Accurate Online Posterior Alignments for Principled Lexically-Constrained Decoding

• URL: http://arxiv.org/abs/2204.00871v1
• Date: Sat, 2 Apr 2022 14:37:07 GMT
• Title: Accurate Online Posterior Alignments for Principled Lexically-Constrained Decoding
• Authors: Soumya Chatterjee, Sunita Sarawagi, Preethi Jyothi
• Abstract summary: We propose a novel posterior alignment technique that is truly online in its execution and superior in terms of alignment error rates. On five language pairs, including two distant language pairs, we achieve consistent drop in alignment error rates. When deployed on seven lexically constrained translation tasks, we achieve significant improvements in BLEU specifically around the constrained positions.
• Score: 40.212186465135304
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Online alignment in machine translation refers to the task of aligning a target word to a source word when the target sequence has only been partially decoded. Good online alignments facilitate important applications such as lexically constrained translation where user-defined dictionaries are used to inject lexical constraints into the translation model. We propose a novel posterior alignment technique that is truly online in its execution and superior in terms of alignment error rates compared to existing methods. Our proposed inference technique jointly considers alignment and token probabilities in a principled manner and can be seamlessly integrated within existing constrained beam-search decoding algorithms. On five language pairs, including two distant language pairs, we achieve consistent drop in alignment error rates. When deployed on seven lexically constrained translation tasks, we achieve significant improvements in BLEU specifically around the constrained positions.

Related papers

• An Analysis of BPE Vocabulary Trimming in Neural Machine Translation [56.383793805299234]
  vocabulary trimming is a postprocessing step that replaces rare subwords with their component subwords. We show that vocabulary trimming fails to improve performance and is even prone to incurring heavy degradation.
  arXiv  Detail & Related papers  (2024-03-30T15:29:49Z)
• Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback [70.32795295142648]
  Linear alignment is a novel algorithm that aligns language models with human preferences in one single inference step. Experiments on both general and personalized preference datasets demonstrate that linear alignment significantly enhances the performance and efficiency of LLM alignment.
  arXiv  Detail & Related papers  (2024-01-21T10:46:23Z)
• Third-Party Aligner for Neural Word Alignments [18.745852103348845]
  We propose to use word alignments generated by a third-party word aligner to supervise the neural word alignment training. Experiments show that our approach can surprisingly do self-correction over the third-party supervision. We achieve state-of-the-art word alignment performances, with averagely more than two points lower alignment error rates than the best third-party aligner.
  arXiv  Detail & Related papers  (2022-11-08T12:30:08Z)
• Unsupervised Alignment of Distributional Word Embeddings [0.0]
  Cross-domain alignment play a key role in tasks ranging from machine translation to transfer learning. We show that the proposed approach achieves good performance on the bilingual lexicon induction task across several language pairs.
  arXiv  Detail & Related papers  (2022-03-09T16:39:06Z)
• Using Optimal Transport as Alignment Objective for fine-tuning Multilingual Contextualized Embeddings [7.026476782041066]
  We propose using Optimal Transport (OT) as an alignment objective during fine-tuning to improve multilingual contextualized representations. This approach does not require word-alignment pairs prior to fine-tuning and instead learns the word alignments within context in an unsupervised manner.
  arXiv  Detail & Related papers  (2021-10-06T16:13:45Z)
• End-to-End Lexically Constrained Machine Translation for Morphologically Rich Languages [0.0]
  We investigate mechanisms to allow neural machine translation to infer the correct word inflection given lemmatized constraints. Our experiments on the English-Czech language pair show that this approach improves the translation of constrained terms in both automatic and manual evaluation.
  arXiv  Detail & Related papers  (2021-06-23T13:40:13Z)
• SLUA: A Super Lightweight Unsupervised Word Alignment Model via Cross-Lingual Contrastive Learning [79.91678610678885]
  We propose a super lightweight unsupervised word alignment model (SLUA) Experimental results on several public benchmarks demonstrate that our model achieves competitive, if not better, performance. Notably, we recognize our model as a pioneer attempt to unify bilingual word embedding and word alignments.
  arXiv  Detail & Related papers  (2021-02-08T05:54:11Z)
• Word Alignment by Fine-tuning Embeddings on Parallel Corpora [96.28608163701055]
  Word alignment over parallel corpora has a wide variety of applications, including learning translation lexicons, cross-lingual transfer of language processing tools, and automatic evaluation or analysis of translation outputs. Recently, other work has demonstrated that pre-trained contextualized word embeddings derived from multilingually trained language models (LMs) prove an attractive alternative, achieving competitive results on the word alignment task even in the absence of explicit training on parallel data. In this paper, we examine methods to marry the two approaches: leveraging pre-trained LMs but fine-tuning them on parallel text with objectives designed to improve alignment quality, and proposing
  arXiv  Detail & Related papers  (2021-01-20T17:54:47Z)
• Learning aligned embeddings for semi-supervised word translation using Maximum Mean Discrepancy [3.299672391663527]
  We propose an end-to-end approach for word embedding alignment that does not require known word pairs. Our method learns embeddings that are aligned during sentence translation training using a localized Maximum Mean Discrepancy (MMD) constraint. We show that our method not only out-performs unsupervised methods, but also supervised methods that train on known word translations.
  arXiv  Detail & Related papers  (2020-06-20T13:57:55Z)
• Multilingual Alignment of Contextual Word Representations [49.42244463346612]
  BERT exhibits significantly improved zero-shot performance on XNLI compared to the base model. We introduce a contextual version of word retrieval and show that it correlates well with downstream zero-shot transfer. These results support contextual alignment as a useful concept for understanding large multilingual pre-trained models.
  arXiv  Detail & Related papers  (2020-02-10T03:27:21Z)

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.