality. Obviously degenerated morphological processing limits the usable vocabulary size for the system and word-level dictionary results in e…
UNIVERSITE FERHAT ABBAS – SETIF 1（费哈特·阿巴斯大学-塞提夫1号）；Faculté des Sciences（理学院）；Université El Oued（乌埃勒大学）；Université Sétif -1-（塞提夫1号大学）；Université Souk Ahras（苏克阿赫拉斯大学）；Université BBA（巴特纳大学）
In this thesis, we address several important issues concerning the morphological analysis of Arabic language applied to textual data and machine translation. First, we provided an overview on machine translation, its history and its development, then we exposed human translation techniques for eventual inspiration in machine translation, and we exposed linguistic approaches and particularly indirect transfer approaches. Finally, we presented our contributions to the resolution of morphosyntactic problems in computer linguistics as multilingual information retrieval and machine translation. As …
We present a new approach for neural machine translation (NMT) using the morphological and grammatical decomposition of the words (factors) in the output side of the neural network. This architecture addresses two main problems occurring in MT, namely dealing with a large target language vocabulary and the out of vocabulary (OOV) words. By the means of factors, we are able to handle larger vocabulary and reduce the training time (for systems with equivalent target language vocabulary size). In addition, we can produce new words that are not in the vocabulary. We use a morphological analyser to…
University of Southern California（南加州大学）；University of Washington（华盛顿大学）
Most statistical machine translation systems cannot translate words that are unseen in the training data. However, humans can translate many classes of out-of-vocabulary (OOV) words (e.g., novel morphological variants, misspellings, and compounds) without context by using orthographic clues. Following this observation, we describe and evaluate several general methods for OOV translation that use only subword information. We pose the OOV translation problem as a standalone task and intrinsically evaluate our approaches on fourteen typologically diverse languages across varying resource levels. …
This thesis investigates how the sub-structure of words can be accounted for in probabilistic models of language. Such models play an important role in natural language processing tasks such as translation or speech recognition, but often rely on the simplistic assumption that words are opaque symbols. This assumption does not fit morphologically complex language well, where words can have rich internal structure and sub-word elements are shared across distinct word forms. Our approach is to encode basic notions of morphology into the assumptions of three different types of language models, wi…
Machine Translation is the challenging problem for Indian languages. Every day we can see some machine translators being developed, but getting a high quality automatic translation is still a very distant dream . The correct translated sentence for Hindi language is rarely found. In this paper, we are emphasizing on English-Hindi language pair, so in order to preserve the correct MT output we present a ranking system, which employs some machine learning techniques and morphological features. In ranking no human intervention is required. We have also validated our results by comparing it with h…
Unlike English, morphologically rich languages can reveal characteristics of speakers or their conversational partners, such as gender and number, via pronouns, morphological endings of words and syntax. When translating from English to such languages, a machine translation model needs to opt for a certain interpretation of textual context, which may lead to serious translation errors if extra-textual information is unavailable. We investigate this challenge in the English-to-Polish language direction. We focus on the underresearched problem of utilising external metadata in automatic translat…
LMU Munich（慕尼黑大学）；Charles University in Prague（布拉格查理大学）；Adam Mickiewicz University in Poznań（波兹南亚当·密茨凯维奇大学）
Discriminative translation models utilizing source context have been shown to help statistical machine translation performance. We propose a novel extension of this work using target context information. Surprisingly, we show that this model can be efficiently integrated directly in the decoding process. Our approach scales to large training data sizes and results in consistent improvements in translation quality on four language pairs. We also provide an analysis comparing the strengths of the baseline source-context model with our extended source-context and target-context model and we show …
Center for Language and Cognition（语言与认知中心）；University of Groningen（格罗宁根大学）
Character-based representations have important advantages over subword-based ones for morphologically rich languages. They come with increased robustness to noisy input and do not need a separate tokenization step. However, they also have a crucial disadvantage: they notably increase the length of text sequences. The GBST method from Charformer groups (aka downsamples) characters to solve this, but allows information to leak when applied to a Transformer decoder. We solve this information leak issue, thereby enabling character grouping in the decoder. We show that Charformer downsampling has n…
Dublin City University（都柏林城市大学）；University of the Basque Country（巴斯克大学）
In this paper we present the ADAPT system built for the Basque to English Low Resource MT Evaluation Campaign. Basque is a low-resourced, morphologically-rich language. This poses a challenge for Neural Machine Translation models which usually achieve better performance when trained with large sets of data. Accordingly, we used synthetic data to improve the translation quality produced by a model built using only authentic data. Our proposal uses back-translated data to: (a) create new sentences, so the system can be trained with more data; and (b) translate sentences that are close to the tes…
Factored neural machine translation (FNMT) is founded on the idea of using the morphological and grammatical decomposition of the words (factors) at the output side of the neural network. This architecture addresses two well-known problems occurring in MT, namely the size of target language vocabulary and the number of unknown tokens produced in the translation. FNMT system is designed to manage larger vocabulary and reduce the training time (for systems with equivalent target language vocabulary size). Moreover, we can produce grammatically correct words that are not part of the vocabulary. F…
Center for Artificial Intelligence Research (CAiRE)（人工智能研究中心（CAiRE））；The Hong Kong University of Science and Technology（香港科技大学）
This paper describes CAiRE's submission to the unsupervised machine translation track of the WMT'19 news shared task from German to Czech. We leverage a phrase-based statistical machine translation (PBSMT) model and a pre-trained language model to combine word-level neural machine translation (NMT) and subword-level NMT models without using any parallel data. We propose to solve the morphological richness problem of languages by training byte-pair encoding (BPE) embeddings for German and Czech separately, and they are aligned using MUSE (Conneau et al., 2018). To ensure the fluency and consist…
Neural Machine Translation (NMT) in low-resource settings and of morphologically rich languages is made difficult in part by data sparsity of vocabulary words. Several methods have been used to help reduce this sparsity, notably Byte-Pair Encoding (BPE) and a character-based CNN layer (charCNN). However, the charCNN has largely been neglected, possibly because it has only been compared to BPE rather than combined with it. We argue for a reconsideration of the charCNN, based on cross-lingual improvements on low-resource data. We translate from 8 languages into English, using a multi-way paralle…
Universitat Politècnica de València（瓦伦西亚理工大学）；Pangeanic / B.I Europa
Tokenization or segmentation is a wide concept that covers simple processes such as separating punctuation from words, or more sophisticated processes such as applying morphological knowledge. Neural Machine Translation (NMT) requires a limited-size vocabulary for computational cost and enough examples to estimate word embeddings. Separating punctuation and splitting tokens into words or subwords has proven to be helpful to reduce vocabulary and increase the number of examples of each word, improving the translation quality. Tokenization is more challenging when dealing with languages with no …
