Don't Rank, Combine! Combining Machine Translation Hypotheses Using Quality Estimation

• URL: http://arxiv.org/abs/2401.06688v2
• Date: Thu, 6 Jun 2024 17:45:39 GMT
• Title: Don't Rank, Combine! Combining Machine Translation Hypotheses Using Quality Estimation
• Authors: Giorgos Vernikos, Andrei Popescu-Belis,
• Abstract summary: This work introduces QE-fusion, a method that synthesizes translations using a quality estimation metric (QE) We demonstrate that our approach generates novel translations in over half of the cases. We empirically establish that QE-fusion scales linearly with the number of candidates in the pool.
• Score: 0.6998085564793366
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Neural machine translation systems estimate probabilities of target sentences given source sentences, yet these estimates may not align with human preferences. This work introduces QE-fusion, a method that synthesizes translations using a quality estimation metric (QE), which correlates better with human judgments. QE-fusion leverages a pool of candidates sampled from a model, combining spans from different candidates using a QE metric such as CometKiwi. We compare QE-fusion against beam search and recent reranking techniques, such as Minimum Bayes Risk decoding or QE-reranking. Our method consistently improves translation quality in terms of COMET and BLEURT scores when applied to large language models (LLMs) used for translation (PolyLM, XGLM, Llama2, Mistral, ALMA, and Tower) and to multilingual translation models (NLLB), over five language pairs. Notably, QE-fusion exhibits larger improvements for LLMs due to their ability to generate diverse outputs. We demonstrate that our approach generates novel translations in over half of the cases and consistently outperforms other methods across varying numbers of candidates (5-200). Furthermore, we empirically establish that QE-fusion scales linearly with the number of candidates in the pool.

Related papers

• Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraph [83.90988015005934]
  Uncertainty quantification (UQ) is a critical component of machine learning (ML) applications. We introduce a novel benchmark that implements a collection of state-of-the-art UQ baselines. We conduct a large-scale empirical investigation of UQ and normalization techniques across nine tasks, and identify the most promising approaches.
  arXiv  Detail & Related papers  (2024-06-21T20:06:31Z)
• QUEST: Quality-Aware Metropolis-Hastings Sampling for Machine Translation [25.165239478219267]
  We propose a simple and effective way to avoid over-reliance on noisy quality estimates by using them as the energy function of a Gibbs distribution. Instead of looking for a mode in the distribution, we generate multiple samples from high-density areas through the Metropolis-Hastings algorithm.
  arXiv  Detail & Related papers  (2024-05-28T17:36:06Z)
• The Power of Question Translation Training in Multilingual Reasoning: Broadened Scope and Deepened Insights [108.40766216456413]
  We propose a question alignment framework to bridge the gap between large language models' English and non-English performance. Experiment results show it can boost multilingual performance across diverse reasoning scenarios, model families, and sizes. We analyze representation space, generated response and data scales, and reveal how question translation training strengthens language alignment within LLMs.
  arXiv  Detail & Related papers  (2024-05-02T14:49:50Z)
• On the Calibration of Multilingual Question Answering LLMs [57.296161186129545]
  We benchmark the calibration of several multilingual Large Language Models (MLLMs) on a variety of Question Answering tasks. We study different dimensions of calibration in in-distribution, out-of-distribution, and cross-lingual transfer settings. For decoder-only LLMs such as LlaMa2, we additionally find that in-context learning improves confidence calibration on multilingual data.
  arXiv  Detail & Related papers  (2023-11-15T03:29:02Z)
• Unify word-level and span-level tasks: NJUNLP's Participation for the WMT2023 Quality Estimation Shared Task [59.46906545506715]
  We introduce the NJUNLP team to the WMT 2023 Quality Estimation (QE) shared task. Our team submitted predictions for the English-German language pair on all two sub-tasks. Our models achieved the best results in English-German for both word-level and fine-grained error span detection sub-tasks.
  arXiv  Detail & Related papers  (2023-09-23T01:52:14Z)
• SQUARE: Automatic Question Answering Evaluation using Multiple Positive and Negative References [73.67707138779245]
  We propose a new evaluation metric: SQuArE (Sentence-level QUestion AnsweRing Evaluation) We evaluate SQuArE on both sentence-level extractive (Answer Selection) and generative (GenQA) QA systems.
  arXiv  Detail & Related papers  (2023-09-21T16:51:30Z)
• PAXQA: Generating Cross-lingual Question Answering Examples at Training Scale [53.92008514395125]
  PAXQA (Projecting annotations for cross-lingual (x) QA) decomposes cross-lingual QA into two stages. We propose a novel use of lexically-constrained machine translation, in which constrained entities are extracted from the parallel bitexts. We show that models fine-tuned on these datasets outperform prior synthetic data generation models over several extractive QA datasets.
  arXiv  Detail & Related papers  (2023-04-24T15:46:26Z)
• Ensemble Fine-tuned mBERT for Translation Quality Estimation [0.0]
  In this paper, we discuss our submission to the WMT 2021 QE Shared Task. Our proposed system is an ensemble of multilingual BERT (mBERT)-based regression models. It demonstrates comparable performance with respect to the Pearson's correlation and beats the baseline system in MAE/ RMSE for several language pairs.
  arXiv  Detail & Related papers  (2021-09-08T20:13:06Z)
• An Exploratory Analysis of Multilingual Word-Level Quality Estimation with Cross-Lingual Transformers [3.4355075318742165]
  We show that multilingual, word-level QE models perform on par with the current language-specific models. In the cases of zero-shot and few-shot QE, we demonstrate that it is possible to accurately predict word-level quality for any given new language pair from models trained on other language pairs.
  arXiv  Detail & Related papers  (2021-05-31T23:21:10Z)
• Ensemble-based Transfer Learning for Low-resource Machine Translation Quality Estimation [1.7188280334580195]
  We focus on the Sentence-Level QE Shared Task of the Fifth Conference on Machine Translation (WMT20) We propose an ensemble-based predictor-estimator QE model with transfer learning to overcome such QE data scarcity challenge. We achieve the best performance on the ensemble model combining the models pretrained by individual languages as well as different levels of parallel trained corpus with a Pearson's correlation of 0.298.
  arXiv  Detail & Related papers  (2021-05-17T06:02:17Z)
• Revisiting Round-Trip Translation for Quality Estimation [0.0]
  Quality estimation (QE) is the task of automatically evaluating the quality of translations without human-translated references. In this paper, we employ semantic embeddings to RTT-based QE. Our method achieves the highest correlations with human judgments, compared to previous WMT 2019 quality estimation metric task submissions.
  arXiv  Detail & Related papers  (2020-04-29T03:20:22Z)

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.