Abstract
Automatic word alignment plays a critical role in statistical machine translation. Unfortunately, the relationship between alignment quality and statistical machine translation performance has not been well understood. In the recent literature, the alignment task has frequently been decoupled from the translation task and assumptions have been made about measuring alignment quality for machine translation which, it turns out, are not justified. In particular, none of the tens of papers published over the last five years has shown that significant decreases in alignment error rate (AER) result in significant increases in translation performance. This paper explains this state of affairs and presents steps towards measuring alignment quality in a way which is predictive of statistical machine translation performance.
Keywords
Machine translationComputer scienceTask (project management)Translation (biology)Word error rateEvaluation of machine translationNatural language processingArtificial intelligenceQuality (philosophy)Word (group theory)Example-based machine translationMachine translation software usabilitySpeech recognitionMachine learningLinguistics
Affiliated Institutions
Related Publications
Unsupervised construction of large paraphrase corpora
We investigate unsupervised techniques for acquiring monolingual sentence-level paraphrases from a corpus of temporally and topically clustered news articles collected from thou...
Letter N-Gram-based Input Encoding for Continuous Space Language Models
We present a letter-based encoding for words in continuous space language models. We represent the words completely by letter n-grams instead of using the word index. This way, ...
Survey of Hallucination in Natural Language Generation
Natural Language Generation (NLG) has improved exponentially in recent years thanks to the development of sequence-to-sequence deep learning technologies such as Transformer-bas...
Neural Machine Translation by Jointly Learning to Align and Translate
Neural machine translation is a recently proposed approach to machine translation. Unlike the traditional statistical machine translation, the neural machine translation aims at...
Efficient Estimation of Word Representations in Vector Space
We propose two novel model architectures for computing continuous vector representations of words from very large data sets. The quality of these representations is measured in ...
Publication Info
- Year
- 2007
- Type
- article
- Volume
- 33
- Issue
- 3
- Pages
- 293-303
- Citations
- 208
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
208
OpenAlex
Cite This
Alexander Fraser,
Daniel Marcu
(2007).
Measuring Word Alignment Quality for Statistical Machine Translation.
Computational Linguistics
, 33
(3)
, 293-303.
https://doi.org/10.1162/coli.2007.33.3.293
Identifiers
- DOI
- 10.1162/coli.2007.33.3.293