We introduce a new proxy score for evaluating bitext mining based on similarity in a multilingual embedding space: xSIM++. In comparison to xSIM, this improved proxy leverages rule-based approaches to extend English sentences in any evaluation set with synthetic, hard-to-distinguish examples which more closely mirror the scenarios we encounter during large-scale mining. We validate this proxy by running a significant number of bitext mining experiments for a set of low-resource languages, and subsequently train NMT systems on the mined data. In comparison to xSIM, we show that xSIM++ is better correlated with the downstream BLEU scores of translation systems trained on mined bitexts, providing a reliable proxy of bitext mining performance without needing to run expensive bitext mining pipelines. xSIM++ also reports performance for different error types, offering more fine-grained feedback for model development.

This paper gives an Indic-to-Indic (IL-IL) MNMT baseline model for 11 ILs implemented on the Samanantar corpus and analyzed on the Flores-200 corpus. All the models are evaluated using the BLEU score. In addition, the languages are classified under three groups namely East Indo- Aryan (EI), Dravidian (DR), and West Indo-Aryan (WI). The effect of language relatedness on MNMT model efficiency is studied. Owing to the presence of large corpora from English (EN) to ILs, MNMT IL-IL models using EN as a pivot are also built and examined. To achieve this, English- Indic (EN-IL) models are also developed, with and without the usage of related languages. Results reveal that using related languages is beneficial for the WI group only, while it is detrimental for the EI group and shows an inconclusive effect on the DR group, but it is useful for EN-IL models. Thus, related language groups are used to develop pivot MNMT models. Furthermore, the IL corpora are transliterated from the corresponding scripts to a modified ITRANS script, and the best MNMT models from the previous approaches are built on the transliterated corpus. It is observed that the usage of pivot models greatly improves MNMT baselines with AS-TA achieving the minimum BLEU score and PA-HI achieving the maximum score. Among languages, AS, ML, and TA achieve the lowest BLEU score, whereas HI, PA, and GU perform the best. Transliteration also helps the models with few exceptions. The best increment of scores is observed in ML, TA, and BN and the worst average increment is observed in KN, HI, and PA, across all languages. The best model obtained is the PA-HI language pair trained on PAWI transliterated corpus which gives 24.29 BLEU.

Lexically-constrained NMT (LNMT) aims to incorporate user-provided terminology into translations. Despite its practical advantages, existing work has not evaluated LNMT models under challenging real-world conditions. In this paper, we focus on two important but under-studied issues that lie in the current evaluation process of LNMT studies. The model needs to cope with challenging lexical constraints that are "homographs" or "unseen" during training. To this end, we first design a homograph disambiguation module to differentiate the meanings of homographs. Moreover, we propose PLUMCOT, which integrates contextually rich information about unseen lexical constraints from pre-trained language models and strengthens a copy mechanism of the pointer network via direct supervision of a copying score. We also release HOLLY, an evaluation benchmark for assessing the ability of a model to cope with "homographic" and "unseen" lexical constraints. Experiments on HOLLY and the previous test setup show the effectiveness of our method. The effects of PLUMCOT are shown to be remarkable in "unseen" constraints. Our dataset is available at https://github.com/papago-lab/HOLLY-benchmark

In this paper, we focus on how current Machine Translation (MT) tools perform on the translation of emotion-loaded texts by evaluating outputs from Google Translate according to a framework proposed in this paper. We propose this evaluation framework based on the Multidimensional Quality Metrics (MQM) and perform a detailed error analysis of the MT outputs. From our analysis, we observe that about 50% of the MT outputs fail to preserve the original emotion. After further analysis of the errors, we find that emotion carrying words and linguistic phenomena such as polysemous words, negation, abbreviation etc., are common causes for these translation errors.

Improving MT models requires continuously expanding their MT corpora for re-training cycles by post-editing their outputs on samples received from the production environment. Hence, the MT model lifecycle requires continuous human effort, which could scale and be more efficient by semi-automating it via machine-learning models trained by linguists. Those models can be used to select the maximally useful set of translations to store and post-edit by looking at what is challenging for an MT. They can upsample and prioritize translation outputs from where MTs are not performing well, and reduce costs by post-editing production translations intelligently. The continuous and interactive nature of the MT lifecycle provides the perfect ground for applying active-learning techniques in training those machine-learning models for semi-automation. Custom translation quality or post-editing effort estimation models trained on-the-fly as linguists post-edit translations can be used to prioritize samples accumulating from the model inferences in the production environment. The trained estimators enable to focus the linguist effort on the most challenging samples for the MT model requiring the most post-edits, which are also the most valuable to check for evaluating the MT model quality by humans. In the WMT20 Metrics Shared Task (Mathur et al., 2020), participants were asked to score MT outputs in the WMT20 News Translation Task with automatic metrics, and four referenceless metrics were submitted. Those metrics (OpenKiwi-BERT, OpenKiwi-XLMR, YISI-2, COMET-QE) use bilingual mappings of the contextual embeddings extracted from pre-trained or fine-tuned language models (like XLM-RoBERTa) to evaluate the cross-lingual lexical semantic similarity between the input and MT output.

This paper presents EvolveMT for efficiently combining multiple machine translation (MT) engines. The proposed system selects the output from a single engine for each segment by utilizing online learning techniques to predict the most suitable system for every translation request. A neural quality estimation metric supervises the method without requiring reference translations. The online learning capability of this system allows for dynamic adaptation to alterations in the domain or machine translation engines, thereby obviating the necessity for additional training. EvolveMT selects a subset of translation engines to be called based on the source sentence features. The degree of exploration is configurable according to the desired quality-cost trade-off. Results from custom datasets demonstrate that EvolveMT achieves similar translation accuracy at a lower cost than selecting the best translation of each segment from all translations using an MT quality estimator. To our knowledge, EvolveMT is the first meta MT system that adapts itself after deployment to incoming translation requests from the production environment without needing costly retraining on human feedback.

Recently, speech-to-text translation has attracted more and more attention and many studies have emerged rapidly. In this paper, we present a comprehensive survey on direct speech translation aiming to summarize the current state-of-the-art techniques. First, we categorize the existing research work into three directions based on the main challenges -- modeling burden, data scarcity, and application issues. To tackle the problem of modeling burden, two main structures have been proposed, encoder-decoder framework (Transformer and the variants) and multitask frameworks. For the challenge of data scarcity, recent work resorts to many sophisticated techniques, such as data augmentation, pre-training, knowledge distillation, and multilingual modeling. We analyze and summarize the application issues, which include real-time, segmentation, named entity, gender bias, and code-switching. Finally, we discuss some promising directions for future work.

Compositional generalization allows efficient learning and human-like inductive biases. Since most research investigating compositional generalization in NLP is done on English, important questions remain underexplored. Do the necessary compositional generalization abilities differ across languages? Can models compositionally generalize cross-lingually? As a first step to answering these questions, recent work used neural machine translation to translate datasets for evaluating compositional generalization in semantic parsing. However, we show that this entails critical semantic distortion. To address this limitation, we craft a faithful rule-based translation of the MCWQ dataset from English to Chinese and Japanese. Even with the resulting robust benchmark, which we call MCWQ-R, we show that the distribution of compositions still suffers due to linguistic divergences, and that multilingual models still struggle with cross-lingual compositional generalization. Our dataset and methodology will be useful resources for the study of cross-lingual compositional generalization in other tasks.

We introduce HK-LegiCoST, a new three-way parallel corpus of Cantonese-English translations, containing 600+ hours of Cantonese audio, its standard traditional Chinese transcript, and English translation, segmented and aligned at the sentence level. We describe the notable challenges in corpus preparation: segmentation, alignment of long audio recordings, and sentence-level alignment with non-verbatim transcripts. Such transcripts make the corpus suitable for speech translation research when there are significant differences between the spoken and written forms of the source language. Due to its large size, we are able to demonstrate competitive speech translation baselines on HK-LegiCoST and extend them to promising cross-corpus results on the FLEURS Cantonese subset. These results deliver insights into speech recognition and translation research in languages for which non-verbatim or ``noisy'' transcription is common due to various factors, including vernacular and dialectal speech.

Task-oriented dialogue (TOD) systems have been widely deployed in many industries as they deliver more efficient customer support. These systems are typically constructed for a single domain or language and do not generalise well beyond this. To support work on Natural Language Understanding (NLU) in TOD across multiple languages and domains simultaneously, we constructed MULTI3NLU++, a multilingual, multi-intent, multi-domain dataset. MULTI3NLU++ extends the English only NLU++ dataset to include manual translations into a range of high, medium, and low resource languages (Spanish, Marathi, Turkish and Amharic), in two domains (BANKING and HOTELS). Because of its multi-intent property, MULTI3NLU++ represents complex and natural user goals, and therefore allows us to measure the realistic performance of TOD systems in a varied set of the world's languages. We use MULTI3NLU++ to benchmark state-of-the-art multilingual models for the NLU tasks of intent detection and slot labelling for TOD systems in the multilingual setting. The results demonstrate the challenging nature of the dataset, particularly in the low-resource language setting, offering ample room for future experimentation in multi-domain multilingual TOD setups.