Alignment with human preferences is an important step in developing accurate and safe large language models. This is no exception in machine translation (MT), where better handling of language nuances and context-specific variations leads to improved quality. However, preference data based on human feedback can be very expensive to obtain and curate at a large scale. Automatic metrics, on the other hand, can induce preferences, but they might not match human expectations perfectly. In this paper, we propose an approach that leverages the best of both worlds. We first collect sentence-level quality assessments from professional linguists on translations generated by multiple high-quality MT systems and evaluate the ability of current automatic metrics to recover these preferences. We then use this analysis to curate a new dataset, MT-Pref (metric induced translation preference) dataset, which comprises 18k instances covering 18 language directions, using texts sourced from multiple domains post-2022. We show that aligning TOWER models on MT-Pref significantly improves translation quality on WMT23 and FLORES benchmarks.

Despite the recent success of automatic metrics for assessing translation quality, their application in evaluating the quality of machine-translated chats has been limited. Unlike more structured texts like news, chat conversations are often unstructured, short, and heavily reliant on contextual information. This poses questions about the reliability of existing sentence-level metrics in this domain as well as the role of context in assessing the translation quality. Motivated by this, we conduct a meta-evaluation of existing automatic metrics, primarily designed for structured domains such as news, to assess the quality of machine-translated chats. We find that reference-free metrics lag behind reference-based ones, especially when evaluating translation quality in out-of-English settings. We then investigate how incorporating conversational contextual information in these metrics for sentence-level evaluation affects their performance. Our findings show that augmenting neural learned metrics with contextual information helps improve correlation with human judgments in the reference-free scenario and when evaluating translations in out-of-English settings. Finally, we propose a new evaluation metric, Context-MQM, that utilizes bilingual context with a large language model (LLM) and further validate that adding context helps even for LLM-based evaluation metrics.

Reinforcement learning from human feedback (RLHF) is a recent technique to improve the quality of the text generated by a language model, making it closer to what humans would generate.A core ingredient in RLHF’s success in aligning and improving large language models (LLMs) is its reward model, trained using human feedback on model outputs. In machine translation (MT), where metrics trained from human annotations can readily be used as reward models, recent methods using minimum Bayes risk decoding and reranking have succeeded in improving the final quality of translation.In this study, we comprehensively explore and compare techniques for integrating quality metrics as reward models into the MT pipeline. This includes using the reward model for data filtering, during the training phase through RL, and at inference time by employing reranking techniques, and we assess the effects of combining these in a unified approach.Our experimental results, conducted across multiple translation tasks, underscore the crucial role of effective data filtering, based on estimated quality, in harnessing the full potential of RL in enhancing MT quality.Furthermore, our findings demonstrate the effectiveness of combining RL training with reranking techniques, showcasing substantial improvements in translation quality.

This paper describes CMU’s submission to the IWSLT 2024 Simultaneous Speech Translation (SST) task for translating English speech to German text in a streaming manner. Our end-to-end speech-to-text (ST) system integrates the WavLM speech encoder, a modality adapter, and the Llama2-7B-Base model as the decoder. We employ a two-stage training approach: initially, we align the representations of speech and text, followed by full fine-tuning. Both stages are trained on MuST-c v2 data with cross-entropy loss. We adapt our offline ST model for SST using a simple fixed hold-n policy. Experiments show that our model obtains an offline BLEU score of 31.1 and a BLEU score of 29.5 under 2 seconds latency on the MuST-C-v2 tst-COMMON.

This work describes CMU’s submission to the IWSLT 2024 Offline Speech Translation (ST) Shared Task for translating English speech to German, Chinese, and Japanese text. We are the first participants to employ a long-form strategy which directly processes unsegmented recordings without the need for a separate voice-activity detection stage (VAD). We show that the Whisper automatic speech recognition (ASR) model has a hallucination problem when applied out-of-the-box to recordings containing non-speech noises, but a simple noisy fine-tuning approach can greatly enhance Whisper’s long-form robustness across multiple domains. Then, we feed English ASR outputs into fine-tuned NLLB machine translation (MT) models which are decoded using COMET-based Minimum Bayes Risk. Our VAD-free ASR+MT cascade is tested on TED talks, TV series, and workout videos and shown to outperform prior winning IWSLT submissions and large open-source models.

In this work, we present Tower v2, an improved iteration of the state-of-the-art open-weight Tower models, and the backbone of our submission to the WMT24 General Translation shared task. Tower v2 introduces key improvements including expanded language coverage, enhanced data quality, and increased model capacity up to 70B parameters. Our final submission combines these advancements with quality-aware decoding strategies, selecting translations based on multiple translation quality signals. The resulting system demonstrates significant improvement over previous versions, outperforming closed commercial systems like GPT-4o, Claude 3.5, and DeepL even at a smaller 7B scale.

Although proper handling of discourse significantly contributes to the quality of machine translation (MT), these improvements are not adequately measured in common translation quality metrics. Recent works in context-aware MT attempt to target a small set of discourse phenomena during evaluation, however not in a fully systematic way. In this paper, we develop the Multilingual Discourse-Aware (MuDA) benchmark, a series of taggers that identify and evaluate model performance on discourse phenomena in any given dataset. The choice of phenomena is inspired by a novel methodology to systematically identify translations that require context. This methodology confirms the difficulty of previously studied phenomena while uncovering others which were not previously addressed. We find that commonly studied context-aware MT models make only marginal improvements over context-agnostic models, which suggests these models do not handle these ambiguities effectively. We release code and data for 14 language pairs to encourage the MT community to focus on accurately capturing discourse phenomena. Code available at https://github.com/neulab/contextual-mt

ESPnet-ST-v2 is a revamp of the open-source ESPnet-ST toolkit necessitated by the broadening interests of the spoken language translation community. ESPnet-ST-v2 supports 1) offline speech-to-text translation (ST), 2) simultaneous speech-to-text translation (SST), and 3) offline speech-to-speech translation (S2ST) – each task is supported with a wide variety of approaches, differentiating ESPnet-ST-v2 from other open source spoken language translation toolkits. This toolkit offers state-of-the-art architectures such as transducers, hybrid CTC/attention, multi-decoders with searchable intermediates, time-synchronous blockwise CTC/attention, Translatotron models, and direct discrete unit models. In this paper, we describe the overall design, example models for each task, and performance benchmarking behind ESPnet-ST-v2, which is publicly available at https://github.com/espnet/espnet.

Recent works on tokenizer-free multilingual pretrained models show promising results in improving cross-lingual transfer and reducing engineering overhead compared to subword-based alternatives. However, previous work mainly focuses on reporting accuracy on a limited set of tasks and data settings, placing less emphasis on other important factors when tuning and deploying the models in practice, such as memory usage, inference speed, and finetuning data efficiency. We attempt to fill this gap by performing a comprehensive empirical comparison of multilingual tokenizer-free and subword-based models considering the various dimensions. Surprisingly, we find that subword-based models might still be the most practical choice in many settings, achieving better performance for lower inference latency and memory usage. Based on these results, we encourage future work in tokenizer-free methods to consider these factors when designing and evaluating new models.

Evaluation of natural language generation (NLG) is complex and multi-dimensional. Generated text can be evaluated for fluency, coherence, factuality, or any other dimensions of interest. Most frameworks that perform such multi-dimensional evaluation require training on large manually or synthetically generated datasets. In this paper, we study the efficacy of large language models as multi-dimensional evaluators using in-context learning, obviating the need for large training datasets. Our experiments show that in-context learning-based evaluators are competitive with learned evaluation frameworks for the task of text summarization, establishing state-of-the-art on dimensions such as relevance and factual consistency. We then analyze the effects of factors such as the selection and number of in-context examples on performance. Finally, we study the efficacy of in-context learning-based evaluators in evaluating zero-shot summaries written by large language models such as GPT-3.

Recent advances in machine translation (MT) have shown that Minimum Bayes Risk (MBR) decoding can be a powerful alternative to beam search decoding, especially when combined with neural-based utility functions. However, the performance of MBR decoding depends heavily on how and how many candidates are sampled from the model. In this paper, we explore how different sampling approaches for generating candidate lists for MBR decoding affect performance. We evaluate popular sampling approaches, such as ancestral, nucleus, and top-k sampling. Based on our insights into their limitations, we experiment with the recently proposed epsilon-sampling approach, which prunes away all tokens with a probability smaller than epsilon, ensuring that each token in a sample receives a fair probability mass. Through extensive human evaluations, we demonstrate that MBR decoding based on epsilon-sampling significantly outperforms not only beam search decoding, but also MBR decoding with all other tested sampling methods across four language pairs.

Natural language generation has witnessed significant advancements due to the training of large language models on vast internet-scale datasets. Despite these advancements, there exists a critical challenge: These models can inadvertently generate content that is toxic, inaccurate, and unhelpful, and existing automatic evaluation metrics often fall short of identifying these shortcomings. As models become more capable, human feedback is an invaluable signal for evaluating and improving models. This survey aims to provide an overview of recent research that has leveraged human feedback to improve natural language generation. First, we introduce a taxonomy distilled from existing research to categorize and organize the varied forms of feedback. Next, we discuss how feedback can be described by its format and objective, and cover the two approaches proposed to use feedback (either for training or decoding): directly using feedback or training feedback models. We also discuss existing datasets for human-feedback data collection, and concerns surrounding feedback collection. Finally, we provide an overview of the nascent field of AI feedback, which uses large language models to make judgments based on a set of principles and minimize the need for human intervention. We also release a website of this survey at feedback-gap-survey.info.

Automatic evaluation of machine translation (MT) is a critical tool driving the rapid iterative development of MT systems. While considerable progress has been made on estimating a single scalar quality score, current metrics lack the informativeness of more detailed schemes that annotate individual errors, such as Multidimensional Quality Metrics (MQM). In this paper, we help fill this gap by proposing AutoMQM, a prompting technique which leverages the reasoning and in-context learning capabilities of large language models (LLMs) and asks them to identify and categorize errors in translations. We start by evaluating recent LLMs, such as PaLM and PaLM-2, through simple score prediction prompting, and we study the impact of labeled data through in-context learning and finetuning. We then evaluate AutoMQM with PaLM-2 models, and we find that it improves performance compared to just prompting for scores (with particularly large gains for larger models) while providing interpretability through error spans that align with human annotations.

Despite the remarkable advancements in machine translation, the current sentence-level paradigm faces challenges when dealing with highly-contextual languages like Japanese. In this paper, we explore how context-awareness can improve the performance of the current Neural Machine Translation (NMT) models for English-Japanese business dialogues translation, and what kind of context provides meaningful information to improve translation. As business dialogue involves complex discourse phenomena but offers scarce training resources, we adapted a pretrained mBART model, finetuning on multi-sentence dialogue data, which allows us to experiment with different contexts. We investigate the impact of larger context sizes and propose novel context tokens encoding extra-sentential information, such as speaker turn and scene type. We make use of Conditional Cross-Mutual Information (CXMI) to explore how much of the context the model uses and generalise CXMI to study the impact of the extra sentential context. Overall, we find that models leverage both preceding sentences and extra-sentential context (with CXMI increasing with context size) and we provide a more focused analysis on honorifics translation. Regarding translation quality, increased source-side context paired with scene and speaker information improves the model performance compared to previous work and our context-agnostic baselines, measured in BLEU and COMET metrics.

Despite the progress in machine translation quality estimation and evaluation in the last years, decoding in neural machine translation (NMT) is mostly oblivious to this and centers around finding the most probable translation according to the model (MAP decoding), approximated with beam search. In this paper, we bring together these two lines of research and propose quality-aware decoding for NMT, by leveraging recent breakthroughs in reference-free and reference-based MT evaluation through various inference methods like N-best reranking and minimum Bayes risk decoding. We perform an extensive comparison of various possible candidate generation and ranking methods across four datasets and two model classes and find that quality-aware decoding consistently outperforms MAP-based decoding according both to state-of-the-art automatic metrics (COMET and BLEURT) and to human assessments.

Transformers’ quadratic complexity with respect to the input sequence length has motivated a body of work on efficient sparse approximations to softmax. An alternative path, used by entmax transformers, consists of having built-in exact sparse attention; however this approach still requires quadratic computation. In this paper, we propose Sparsefinder, a simple model trained to identify the sparsity pattern of entmax attention before computing it. We experiment with three variants of our method, based on distances, quantization, and clustering, on two tasks: machine translation (attention in the decoder) and masked language modeling (encoder-only). Our work provides a new angle to study model efficiency by doing extensive analysis of the tradeoff between the sparsity and recall of the predicted attention graph. This allows for detailed comparison between different models along their Pareto curves, important to guide future benchmarks for sparse attention models.

This paper reports the findings of the second edition of the Chat Translation Shared Task. Similarly to the previous WMT 2020 edition, the task consisted of translating bilingual customer support conversational text. However, unlike the previous edition, in which the bilingual data was created from a synthetic monolingual English corpus, this year we used a portion of the newly released Unbabel’s MAIA corpus, which contains genuine bilingual conversations between agents and customers. We also expanded the language pairs to English↔German (en↔de), English↔French (en↔fr), and English↔Brazilian Portuguese (en↔pt-br).Given that the main goal of the shared task is to translate bilingual conversations, participants were encouraged to train and test their models specifically for this environment. In total, we received 18 submissions from 4 different teams. All teams participated in both directions of en↔de. One of the teams also participated in en↔fr and en↔pt-br. We evaluated the submissions with automatic metrics as well as human judgments via Multidimensional Quality Metrics (MQM) on both directions. The official ranking of the systems is based on the overall MQM scores of the participating systems on both directions, i.e. agent and customer.

This paper describes CMU’s submissions to the IWSLT 2022 dialect speech translation (ST) shared task for translating Tunisian-Arabic speech to English text. We use additional paired Modern Standard Arabic data (MSA) to directly improve the speech recognition (ASR) and machine translation (MT) components of our cascaded systems. We also augment the paired ASR data with pseudo translations via sequence-level knowledge distillation from an MT model and use these artificial triplet ST data to improve our end-to-end (E2E) systems. Our E2E models are based on the Multi-Decoder architecture with searchable hidden intermediates. We extend the Multi-Decoder by orienting the speech encoder towards the target language by applying ST supervision as hierarchical connectionist temporal classification (CTC) multi-task. During inference, we apply joint decoding of the ST CTC and ST autoregressive decoder branches of our modified Multi-Decoder. Finally, we apply ROVER voting, posterior combination, and minimum bayes-risk decoding with combined N-best lists to ensemble our various cascaded and E2E systems. Our best systems reached 20.8 and 19.5 BLEU on test2 (blind) and test1 respectively. Without any additional MSA data, we reached 20.4 and 19.2 on the same test sets.

Context-aware machine translation models are designed to leverage contextual information, but often fail to do so. As a result, they inaccurately disambiguate pronouns and polysemous words that require context for resolution. In this paper, we ask several questions: What contexts do human translators use to resolve ambiguous words? Are models paying large amounts of attention to the same context? What if we explicitly train them to do so? To answer these questions, we introduce SCAT (Supporting Context for Ambiguous Translations), a new English-French dataset comprising supporting context words for 14K translations that professional translators found useful for pronoun disambiguation. Using SCAT, we perform an in-depth analysis of the context used to disambiguate, examining positional and lexical characteristics of the supporting words. Furthermore, we measure the degree of alignment between the model’s attention scores and the supporting context from SCAT, and apply a guided attention strategy to encourage agreement between the two.

Recent work in neural machine translation has demonstrated both the necessity and feasibility of using inter-sentential context, context from sentences other than those currently being translated. However, while many current methods present model architectures that theoretically can use this extra context, it is often not clear how much they do actually utilize it at translation time. In this paper, we introduce a new metric, conditional cross-mutual information, to quantify usage of context by these models. Using this metric, we measure how much document-level machine translation systems use particular varieties of context. We find that target context is referenced more than source context, and that including more context has a diminishing affect on results. We then introduce a new, simple training method, context-aware word dropout, to increase the usage of context by context-aware models. Experiments show that our method not only increases context usage, but also improves the translation quality according to metrics such as BLEU and COMET, as well as performance on anaphoric pronoun resolution and lexical cohesion contrastive datasets.