While vision-language pre-trained models (VL-PTMs) have advanced multimodal research in recent years, their mastery in a few languages like English restricts their applicability in broader communities. To this end, there is an increasing interest in developing multilingual VL models via a joint-learning setup, which, however, could be unrealistic due to expensive costs and data availability. In this work, we propose to extend VL-PTMs' language capacity by continual language learning (CLL), where a model needs to update its linguistic knowledge incrementally without suffering from catastrophic forgetting (CF). We begin our study by introducing a model dubbed CLL-CLIP, which builds upon CLIP, a prevailing VL-PTM that has acquired image-English text alignment. Specifically, CLL-CLIP contains an expandable token embedding layer to handle linguistic differences. It solely trains token embeddings to improve memory stability and is optimized under cross-modal and cross-lingual objectives to learn the alignment between images and multilingual texts. To alleviate CF raised by covariate shift and lexical overlap, we further propose a novel approach that ensures the identical distribution of all token embeddings during initialization and regularizes token embedding learning during training. We construct a CLL benchmark covering 36 languages based on MSCOCO and XM3600 datasets and then evaluate multilingual image-text retrieval performance. Extensive experiments verify the effectiveness of CLL-CLIP and show that our approach can boost CLL-CLIP, e.g., by 6.7% in text-to-image average Recall@1 on XM3600, and improve various state-of-the-art methods consistently. Our code and data are available at \url{https://github.com/yangbang18/CLFM}.

Traditionally, Machine Translation (MT) Evaluation has been treated as a regression problem--producing an absolute translation-quality score. This approach has two limitations: i) the scores lack interpretability, and human annotators struggle with giving consistent scores; ii) most scoring methods are based on (reference, translation) pairs, limiting their applicability in real-world scenarios where references are absent. In practice, we often care about whether a new MT system is better or worse than some competitors. In addition, reference-free MT evaluation is increasingly practical and necessary. Unfortunately, these two practical considerations have yet to be jointly explored. In this work, we formulate the reference-free MT evaluation into a pairwise ranking problem. Given the source sentence and a pair of translations, our system predicts which translation is better. In addition to proposing this new formulation, we further show that this new paradigm can demonstrate superior correlation with human judgments by merely using indirect supervision from natural language inference and weak supervision from our synthetic data. In the context of reference-free evaluation, MT-Ranker, trained without any human annotations, achieves state-of-the-art results on the WMT Shared Metrics Task benchmarks DARR20, MQM20, and MQM21. On a more challenging benchmark, ACES, which contains fine-grained evaluation criteria such as addition, omission, and mistranslation errors, MT-Ranker marks state-of-the-art against reference-free as well as reference-based baselines. Automatic MT evaluation is crucial to measure the progress of MT systems. Compared to human evaluation, automatic evaluation is much cheaper and less subjective.

In today's globalized world, bridging the cultural divide is more critical than ever for forging meaningful connections. The Socially-Aware Dialogue Assistant System (SADAS) is our answer to this global challenge, and it's designed to ensure that conversations between individuals from diverse cultural backgrounds unfold with respect and understanding. Our system's novel architecture includes: (1) identifying the categories of norms present in the dialogue, (2) detecting potential norm violations, (3) evaluating the severity of these violations, (4) implementing targeted remedies to rectify the breaches, and (5) articulates the rationale behind these corrective actions. We employ a series of State-Of-The-Art (SOTA) techniques to build different modules, and conduct numerous experiments to select the most suitable backbone model for each of the modules. We also design a human preference experiment to validate the overall performance of the system. We will open-source our system (including source code, tools and applications), hoping to advance future research. A demo video of our system can be found at:~\url{https://youtu.be/JqetWkfsejk}. We have released our code and software at:~\url{https://github.com/AnonymousEACLDemo/SADAS}.

Translation into severely low-resource languages has both the cultural goal of saving and reviving those languages and the humanitarian goal of assisting the everyday needs of local communities that are accelerated by the recent COVID-19 pandemic. In many humanitarian efforts, translation into severely low-resource languages often does not require a universal translation engine, but a dedicated text-specific translation engine. For example, healthcare records, hygienic procedures, government communication, emergency procedures and religious texts are all limited texts. While generic translation engines for all languages do not exist, translation of multilingually known limited texts into new, low-resource languages may be possible and reduce human translation effort. We attempt to leverage translation resources from rich-resource languages to efficiently produce best possible translation quality for well known texts, which are available in multiple languages, in a new, low-resource language. To reach this goal, we argue that in translating a closed text into low-resource languages, generalization to out-of-domain texts is not necessary, but generalization to new languages is. Performance gain comes from massive source parallelism by careful choice of close-by language families, style-consistent corpus-level paraphrases within the same language and strategic adaptation of existing large pretrained multilingual models to the domain first and then to the language. Such performance gain makes it possible for machine translation systems to collaborate with human translators to expedite the translation process into new, low-resource languages.

Recent machine translation (MT) metrics calibrate their effectiveness by correlating with human judgement but without any insights about their behaviour across different error types. Challenge sets are used to probe specific dimensions of metric behaviour but there are very few such datasets and they either focus on a limited number of phenomena or a limited number of language pairs. We introduce ACES, a contrastive challenge set spanning 146 language pairs, aimed at discovering whether metrics can identify 68 translation accuracy errors. These phenomena range from simple alterations at the word/character level to more complex errors based on discourse and real-world knowledge. We conduct a large-scale study by benchmarking ACES on 50 metrics submitted to the WMT 2022 and 2023 metrics shared tasks. We benchmark metric performance, assess their incremental performance over successive campaigns, and measure their sensitivity to a range of linguistic phenomena. We also investigate claims that Large Language Models (LLMs) are effective as MT evaluators by evaluating on ACES. Our results demonstrate that different metric families struggle with different phenomena and that LLM-based methods fail to demonstrate reliable performance. Our analyses indicate that most metrics ignore the source sentence, tend to prefer surface-level overlap and end up incorporating properties of base models which are not always beneficial. We expand ACES to include error span annotations, denoted as SPAN-ACES and we use this dataset to evaluate span-based error metrics showing these metrics also need considerable improvement. Finally, we provide a set of recommendations for building better MT metrics, including focusing on error labels instead of scores, ensembling, designing strategies to explicitly focus on the source sentence, focusing on semantic content and choosing the right base model for representations.

Assessing performance in Natural Language Processing is becoming increasingly complex. One particular challenge is the potential for evaluation datasets to overlap with training data, either directly or indirectly, which can lead to skewed results and overestimation of model performance. As a consequence, human evaluation is gaining increasing interest as a means to assess the performance and reliability of models. One such method is the red teaming approach, which aims to generate edge cases where a model will produce critical errors. While this methodology is becoming standard practice for generative AI, its application to the realm of conditional AI remains largely unexplored. This paper presents the first study on human-based red teaming for Machine Translation (MT), marking a significant step towards understanding and improving the performance of translation models. We delve into both human-based red teaming and a study on automation, reporting lessons learned and providing recommendations for both translation models and red teaming drills. This pioneering work opens up new avenues for research and development in the field of MT.

We introduce MultiMUC, the first multilingual parallel corpus for template filling, comprising translations of the classic MUC-4 template filling benchmark into five languages: Arabic, Chinese, Farsi, Korean, and Russian. We obtain automatic translations from a strong multilingual machine translation system and manually project the original English annotations into each target language. For all languages, we also provide human translations for sentences in the dev and test splits that contain annotated template arguments. Finally, we present baselines on MultiMUC both with state-of-the-art template filling models and with ChatGPT.

Abstract--When the amount of parallel sentences available to train a neural machine translation is scarce, a common practice is to generate new synthetic training samples from them. A number of approaches have been proposed to produce synthetic parallel sentences that are similar to those in the parallel data available. These approaches work under the assumption that non-fluent target-side synthetic training samples can be harmful and may deteriorate translation performance. Even so, in this paper we demonstrate that synthetic training samples with non-fluent target sentences can improve translation performance if they are used in a multilingual machine translation framework as if they were sentences in another language. We conducted experiments on ten low-resource and four high-resource translation tasks and found out that this simple approach consistently improves translation performance as compared to state-of-the-art methods for generating synthetic training samples similar to those found in corpora. Furthermore, this improvement is independent of the size of the original training corpus, the resulting systems are much more robust against domain shift and produce less hallucinations.

This paper studies the effects of word-level linguistic annotations in under-resourced neural machine translation, for which there is incomplete evidence in the literature. The study covers eight language pairs, different training corpus sizes, two architectures, and three types of annotation: dummy tags (with no linguistic information at all), part-of-speech tags, and morpho-syntactic description tags, which consist of part of speech and morphological features. These linguistic annotations are interleaved in the input or output streams as a single tag placed before each word. In order to measure the performance under each scenario, we use automatic evaluation metrics and perform automatic error classification. Our experiments show that, in general, source-language annotations are helpful and morpho-syntactic descriptions outperform part of speech for some language pairs. On the contrary, when words are annotated in the target language, part-of-speech tags systematically outperform morpho-syntactic description tags in terms of automatic evaluation metrics, even though the use of morpho-syntactic description tags improves the grammaticality of the output. We provide a detailed analysis of the reasons behind this result.

In learning-based functionality stealing, the attacker is trying to build a local model based on the victim's outputs. The attacker has to make choices regarding the local model's architecture, optimization method and, specifically for NLP models, subword vocabulary, such as BPE. On the machine translation task, we explore (1) whether the choice of the vocabulary plays a role in model stealing scenarios and (2) if it is possible to extract the victim's vocabulary. We find that the vocabulary itself does not have a large effect on the local model's performance. Given gray-box model access, it is possible to collect the victim's vocabulary by collecting the outputs (detokenized subwords on the output). The results of the minimum effect of vocabulary choice are important more broadly for black-box knowledge distillation.