Re-evaluating machine translation results with paraphrase support

Zhou, Liang; Lin, Chin-Yew; Hovy, Eduard

doi:10.3115/1610075.1610087

Cited by 41 publications

(36 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Banerjee and Lavie (2005) and Chan and Ng (2008) use WordNet, and Zhou et al (2006) and Kauchak and Barzilay (2006) exploit large collections of automatically extracted paraphrases. These approaches reduce the risk that a good (but free) translation is rated poorly, but do not address the problem of translations that contain long matches while lacking coherence and grammaticality (cf.…”

Section: Related Workmentioning

confidence: 99%

Measuring machine translation quality as semantic equivalence: A metric based on entailment features

Padó¹,

Cer

Galley

et al. 2009

Machine Translation

View full text Add to dashboard Cite

Current evaluation metrics for machine translation have increasing difficulty in distinguishing good from merely fair translations. We believe the main problem to be their inability to properly capture meaning: A good translation candidate means the same thing as the reference translation, regardless of formulation. We propose a metric that assesses the quality of MT output through its semantic equivalence to the reference translation, based on a rich set of match and mismatch features motivated by textual entailment. We first evaluate this metric in an evaluation setting against a combination metric of four state-of-the-art scores. Our metric predicts human judgments better than the combination metric. Combining the entailment and traditional features yields further improvements. Then, we demonstrate that the entailment metric can also be used as learning criterion in minimum error rate training (MERT) to improve parameter estimation in MT system training. A manual evaluation of the resulting translations indicates that the new model obtains a significant improvement in translation quality.

show abstract

Section: Related Workmentioning

confidence: 99%

Measuring machine translation quality as semantic equivalence: A metric based on entailment features

Padó¹,

Cer

Galley

et al. 2009

Machine Translation

View full text Add to dashboard Cite

show abstract

“…As discussed above, semantic interpretation of noun-noun compounds can be used as a set of or a distribution over fine-grained paraphrasing verbs, or directly in paraphrases of the target noun-noun compounds tasks, e.g., for noun compound translation in isolation [Baldwin and Tanaka 2004;Grefenstette 1999;Tanaka and Baldwin 2003], for paraphrase-augmented machine translation [Callison-Burch et al 2006;Nakov 2008a;Nakov and Hearst 2007b;Nakov 2008b], for machine translation evaluation [RussoLassner et al 2005;Kauchak and Barzilay 2006], and for summarization evaluation [Zhou et al 2006], among others.…”

Section: Applicationsmentioning

confidence: 99%

Semantic interpretation of noun compounds using verbal and other paraphrases

Nakov

Hearst

2013

ACM Trans. Speech Lang. Process.

View full text Add to dashboard Cite

We study the problem of semantic interpretation of noun compounds such as bee honey, malaria mosquito, apple cake, and stem cell. In particular, we explore the potential of using predicates that make explicit the hidden relation that holds between the nouns that form the noun compound. For example, mosquito that carries malaria is a paraphrase of the compound malaria mosquito in which the verb explicitly states the semantic relation between the two nouns. We study the utility of using such paraphrasing verbs, with associated weights, to build a representation of the semantics of a noun compound, e.g., malaria mosquito can be represented as follows: carry (23), spread (16), cause (12), transmit (9), etc. We also explore the potential of using multiple paraphrasing verbs as features for predicting abstract semantic relations such as CAUSE, and we demonstrate that using explicit paraphrases can help improve statistical machine translation.

show abstract

“…复述(paraphrase)是指对相同语义的不同表达 [1] .复述研究在众多自然语言处理的应用领域中都有重要的意义.例如,在机器翻译研究中,对翻译短语的复述可以有效扩充翻译短语表,从而解决数据稀疏问题 [2] .同时,对赵世奇等:基于二元分类的复述搭配抽取翻译候选答案的复述可以提供更多更丰富的参考翻译句,从而促进翻译结果的自动评价 [3][4] .在自动问答研究中,对问句和答案抽取模板的复述可以解决问句和答案句之间的"词不匹配"问题,提高答案抽取的召回率 [5][6][7] .…”

Section: 研究背景unclassified

Paraphrase Collocation Extraction Based on Binary Classification

Zhao¹,

Zhao²,

Liu³

et al. 2010

Journal of Software

View full text Add to dashboard Cite

Paraphrase collocations are collocations that convey the same meaning using different surface words.Paraphrase collocations are important in various natural language processing applications. However, it has not been widely researched. This paper addresses the problem of paraphrase collocation extraction using collocations with "OBJ" relationship as a case study. Specifically, the proposed method recasts paraphrase collocation extraction as a binary classification problem, which combines multiple features based on translation, thesaurus, polarity words, and web mining. Experimental results show that the binary classification based method is effective for paraphrase collocation extraction. Especially, the exploited features are all helpful for improving the extraction performance.Using the proposed method, we extract more than 280,000 pairs of paraphrase collocations, the precision of which is above 70%. Further experiments show that nearly 40% of sentences can be paraphrased using the extracted paraphrase collocations, which demonstrates that the proposed method is useful in practice.

show abstract

Re-evaluating machine translation results with paraphrase support

Cited by 41 publications

References 9 publications

Measuring machine translation quality as semantic equivalence: A metric based on entailment features

Measuring machine translation quality as semantic equivalence: A metric based on entailment features

Semantic interpretation of noun compounds using verbal and other paraphrases

Paraphrase Collocation Extraction Based on Binary Classification

Contact Info

Product

Resources

About