This paper presents an evaluation of 16 machine translation systems submitted to the Shared Task of the 9th Conference of Machine Translation (WMT24) for the English-Hindi (en-hi) language pair using our Complex Structures Test (CoST) suite. Aligning with this year’s test suite sub-task theme, “Help us break LLMs”, we curated a comprehensive test suite encompassing diverse datasets across various categories, including autobiography, poetry, legal, conversation, play, narration, technical, and mixed genres. Our evaluation reveals that all the systems struggle significantly with the archaic style of text like legal and technical writings or text with creative twist like conversation and poetry datasets, highlighting their weaknesses in handling complex linguistic structures and stylistic nuances inherent in these text types. Our evaluation identifies the strengths and limitations of the submitted models, pointing to specific areas where further research and development are needed to enhance their performance. Our test suite is available at https://github.com/AnanyaCoder/CoST-WMT-24-Test-Suite-Task.

Machine translation (MT) evaluation metrics like BLEU and chrF++ are widely used reference-based metrics that do not require training and are language-independent. However, these metrics primarily focus on n-gram matching and often overlook semantic depth and contextual understanding. To address this gap, we introduce chrF-S (Semantic chrF++), an enhanced metric that integrates sentence embeddings to evaluate translation quality more comprehensively. By combining traditional character and word n-gram analysis with semantic information derived from embeddings, chrF-S captures both syntactic accuracy and sentence-level semantics. This paper presents our contributions to the WMT24 shared metrics task, showcasing our participation and the development of chrF-S. We also demonstrate that, according to preliminary results on the leaderboard, our metric performs on par with other supervised and LLM-based metrics. By merging semantic insights with n-gram precision, chrF-S offers a significant enhancement in the assessment of machine-generated translations, advancing the field of MT evaluation. Our code and data will be made available at https://github.com/AnanyaCoder/chrF-S.

Translating for languages with limited resources poses a persistent challenge due to the scarcity of high-quality training data. To enhance translation accuracy, we explored controlled generation mechanisms, focusing on the importance of control tokens. In our experiments, while training, we encoded the target sentence length as a control token to the source sentence, treating it as an additional feature for the source sentence. We developed various NMT models using transformer architecture and conducted experiments across 8 language directions (English = Assamese, Manipuri, Khasi, and Mizo), exploring four variations of length encoding mechanisms. Through comparative analysis against the baseline model, we submitted two systems for each language direction. We report our findings for the same in this work.

In this report, we share our contribution to the Eval4NLP Shared Task titled “Prompting Large Language Models as Explainable Metrics.” We build our prompts with a primary focus on effective prompting strategies, score-aggregation, and explainability for LLM-based metrics. We participated in the track for smaller models by submitting the scores along with their explanations. According to the Kendall correlation scores on the leaderboard, our MT evaluation submission ranks second-best, while our summarization evaluation submission ranks fourth, with only a 0.06 difference from the leading submission.

This paper summarizes the results of our test suite evaluation on 12 machine translation systems submitted at the Shared Task of the 8th Conference of Machine Translation (WMT23) for English-German (en-de) language pair. Our test suite covers five specific domains (entertainment, environment, health, science, legal) and spans five distinct writing styles (descriptive, judgments, narrative, reporting, technical-writing). We present our analysis through automatic evaluation methods, conducted with a focus on domain-specific and writing style-specific evaluations.

This paper presents our contributions to the WMT2023 shared metrics task, consisting of two distinct evaluation approaches: a) Unsupervised Metric (MEE4) and b) Supervised Metric (XLSim). MEE4 represents an unsupervised, reference-based assessment metric that quantifies linguistic features, encompassing lexical, syntactic, semantic, morphological, and contextual similarities, leveraging embeddings. In contrast, XLsim is a supervised reference-based evaluation metric, employing a Siamese Architecture, which regresses on Direct Assessments (DA) from previous WMT News Translation shared tasks from 2017-2022. XLsim is trained using XLM-RoBERTa (base) on English-German reference and mt pairs with human scores.

In this paper, we describe our submission to the WMT22 metrics shared task. Our metric focuses on computing contextual and syntactic equivalences along with lexical, morphological, and semantic similarity. The intent is to capture the fluency and context of the MT outputs along with their adequacy. Fluency is captured using syntactic similarity and context is captured using sentence similarity leveraging sentence embeddings. The final sentence translation score is the weighted combination of three similarity scores: a) Syntactic Similarity b) Lexical, Morphological and Semantic Similarity, and c) Contextual Similarity. This paper outlines two improved versions of MEE i.e., MEE2 and MEE4. Additionally, we report our experiments on language pairs of en-de, en-ru and zh-en from WMT17-19 testset and further depict the correlation with human assessments.

This paper describes our submission to the WMT2022 shared metrics task. Our unsupervised metric estimates the translation quality at chunk-level and sentence-level. Source and target sentence chunks are retrieved by using a multi-lingual chunker. The chunk-level similarity is computed by leveraging BERT contextual word embeddings and sentence similarity scores are calculated by leveraging sentence embeddings of Language-Agnostic BERT models. The final quality estimation score is obtained by mean pooling the chunk-level and sentence-level similarity scores. This paper outlines our experiments and also reports the correlation with human judgements for en-de, en-ru and zh-en language pairs of WMT17, WMT18 and WMT19 test sets.