In the present study, we propose novel sequence-to-sequence pre-training objectives for low-resource machine translation (NMT): Japanese-specific sequence to sequence (JASS) for language pairs involving Japanese as the source or target language, and English-specific sequence to sequence (ENSS) for language pairs involving English. JASS focuses on masking and reordering Japanese linguistic units known as bunsetsu, whereas ENSS is proposed based on phrase structure masking and reordering tasks. Experiments on ASPEC Japanese--English & Japanese--Chinese, Wikipedia Japanese--Chinese, News English--Korean corpora demonstrate that JASS and ENSS outperform MASS and other existing language-agnostic pre-training methods by up to +2.9 BLEU points for the Japanese--English tasks, up to +7.0 BLEU points for the Japanese--Chinese tasks and up to +1.3 BLEU points for English--Korean tasks. Empirical analysis, which focuses on the relationship between individual parts in JASS and ENSS, reveals the complementary nature of the subtasks of JASS and ENSS. Adequacy evaluation using LASER, human evaluation, and case studies reveals that our proposed methods significantly outperform pre-training methods without injected linguistic knowledge and they have a larger positive impact on the adequacy as compared to the fluency. We release codes here: https://github.com/Mao-KU/JASS/tree/master/linguistically-driven-pretraining.
German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）；Common Sense Advisory (CSA Research)（常识咨询公司（CSA研究））
We present an alternative method of evaluating Quality Estimation systems, which is based on a linguistically-motivated Test Suite. We create a test-set consisting of 14 linguistic error categories and we gather for each of them a set of samples with both correct and erroneous translations. Then, we measure the performance of 5 Quality Estimation systems by checking their ability to distinguish between the correct and the erroneous translations. The detailed results are much more informative about the ability of each system. The fact that different Quality Estimation systems perform differentl…
In the field of Japanese-Chinese translation linguistics, the issue of correctly translating attributive clauses has persistently proven to be challenging. Present-day machine translation tools often fail to accurately translate attributive clauses from Japanese to Chinese. In light of this, this paper investigates the linguistic problem underlying such difficulties, namely how does the semantic role of the modified noun affect the selection of translation patterns for attributive clauses, from a linguistic perspective. To ad-dress these difficulties, a pre-edit scheme is proposed, which aims …
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 …
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…
Although recent years have brought significant progress in improving translation of unambiguously gendered sentences, translation of ambiguously gendered input remains relatively unexplored. When source gender is ambiguous, machine translation models typically default to stereotypical gender roles, perpetuating harmful bias. Recent work has led to the development of "gender rewriters" that generate alternative gender translations on such ambiguous inputs, but such systems are plagued by poor linguistic coverage. To encourage better performance on this task we present and release GATE, a lingui…
Alexandria: A Multi-Domain Dialectal Arabic Machine Translation Dataset for Culturally Inclusive and Linguistically Diverse LLMs
The University of British Columbia（不列颠哥伦比亚大学）；Canada Research Chair in NLP and ML（自然语言处理和机器学习研究主席）；Mohammed VI Polytechnic University（穆莱·阿卜杜勒阿齐兹国王理工学院）；Birzeit University（比尔泽特大学）；Western Michigan University（西部密歇根大学）；Tuwaiq Academy（图瓦伊克学院）；King Khalid University（国王卡利德大学）；American University of Beirut（贝鲁特美国大学）；Ibb University（伊卜大学）；University of Hail（海勒大学）；University of Technology and Applied Sciences（技术与应用科学大学）；Arab Open University（阿拉伯开放大学）；Minia University（米尼亚大学）；Nantes University（南特大学）；Prince Sultan University（沙特王子大学）；Umm Al-Qura University（乌姆·阿勒·卡拉大学）；University of Nouakchott（努尔人大学）；Fatabyyano（法塔比亚诺）；Independent Researcher（独立研究者）；Hadhramout University（哈德拉姆大学）；Cairo University（开罗大学）；Misurata University（米斯拉塔大学）；Al-Balqa Applied University（巴勒斯坦应用大学）；University of Khartoum（喀土穆大学）；Sultan Qaboos Higher Centre for Culture and Science（穆罕默德·本·拉希德·阿勒马克图姆文化与科学高级中心）；Arab Center for Research and Policy Studies（阿拉伯研究中心）；Hamad Bin Khalifa University（哈马德·本·哈利法大学）；Institut Supérieur du Numérique（数字高级学院）
We present a challenge set for French --> English machine translation based on the approach introduced in Isabelle, Cherry and Foster (EMNLP 2017). Such challenge sets are made up of sentences that are expected to be relatively difficult for machines to translate correctly because their most straightforward translations tend to be linguistically divergent. We present here a set of 506 manually constructed French sentences, 307 of which are targeted to the same kinds of structural divergences as in the paper mentioned above. The remaining 199 sentences are designed to test the ability of the sy…
Korean-Chinese is a low resource language pair, but Korean and Chinese have a lot in common in terms of vocabulary. Sino-Korean words, which can be converted into corresponding Chinese characters, account for more than fifty of the entire Korean vocabulary. Motivated by this, we propose a simple linguistically motivated solution to improve the performance of the Korean-to-Chinese neural machine translation model by using their common vocabulary. We adopt Chinese characters as a translation pivot by converting Sino-Korean words in Korean sentences to Chinese characters and then train the machin…
New York University Abu Dhabi（纽约大学阿布扎比分校）；Element AI
Neural networks have become the state-of-the-art approach for machine translation (MT) in many languages. While linguistically-motivated tokenization techniques were shown to have significant effects on the performance of statistical MT, it remains unclear if those techniques are well suited for neural MT. In this paper, we systematically compare neural and statistical MT models for Arabic-English translation on data preprecossed by various prominent tokenization schemes. Furthermore, we consider a range of data and vocabulary sizes and compare their effect on both approaches. Our empirical re…
College of Natural Sciences（自然科学学院）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；Department of Computer Science（计算机科学系）；San Jose State University（圣何塞州立大学）；Department of Linguistics（语言学系）；College of Information and Computer Sciences（信息与计算机科学学院）
Sequence to sequence (seq2seq) models are often employed in settings where the target output is natural language. However, the syntactic properties of the language generated from these models are not well understood. We explore whether such output belongs to a formal and realistic grammar, by employing the English Resource Grammar (ERG), a broad coverage, linguistically precise HPSG-based grammar of English. From a French to English parallel corpus, we analyze the parseability and grammatical constructions occurring in output from a seq2seq translation model. Over 93\% of the model translation…
BhashaSetu: A Data-Centric Approach to Low-Resource Machine Translation
Department of Computer Engineering and Information Technology, Veermata Jijabai Technological Institute, Mumbai（孟买韦尔马塔·吉贾拜技术学院计算机工程与信息技术系）；Tübingen AI Center, University of Tübingen, Germany（图宾根大学图宾根人工智能中心，德国）
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. …
In this paper, we investigate the use of linguistically motivated and computationally efficient structured language models for reranking N-best hypotheses in a statistical machine translation system. These language models, developed from Constraint Dependency Grammar parses, tightly integrate knowledge of words, morphological and lexical features, and syntactic dependency constraints. Two structured language models are applied for N-best rescoring, one is an almost-parsing language model, and the other utilizes more syntactic features by explicitly modeling syntactic dependencies between words…
Recent advances in Neural Machine Translation (NMT) show that adding syntactic information to NMT systems can improve the quality of their translations. Most existing work utilizes some specific types of linguistically-inspired tree structures, like constituency and dependency parse trees. This is often done via a standard RNN decoder that operates on a linearized target tree structure. However, it is an open question of what specific linguistic formalism, if any, is the best structural representation for NMT. In this paper, we (1) propose an NMT model that can naturally generate the topology …
German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）
We present an analysis of 16 state-of-the-art MT systems on German-English based on a linguistically-motivated test suite. The test suite has been devised manually by a team of language professionals in order to cover a broad variety of linguistic phenomena that MT often fails to translate properly. It contains 5,000 test sentences covering 106 linguistic phenomena in 14 categories, with an increased focus on verb tenses, aspects and moods. The MT outputs are evaluated in a semi-automatic way through regular expressions that focus only on the part of the sentence that is relevant to each pheno…
University of Texas at Austin（德克萨斯大学奥斯汀分校）；Facebook AI（脸书人工智能研究院）；The Hong Kong University of Science and Technology（香港科技大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；Twitter Cortex（推特Cortex部门）
The scarcity of parallel data is a major obstacle for training high-quality machine translation systems for low-resource languages. Fortunately, some low-resource languages are linguistically related or similar to high-resource languages; these related languages may share many lexical or syntactic structures. In this work, we exploit this linguistic overlap to facilitate translating to and from a low-resource language with only monolingual data, in addition to any parallel data in the related high-resource language. Our method, NMT-Adapt, combines denoising autoencoding, back-translation and a…
University of North Texas（北德克萨斯大学）；George Mason University（乔治梅森大学）
As machine translation (MT) systems progress at a rapid pace, questions of their adequacy linger. In this study we focus on negation, a universal, core property of human language that significantly affects the semantics of an utterance. We investigate whether translating negation is an issue for modern MT systems using 17 translation directions as test bed. Through thorough analysis, we find that indeed the presence of negation can significantly impact downstream quality, in some cases resulting in quality reductions of more than 60%. We also provide a linguistically motivated analysis that di…
Center For Indian Language Technology（印度语言技术中心）；Department of Computer Science & Engineering（计算机科学与工程系）；Indian Institute of Technology Bombay（印度理工学院孟买分校）
We explore the use of segments learnt using Byte Pair Encoding (referred to as BPE units) as basic units for statistical machine translation between related languages and compare it with orthographic syllables, which are currently the best performing basic units for this translation task. BPE identifies the most frequent character sequences as basic units, while orthographic syllables are linguistically motivated pseudo-syllables. We show that BPE units modestly outperform orthographic syllables as units of translation, showing up to 11% increase in BLEU score. While orthographic syllables can…
University of Amsterdam（阿姆斯特丹大学）；Informatics Institute（信息学研究所）
Neural Machine Translation (NMT) is an open vocabulary problem. As a result, dealing with the words not occurring during training (a.k.a. out-of-vocabulary (OOV) words) have long been a fundamental challenge for NMT systems. The predominant method to tackle this problem is Byte Pair Encoding (BPE) which splits words, including OOV words, into sub-word segments. BPE has achieved impressive results for a wide range of translation tasks in terms of automatic evaluation metrics. While it is often assumed that by using BPE, NMT systems are capable of handling OOV words, the effectiveness of BPE in …
Center for Information and Language Processing（信息与语言处理中心）；ILLC, University of Amsterdam（阿姆斯特丹大学逻辑、语言与计算研究所）；CIS, LMU Munich（慕尼黑大学信息与语言处理中心）；LMU Munich（慕尼黑大学）
Morphologically rich languages pose difficulties to machine translation. Machine translation engines that rely on statistical learning from parallel training data, such as state-of-the-art neural systems, face challenges especially with rich morphology on the output language side. Key challenges of rich target-side morphology in data-driven machine translation include: (1) A large amount of differently inflected word surface forms entails a larger vocabulary and thus data sparsity. (2) Some inflected forms of infrequent terms typically do not appear in the training corpus, which makes closed-v…
With the fast development of Machine Translation (MT) systems, especially the new boost from Neural MT (NMT) models, the MT output quality has reached a new level of accuracy. However, many researchers criticised that the current popular evaluation metrics such as BLEU can not correctly distinguish the state-of-the-art NMT systems regarding quality differences. In this short paper, we describe the design and implementation of a linguistically motivated human-in-the-loop evaluation metric looking into idiomatic and terminological Multi-word Expressions (MWEs). MWEs have played a bottleneck in m…
Grapheme-to-phoneme (G2P) models are a key component in Automatic Speech Recognition (ASR) systems, such as the ASR system in Alexa, as they are used to generate pronunciations for out-of-vocabulary words that do not exist in the pronunciation lexicons (mappings like "e c h o" to "E k oU"). Most G2P systems are monolingual and based on traditional joint-sequence based n-gram models [1,2]. As an alternative, we present a single end-to-end trained neural G2P model that shares same encoder and decoder across multiple languages. This allows the model to utilize a combination of universal symbol in…
Centre for Translation Studies（翻译研究中心）；University of Surrey（萨里大学）；RGCL（语言计算研究组）；University of Wolverhampton（伍尔弗汉普顿大学）
Although emotions are universal concepts, transferring the different shades of emotion from one language to another may not always be straightforward for human translators, let alone for machine translation systems. Moreover, the cognitive states are established by verbal explanations of experience which is shaped by both the verbal and cultural contexts. There are a number of verbal contexts where expression of emotions constitutes the pivotal component of the message. This is particularly true for User-Generated Content (UGC) which can be in the form of a review of a product or a service, a …
With the advent of faster computers, the notion of doing machine translation from a huge stored database of translation examples is no longer unreasonable. This paper describes an attempt to merge the Example-Based Machine Translation (EBMT) approach with psycholinguistic principles. A new formalism for context- free grammars, called *marker-normal form*, is demonstrated and used to describe language data in a way compatible with psycholinguistic theories. By embedding this formalism in a standard multivariate optimization framework, a system can be built that infers correct transfer functions…
Linguistic Acceptability is the task of determining whether a sentence is grammatical or ungrammatical. It has applications in several use cases like Question-Answering, Natural Language Generation, Neural Machine Translation, where grammatical correctness is crucial. In this paper we aim to understand the decision-making process of BERT (Devlin et al., 2019) in distinguishing between Linguistically Acceptable sentences (LA) and Linguistically Unacceptable sentences (LUA). We leverage Layer Integrated Gradients Attribution Scores (LIG) to explain the Linguistic Acceptability criteria that are …
U.S. Dept. of Defense（美国国防部）；JHU HLTCOE（约翰斯·霍普金斯大学人类语言技术卓越中心）；University of Maryland（马里兰大学）；CMU（卡内基梅隆大学）；BBN（BBN公司）；JHU/APL（约翰斯·霍普金斯大学应用物理实验室）
We describe a unified and coherent syntactic framework for supporting a semantically-informed syntactic approach to statistical machine translation. Semantically enriched syntactic tags assigned to the target-language training texts improved translation quality. The resulting system significantly outperformed a linguistically naive baseline model (Hiero), and reached the highest scores yet reported on the NIST 2009 Urdu-English translation task. This finding supports the hypothesis (posed by many researchers in the MT community, e.g., in DARPA GALE) that both syntactic and semantic information…
University of Macau（澳门大学）；NewTranx Information Technology（新译信息科技）
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 training an NMT by introducing a novel norm-based curriculum learning method. We use the norm (aka length or module) of a word embedding as a measure of 1) the difficulty of the sentence, 2) the competence of the model, and 3) the weight of the sentence. The norm-based sentence difficulty takes the advantages of both linguistically motivated and model-based s…
University of Alicante（阿利坎特大学）；Center for Responsible Artificial Intelligence (CRAI)（负责任人工智能中心）；Coburg University of Applied Sciences and Arts（科堡应用科学与艺术大学）
The state of the art in learning meaningful semantic representations of words is the Transformer model and its attention mechanisms. Simply put, the attention mechanisms learn to attend to specific parts of the input dispensing recurrence and convolutions. While some of the learned attention heads have been found to play linguistically interpretable roles, they can be redundant or prone to errors. We propose a method to guide the attention heads towards roles identified in prior work as important. We do this by defining role-specific masks to constrain the heads to attend to specific parts of …
Yandex（扬德克斯）；University of Amsterdam（阿姆斯特丹大学）；Moscow Institute of Physics and Technology（莫斯科物理技术学院）；University of Edinburgh（爱丁堡大学）；University of Zurich（苏黎世大学）
Multi-head self-attention is a key component of the Transformer, a state-of-the-art architecture for neural machine translation. In this work we evaluate the contribution made by individual attention heads in the encoder to the overall performance of the model and analyze the roles played by them. We find that the most important and confident heads play consistent and often linguistically-interpretable roles. When pruning heads using a method based on stochastic gates and a differentiable relaxation of the L0 penalty, we observe that specialized heads are last to be pruned. Our novel pruning m…
Progress in cross-lingual modeling depends on challenging, realistic, and diverse evaluation sets. We introduce Multilingual Knowledge Questions and Answers (MKQA), an open-domain question answering evaluation set comprising 10k question-answer pairs aligned across 26 typologically diverse languages (260k question-answer pairs in total). Answers are based on a heavily curated, language-independent data representation, making results comparable across languages and independent of language-specific passages. With 26 languages, this dataset supplies the widest range of languages to-date for evalu…
Multilingual Neural Machine Translation (NMT) models have yielded large empirical success in transfer learning settings. However, these black-box representations are poorly understood, and their mode of transfer remains elusive. In this work, we attempt to understand massively multilingual NMT representations (with 103 languages) using Singular Value Canonical Correlation Analysis (SVCCA), a representation similarity framework that allows us to compare representations across different languages, layers and models. Our analysis validates several empirical results and long-standing intuitions, a…
Hebrew University of Jerusalem（耶路撒冷希伯来大学）；Stockholm University（斯德哥尔摩大学）；University of Stuttgart（斯图加特大学）
We explore the link between the extent to which syntactic relations are preserved in translation and the ease of correctly constructing a parse tree in a zero-shot setting. While previous work suggests such a relation, it tends to focus on the macro level and not on the level of individual edges-a gap we aim to address. As a test case, we take the transfer of Universal Dependencies (UD) parsing from English to a diverse set of languages and conduct two sets of experiments. In one, we analyze zero-shot performance based on the extent to which English source edges are preserved in translation. I…
AlexandriaX 2026: The First Shared Task on Dialectal Arabic Machine Translation
The University of British Columbia（不列颠哥伦比亚大学）；King Fahd University of Petroleum and Minerals（法赫德国王石油矿产大学）；Lancaster University（兰卡斯特大学）；VinUniversity；Hamad Bin Khalifa University（哈马德·本·哈利法大学）；King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）
Decoding Multilingual Topic Dynamics and Trend Identification through ARIMA Time Series Analysis on Social Networks: A Novel Data Translation Framework Enhanced by LDA/HDP Models
Research Laboratory in Algebra Numbers theory and Intelligent Systems（代数数论与智能系统研究实验室）；CNRS（法国国家科学研究中心）；Bordeaux INP（波尔多国立高等工程技术学院）；LaBRI（波尔多计算机科学实验室）；Laboratory LIG（LIG实验室）
