Crosslingual Optimized Metric for Translation Assessment of Indian Languages

• URL: http://arxiv.org/abs/2509.17667v1
• Date: Mon, 22 Sep 2025 12:11:42 GMT
• Title: Crosslingual Optimized Metric for Translation Assessment of Indian Languages
• Authors: Arafat Ahsan, Vandan Mujadia, Pruthwik Mishra, Yash Bhaskar, Dipti Misra Sharma,
• Abstract summary: We create a large human evaluation ratings dataset for 13 Indian languages covering 21 translation directions.<n>We then train a neural translation evaluation metric named Cross-lingual Optimized Metric for Translation Assessment of Indian Languages (COMTAIL) on this dataset.<n>The best performing metric variants show significant performance gains over previous state-of-the-art when adjudging translation pairs with at least one Indian language.
• Score: 3.3904531496305683
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Automatic evaluation of translation remains a challenging task owing to the orthographic, morphological, syntactic and semantic richness and divergence observed across languages. String-based metrics such as BLEU have previously been extensively used for automatic evaluation tasks, but their limitations are now increasingly recognized. Although learned neural metrics have helped mitigate some of the limitations of string-based approaches, they remain constrained by a paucity of gold evaluation data in most languages beyond the usual high-resource pairs. In this present work we address some of these gaps. We create a large human evaluation ratings dataset for 13 Indian languages covering 21 translation directions and then train a neural translation evaluation metric named Cross-lingual Optimized Metric for Translation Assessment of Indian Languages (COMTAIL) on this dataset. The best performing metric variants show significant performance gains over previous state-of-the-art when adjudging translation pairs with at least one Indian language. Furthermore, we conduct a series of ablation studies to highlight the sensitivities of such a metric to changes in domain, translation quality, and language groupings. We release both the COMTAIL dataset and the accompanying metric models.

Related papers

• Beyond Literal Mapping: Benchmarking and Improving Non-Literal Translation Evaluation [57.11989521509119]
  We propose a novel agentic translation evaluation framework, centered by a reflective Core Agent that invokes specialized sub-agents.<n> Experimental results indicate the efficacy of RATE, achieving an improvement of at least 3.2 meta score compared with current metrics.
  arXiv  Detail & Related papers  (2026-01-12T09:03:42Z)
• Revisiting Metric Reliability for Fine-grained Evaluation of Machine Translation and Summarization in Indian Languages [13.098470937627871]
  ITEM systematically evaluates the alignment of 26 automatic metrics with human judgments across six major Indian languages.<n>Findings offer critical guidance for advancing metric design and evaluation in Indian languages.
  arXiv  Detail & Related papers  (2025-10-08T14:27:02Z)
• Low-Resource English-Tigrinya MT: Leveraging Multilingual Models, Custom Tokenizers, and Clean Evaluation Benchmarks [6.177998679139308]
  Despite advances in Neural Machine Translation (NMT), low-resource languages like Tigrinya remain underserved.<n>This paper investigates transfer learning techniques using multilingual pretrained models to enhance translation quality for morphologically rich, low-resource languages.
  arXiv  Detail & Related papers  (2025-09-24T15:02:57Z)
• Beyond N-Grams: Rethinking Evaluation Metrics and Strategies for Multilingual Abstractive Summarization [13.458891794688551]
  We assess evaluation metrics for generation both n-gram-based and neural based to evaluate their effectiveness across languages and tasks.<n>Our findings highlight the sensitivity of evaluation metrics to the language type.
  arXiv  Detail & Related papers  (2025-07-11T06:44:52Z)
• Investigating and Scaling up Code-Switching for Multilingual Language Model Pre-Training [58.696660064190475]
  We find that the existence of code-switching, alternating between different languages within a context, is key to multilingual capabilities.<n>To better explore the power of code-switching for language alignment during pre-training, we investigate the strategy of synthetic code-switching.
  arXiv  Detail & Related papers  (2025-04-02T15:09:58Z)
• Multilingual Coreference Resolution in Low-resource South Asian Languages [36.31301773167754]
  We introduce a Translated dataset for Multilingual Coreference Resolution (TransMuCoRes) in 31 South Asian languages. Nearly all of the predicted translations successfully pass a sanity check, and 75% of English references align with their predicted translations. This study is the first to evaluate an end-to-end coreference resolution model on a Hindi golden set.
  arXiv  Detail & Related papers  (2024-02-21T07:05:51Z)
• Machine Translation Meta Evaluation through Translation Accuracy Challenge Sets [92.38654521870444]
  We introduce ACES, a contrastive challenge set spanning 146 language pairs. This dataset aims to discover whether metrics can identify 68 translation accuracy errors. We conduct a large-scale study by benchmarking ACES on 50 metrics submitted to the WMT 2022 and 2023 metrics shared tasks.
  arXiv  Detail & Related papers  (2024-01-29T17:17:42Z)
• Optimal Transport Posterior Alignment for Cross-lingual Semantic Parsing [68.47787275021567]
  Cross-lingual semantic parsing transfers parsing capability from a high-resource language (e.g., English) to low-resource languages with scarce training data. We propose a new approach to cross-lingual semantic parsing by explicitly minimizing cross-lingual divergence between latent variables using Optimal Transport.
  arXiv  Detail & Related papers  (2023-07-09T04:52:31Z)
• DEMETR: Diagnosing Evaluation Metrics for Translation [21.25704103403547]
  We release DEMETR, a diagnostic dataset with 31K English examples. We find that learned metrics perform substantially better than string-based metrics on DEMETR.
  arXiv  Detail & Related papers  (2022-10-25T03:25:44Z)
• On Cross-Lingual Retrieval with Multilingual Text Encoders [51.60862829942932]
  We study the suitability of state-of-the-art multilingual encoders for cross-lingual document and sentence retrieval tasks. We benchmark their performance in unsupervised ad-hoc sentence- and document-level CLIR experiments. We evaluate multilingual encoders fine-tuned in a supervised fashion (i.e., we learn to rank) on English relevance data in a series of zero-shot language and domain transfer CLIR experiments.
  arXiv  Detail & Related papers  (2021-12-21T08:10:27Z)
• Does Summary Evaluation Survive Translation to Other Languages? [0.0]
  We translate an existing English summarization dataset, SummEval dataset, to four different languages. We analyze the scores from the automatic evaluation metrics in translated languages, as well as their correlation with human annotations in the source language.
  arXiv  Detail & Related papers  (2021-09-16T17:35:01Z)
• AM2iCo: Evaluating Word Meaning in Context across Low-ResourceLanguages with Adversarial Examples [51.048234591165155]
  We present AM2iCo, Adversarial and Multilingual Meaning in Context. It aims to faithfully assess the ability of state-of-the-art (SotA) representation models to understand the identity of word meaning in cross-lingual contexts. Results reveal that current SotA pretrained encoders substantially lag behind human performance.
  arXiv  Detail & Related papers  (2021-04-17T20:23:45Z)
• XL-WiC: A Multilingual Benchmark for Evaluating Semantic Contextualization [98.61159823343036]
  We present the Word-in-Context dataset (WiC) for assessing the ability to correctly model distinct meanings of a word. We put forward a large multilingual benchmark, XL-WiC, featuring gold standards in 12 new languages. Experimental results show that even when no tagged instances are available for a target language, models trained solely on the English data can attain competitive performance.
  arXiv  Detail & Related papers  (2020-10-13T15:32:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.