Log-linear models for word alignment

Liu, Yang; Li, Qun; Lin, Sheng

doi:10.3115/1219840.1219897

Cited by 59 publications

(64 citation statements)

References 17 publications

(10 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, various discriminative models have been proposed in the literature (Liu et al, 2005;Moore, 2005;Taskar et al, 2005). Their advantage is that they may integrate a wide range of features that may lead to improved alignment quality.…”

Section: Word Alignment and Smtmentioning

confidence: 99%

Estimating Word Alignment Quality for SMT Reordering Tasks

Stymne¹,

Tiedemann²,

Nivre³

2014

Proceedings of the Ninth Workshop on Statistical Machine Translation

View full text Add to dashboard Cite

Previous studies of the effect of word alignment on translation quality in SMT generally explore link level metrics only and mostly do not show any clear connections between alignment and SMT quality. In this paper, we specifically investigate the impact of word alignment on two pre-reordering tasks in translation, using a wider range of quality indicators than previously done. Experiments on German-English translation show that reordering may require alignment models different from those used by the core translation system. Sparse alignments with high precision on the link level, for translation units, and on the subset of crossing links, like intersected HMM models, are preferred. Unlike SMT performance the desired alignment characteristics are similar for small and large training data for the pre-reordering tasks. Moreover, we confirm previous research showing that the fuzzy reordering score is a useful and cheap proxy for performance on SMT reordering tasks.

show abstract

Section: Word Alignment and Smtmentioning

confidence: 99%

Estimating Word Alignment Quality for SMT Reordering Tasks

Stymne¹,

Tiedemann²,

Nivre³

2014

Proceedings of the Ninth Workshop on Statistical Machine Translation

View full text Add to dashboard Cite

show abstract

“…In general there are exponentially many such sequences, each implying a different alignment of y to x. This model is reminiscent of conditional models in MT that perform stepwise generation of one string or structure from another-e.g., string alignment models with contextual features (Cherry and Lin, 2003;Liu et al, 2005;Dyer et al, 2013), or tree transducers (Knight and Graehl, 2005).…”

Section: Stochastic Contextual Edit Distancementioning

confidence: 99%

Stochastic Contextual Edit Distance and Probabilistic FSTs

Cotterell

Peng

Eisner

2014

Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

View full text Add to dashboard Cite

String similarity is most often measured by weighted or unweighted edit distance d(x, y). Ristad and Yianilos (1998) defined stochastic edit distance-a probability distribution p(y | x) whose parameters can be trained from data. We generalize this so that the probability of choosing each edit operation can depend on contextual features. We show how to construct and train a probabilistic finite-state transducer that computes our stochastic contextual edit distance. To illustrate the improvement from conditioning on context, we model typos found in social media text.

show abstract

“…We prefer log-linear models over reasonable alternatives e.g., perceptron or SVM, following the practice of a range of previous work in related areas (Smith, 2004;Liu et al, 2005;Poon et al, 2009;Bamman et al, 2012a;Filippova, 2012;Volkova and Bachrach, 2015;Hovy, 2015).…”

Section: Modelsmentioning

confidence: 99%

Account Deletion Prediction on RuNet: A Case Study of Suspicious Twitter Accounts Active During the Russian-Ukrainian Crisis

Volkova¹,

Bell²

2016

Proceedings of the Second Workshop on Computational Approaches To Deception Detection

View full text Add to dashboard Cite

Social networks are dynamically changing over time e.g., some accounts are being created and some are being deleted or become private. This ephemerality at both an account level and content level results from a combination of privacy concerns, spam, and deceptive behaviors. In this study we analyze a large dataset of 180,340 accounts active during the Russian-Ukrainian crisis to discover a series of predictive features for the removal or shutdown of a suspicious account. We find that unlike previously reported profile and network features, lexical features form the basis for highly accurate prediction of the deletion of an account.

show abstract

Log-linear models for word alignment

Cited by 59 publications

References 17 publications

Estimating Word Alignment Quality for SMT Reordering Tasks

Estimating Word Alignment Quality for SMT Reordering Tasks

Stochastic Contextual Edit Distance and Probabilistic FSTs

Account Deletion Prediction on RuNet: A Case Study of Suspicious Twitter Accounts Active During the Russian-Ukrainian Crisis

Contact Info

Product

Resources

About