Machine Translation System (MTS) serves as an effective tool for communication by translating text or speech from one language to another language. The need of an efficient translation system becomes obvious in a large multilingual environment like India, where English and a set of Indian Languages (ILs) are officially used. In contrast with English, ILs are still entreated as low-resource languages due to unavailability of corpora. In order to address such asymmetric nature, multilingual neural machine translation (MNMT) system evolves as an ideal approach in this direction. In this paper, we propose a MNMT system to address the issues related to low-resource language translation. Our model comprises of two MNMT systems i.e. for English-Indic (one-to-many) and the other for Indic-English (many-to-one) with a shared encoder-decoder containing 15 language pairs (30 translation directions). Since most of IL pairs have scanty amount of parallel corpora, not sufficient for training any machine translation model. We explore various augmentation strategies to improve overall translation quality through the proposed model. A state-of-the-art transformer architecture is used to realize the proposed model. Trials over a good amount of data reveal its superiority over the conventional models. In addition, the paper addresses the use of language relationships (in terms of dialect, script, etc.), particularly about the role of high-resource languages of the same family in boosting the performance of low-resource languages. Moreover, the experimental results also show the advantage of backtranslation and domain adaptation for ILs to enhance the translation quality of both source and target languages. Using all these key approaches, our proposed model emerges to be more efficient than the baseline model in terms of evaluation metrics i.e BLEU (BiLingual Evaluation Understudy) score for a set of ILs.
Localizing a semantic parser to support new languages requires effective cross-lingual generalization. Recent work has found success with machine-translation or zero-shot methods although these approaches can struggle to model how native speakers ask questions. We consider how to effectively leverage minimal annotated examples in new languages for few-shot cross-lingual semantic parsing. We introduce a first-order meta-learning algorithm to train a semantic parser with maximal sample efficiency during cross-lingual transfer. Our algorithm uses high-resource languages to train the parser and simultaneously optimizes for cross-lingual generalization for lower-resource languages. Results across six languages on ATIS demonstrate that our combination of generalization steps yields accurate semantic parsers sampling $\le$10% of source training data in each new language. Our approach also trains a competitive model on Spider using English with generalization to Chinese similarly sampling $\le$10% of training data.
Cyrillic and Traditional Mongolian are the two main members of the Mongolian writing system. The Cyrillic-Traditional Mongolian Bidirectional Conversion (CTMBC) task includes two conversion processes, including Cyrillic Mongolian to Traditional Mongolian (C2T) and Traditional Mongolian to Cyrillic Mongolian conversions (T2C). Previous researchers adopted the traditional joint sequence model, since the CTMBC task is a natural Sequence-to-Sequence (Seq2Seq) modeling problem. Recent studies have shown that Recurrent Neural Network (RNN) and Self-attention (or Transformer) based encoder-decoder models have shown significant improvement in machine translation tasks between some major languages, such as Mandarin, English, French, etc. However, an open problem remains as to whether the CTMBC quality can be improved by utilizing the RNN and Transformer models. To answer this question, this paper investigates the utility of these two powerful techniques for CTMBC task combined with agglutinative characteristics of Mongolian language. We build the encoder-decoder based CTMBC model based on RNN and Transformer respectively and compare the different network configurations deeply. The experimental results show that both RNN and Transformer models outperform the traditional joint sequence model, where the Transformer achieves the best performance. Compared with the joint sequence baseline, the word error rate (WER) of the Transformer for C2T and T2C decreased by 5.72\% and 5.06\% respectively.
Recent advances in large pre-trained language models have demonstrated strong results in generating natural languages and significantly improved performances for many natural language generation (NLG) applications such as machine translation and text summarization. However, when the generation tasks are more open-ended and the content is under-specified, existing techniques struggle to generate long-term coherent and creative content. Moreover, the models exhibit and even amplify social biases that are learned from the training corpora. This happens because the generation models are trained to capture the surface patterns (i.e. sequences of words), instead of capturing underlying semantics and discourse structures, as well as background knowledge including social norms. In this paper, I introduce our recent works on controllable text generation to enhance the creativity and fairness of language generation models. We explore hierarchical generation and constrained decoding, with applications to creative language generation including story, poetry, and figurative languages, and bias mitigation for generation models.
Domain adaptation is an important challenge for neural machine translation. However, the traditional fine-tuning solution requires multiple extra training and yields a high cost. In this paper, we propose a non-tuning paradigm, resolving domain adaptation with a prompt-based method. Specifically, we construct a bilingual phrase-level database and retrieve relevant pairs from it as a prompt for the input sentences. By utilizing Retrieved Phrase-level Prompts (RePP), we effectively boost the translation quality. Experiments show that our method improves domain-specific machine translation for 6.2 BLEU scores and improves translation constraints for 11.5% accuracy without additional training.
This paper presents our contribution to the PolEval 2021 Task 2: Evaluation of translation quality assessment metrics. We describe experiments with pre-trained language models and state-of-the-art frameworks for translation quality assessment in both nonblind and blind versions of the task. Our solutions ranked second in the nonblind version and third in the blind version.
This paper introduces a new data augmentation method for neural machine translation that can enforce stronger semantic consistency both within and across languages. Our method is based on Conditional Masked Language Model (CMLM) which is bi-directional and can be conditional on both left and right context, as well as the label. We demonstrate that CMLM is a good technique for generating context-dependent word distributions. In particular, we show that CMLM is capable of enforcing semantic consistency by conditioning on both source and target during substitution. In addition, to enhance diversity, we incorporate the idea of soft word substitution for data augmentation which replaces a word with a probabilistic distribution over the vocabulary. Experiments on four translation datasets of different scales show that the overall solution results in more realistic data augmentation and better translation quality. Our approach consistently achieves the best performance in comparison with strong and recent works and yields improvements of up to 1.90 BLEU points over the baseline.
The design choices in the Transformer attention mechanism, including weak inductive bias and quadratic computational complexity, have limited its application for modeling long sequences. In this paper, we introduce Mega, a simple, theoretically grounded, single-head gated attention mechanism equipped with (exponential) moving average to incorporate inductive bias of position-aware local dependencies into the position-agnostic attention mechanism. We further propose a variant of Mega that offers linear time and space complexity yet yields only minimal quality loss, by efficiently splitting the whole sequence into multiple chunks with fixed length. Extensive experiments on a wide range of sequence modeling benchmarks, including the Long Range Arena, neural machine translation, auto-regressive language modeling, and image and speech classification, show that Mega achieves significant improvements over other sequence models, including variants of Transformers and recent state space models.
Incorporating personal preference is crucial in advanced machine translation tasks. Despite the recent advancement of machine translation, it remains a demanding task to properly reflect personal style. In this paper, we introduce a personalized automatic post-editing framework to address this challenge, which effectively generates sentences considering distinct personal behaviors. To build this framework, we first collect post-editing data that connotes the user preference from a live machine translation system. Specifically, real-world users enter source sentences for translation and edit the machine-translated outputs according to the user's preferred style. We then propose a model that combines a discriminator module and user-specific parameters on the APE framework. Experimental results show that the proposed method outperforms other baseline models on four different metrics (i.e., BLEU, TER, YiSi-1, and human evaluation).
We describe the JD Explore Academy's submission of the WMT 2022 shared general translation task. We participated in all high-resource tracks and one medium-resource track, including Chinese-English, German-English, Czech-English, Russian-English, and Japanese-English. We push the limit of our previous work -- bidirectional training for translation by scaling up two main factors, i.e. language pairs and model sizes, namely the \textbf{Vega-MT} system. As for language pairs, we scale the "bidirectional" up to the "multidirectional" settings, covering all participating languages, to exploit the common knowledge across languages, and transfer them to the downstream bilingual tasks. As for model sizes, we scale the Transformer-Big up to the extremely large model that owns nearly 4.7 Billion parameters, to fully enhance the model capacity for our Vega-MT. Also, we adopt the data augmentation strategies, e.g. cycle translation for monolingual data, and bidirectional self-training for bilingual and monolingual data, to comprehensively exploit the bilingual and monolingual data. To adapt our Vega-MT to the general domain test set, generalization tuning is designed. Based on the official automatic scores of constrained systems, in terms of the sacreBLEU shown in Figure-1, we got the 1st place on {Zh-En (33.5), En-Zh (49.7), De-En (33.7), En-De (37.8), Cs-En (54.9), En-Cs (41.4) and En-Ru (32.7)}, 2nd place on {Ru-En (45.1) and Ja-En (25.6)}, and 3rd place on {En-Ja(41.5)}, respectively; W.R.T the COMET, we got the 1st place on {Zh-En (45.1), En-Zh (61.7), De-En (58.0), En-De (63.2), Cs-En (74.7), Ru-En (64.9), En-Ru (69.6) and En-Ja (65.1)}, 2nd place on {En-Cs (95.3) and Ja-En (40.6)}, respectively.
We present the first neural machine translation system for translation between the endangered Erzya language and Russian and the dataset collected by us to train and evaluate it. The BLEU scores are 17 and 19 for translation to Erzya and Russian respectively, and more than half of the translations are rated as acceptable by native speakers. We also adapt our model to translate between Erzya and 10 other languages, but without additional parallel data, the quality on these directions remains low. We release the translation models along with the collected text corpus, a new language identification model, and a multilingual sentence encoder adapted for the Erzya language. These resources will be available at https://github.com/slone-nlp/myv-nmt.
The powerful modeling capabilities of all-attention-based transformer architectures often cause overfitting and - for natural language processing tasks - lead to an implicitly learned internal language model in the autoregressive transformer decoder complicating the integration of external language models. In this paper, we explore relaxed attention, a simple and easy-to-implement smoothing of the attention weights, yielding a two-fold improvement to the general transformer architecture: First, relaxed attention provides regularization when applied to the self-attention layers in the encoder. Second, we show that it naturally supports the integration of an external language model as it suppresses the implicitly learned internal language model by relaxing the cross attention in the decoder. We demonstrate the benefit of relaxed attention across several tasks with clear improvement in combination with recent benchmark approaches. Specifically, we exceed the former state-of-the-art performance of 26.90% word error rate on the largest public lip-reading LRS3 benchmark with a word error rate of 26.31%, as well as we achieve a top-performing BLEU score of 37.67 on the IWSLT14 (DE$\rightarrow$EN) machine translation task without external language models and virtually no additional model parameters. Code and models will be made publicly available.
Efficiency is a key property to foster inclusiveness and reduce environmental costs, especially in an era of LLMs. In this work, we provide a comprehensive evaluation of efficiency for MT evaluation metrics. Our approach involves replacing computation-intensive transformers with lighter alternatives and employing linear and quadratic approximations for alignment algorithms on top of LLM representations. We evaluate six (reference-free and reference-based) metrics across three MT datasets and examine 16 lightweight transformers. In addition, we look into the training efficiency of metrics like COMET by utilizing adapters. Our results indicate that (a) TinyBERT provides the optimal balance between quality and efficiency, (b) CPU speed-ups are more substantial than those on GPU; (c) WMD approximations yield no efficiency gains while reducing quality and (d) adapters enhance training efficiency (regarding backward pass speed and memory requirements) as well as, in some cases, metric quality. These findings can help to strike a balance between evaluation speed and quality, which is essential for effective NLG systems. Furthermore, our research contributes to the ongoing efforts to optimize NLG evaluation metrics with minimal impact on performance. To our knowledge, ours is the most comprehensive analysis of different aspects of efficiency for MT metrics conducted so far.
We present LINGUIST, a method for generating annotated data for Intent Classification and Slot Tagging (IC+ST), via fine-tuning AlexaTM 5B, a 5-billion-parameter multilingual sequence-to-sequence (seq2seq) model, on a flexible instruction prompt. In a 10-shot novel intent setting for the SNIPS dataset, LINGUIST surpasses state-of-the-art approaches (Back-Translation and Example Extrapolation) by a wide margin, showing absolute improvement for the target intents of +1.9 points on IC Recall and +2.5 points on ST F1 Score. In the zero-shot cross-lingual setting of the mATIS++ dataset, LINGUIST out-performs a strong baseline of Machine Translation with Slot Alignment by +4.14 points absolute on ST F1 Score across 6 languages, while matching performance on IC. Finally, we verify our results on an internal large-scale multilingual dataset for conversational agent IC+ST and show significant improvements over a baseline which uses Back-Translation, Paraphrasing and Slot Catalog Resampling. To our knowledge, we are the first to demonstrate instruction fine-tuning of a large-scale seq2seq model to control the outputs of multilingual intent- and slot-labeled data generation.
We present in this article what we believe to be one of the first attempts at video game machine translation. Our study shows that models trained only with limited in-domain data surpass publicly available systems by a significant margin, and a subsequent human evaluation reveals interesting findings in the final translation. The first part of the article introduces some of the challenges of video game translation, some of the existing literature, as well as the systems and data sets used in this experiment. The last sections discuss our analysis of the resulting translation and the potential benefits of such an automated system. One such finding highlights the model's ability to learn typical rules and patterns of video game translations from English into French. Our conclusions therefore indicate that the specific case of video game machine translation could prove very much useful given the encouraging results, the highly repetitive nature of the work, and the often poor working conditions that translators face in this field. As with other use cases of MT in cultural sectors, however, we believe this is heavily dependent on the proper implementation of the tool, which should be used interactively by human translators to stimulate creativity instead of raw post-editing for the sake of productivity.
K-Nearest Neighbor Neural Machine Translation (kNN-MT) successfully incorporates external corpus by retrieving word-level representations at test time. Generally, kNN-MT borrows the off-the-shelf context representation in the translation task, e.g., the output of the last decoder layer, as the query vector of the retrieval task. In this work, we highlight that coupling the representations of these two tasks is sub-optimal for fine-grained retrieval. To alleviate it, we leverage supervised contrastive learning to learn the distinctive retrieval representation derived from the original context representation. We also propose a fast and effective approach to constructing hard negative samples. Experimental results on five domains show that our approach improves the retrieval accuracy and BLEU score compared to vanilla kNN-MT.
Multiword expression (MWE) is a sequence of words which collectively present a meaning which is not derived from its individual words. The task of processing MWEs is crucial in many natural language processing (NLP) applications, including machine translation and terminology extraction. Therefore, detecting MWEs in different domains is an important research topic. In this paper, we explore state-of-the-art neural transformers in the task of detecting MWEs in flower and plant names. We evaluate different transformer models on a dataset created from Encyclopedia of Plants and Flower. We empirically show that transformer models outperform the previous neural models based on long short-term memory (LSTM).
Automatic post-editing (APE) aims to reduce manual post-editing efforts by automatically correcting errors in machine-translated output. Due to the limited amount of human-annotated training data, data scarcity is one of the main challenges faced by all APE systems. To alleviate the lack of genuine training data, most of the current APE systems employ data augmentation methods to generate large-scale artificial corpora. In view of the importance of data augmentation in APE, we separately study the impact of the construction method of artificial corpora and artificial data domain on the performance of APE models. Moreover, the difficulty of APE varies between different machine translation (MT) systems. We study the outputs of the state-of-art APE model on a difficult APE dataset to analyze the problems in existing APE systems. Primarily, we find that 1) Artificial corpora with high-quality source text and machine-translated text more effectively improve the performance of APE models; 2) In-domain artificial training data can better improve the performance of APE models, while irrelevant out-of-domain data actually interfere with the model; 3) Existing APE model struggles with cases containing long source text or high-quality machine-translated text; 4) The state-of-art APE model works well on grammatical and semantic addition problems, but the output is prone to entity and semantic omission errors.
Automatic evaluation on low-resource language translation suffers from a deficiency of parallel corpora. Round-trip translation could be served as a clever and straightforward technique to alleviate the requirement of the parallel evaluation corpus. However, there was an observation of obscure correlations between the evaluation scores by forward and round-trip translations in the era of statistical machine translation (SMT). In this paper, we report the surprising finding that round-trip translation can be used for automatic evaluation without the references. Firstly, our revisit on the round-trip translation in SMT evaluation unveils that its long-standing misunderstanding is essentially caused by copying mechanism. After removing copying mechanism in SMT, round-trip translation scores can appropriately reflect the forward translation performance. Then, we demonstrate the rectification is overdue as round-trip translation could benefit multiple machine translation evaluation tasks. To be more specific, round-trip translation could be used i) to predict corresponding forward translation scores; ii) to improve the performance of the recently advanced quality estimation model; and iii) to identify adversarial competitors in shared tasks via cross-system verification.
Pre-trained language models (PLMs) often take advantage of the monolingual and multilingual dataset that is freely available online to acquire general or mixed domain knowledge before deployment into specific tasks. Extra-large PLMs (xLPLMs) are proposed very recently to claim supreme performances over smaller-sized PLMs such as in machine translation (MT) tasks. These xLPLMs include Meta-AI's wmt21-dense-24-wide-en-X (2021) and NLLB (2022). In this work, we examine if xLPLMs are absolutely superior to smaller-sized PLMs in fine-tuning toward domain-specific MTs. We use two different in-domain data of different sizes: commercial automotive in-house data and clinical shared task data from the ClinSpEn2022 challenge at WMT2022. We choose popular Marian Helsinki as smaller sized PLM and two massive-sized Mega-Transformers from Meta-AI as xLPLMs. Our experimental investigation shows that 1) on smaller-sized in-domain commercial automotive data, xLPLM wmt21-dense-24-wide-en-X indeed shows much better evaluation scores using SacreBLEU and hLEPOR metrics than smaller-sized Marian, even though its score increase rate is lower than Marian after fine-tuning; 2) on relatively larger-size well prepared clinical data fine-tuning, the xLPLM NLLB tends to lose its advantage over smaller-sized Marian on two sub-tasks (clinical terms and ontology concepts) using ClinSpEn offered metrics METEOR, COMET, and ROUGE-L, and totally lost to Marian on Task-1 (clinical cases) on all official metrics including SacreBLEU and BLEU; 3) metrics do not always agree with each other on the same tasks using the same model outputs; 4) clinic-Marian ranked No.2 on Task- 1 (via SACREBLEU/BLEU) and Task-3 (via METEOR and ROUGE) among all submissions.