Extracting Structural Paraphrases from Aligned Monolingual Corpora

Ibrahim, Ali; Katz, Boris; Lin, Jimmy

doi:10.21236/ada460577

Cited by 25 publications

(32 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Paraphrase generation has the potential of being used in many other NLP research topics, such as machine translation (Madnani et al, 2007) and question answering (Buck et al, 2017;Dong et al, 2017). Early work mainly focuses on extracting paraphrases from parallel monolingual texts (Barzilay and McKeown, 2001;Ibrahim et al, 2003;Pang et al, 2003). Later, Quirk et al (2004) propose to use statistical machine translation for generating paraphrases directly.…”

Section: Related Workmentioning

confidence: 99%

An Empirical Comparison on Imitation Learning and Reinforcement Learning for Paraphrase Generation

Du¹,

Ji²

2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

View full text Add to dashboard Cite

Generating paraphrases from given sentences involves decoding words step by step from a large vocabulary. To learn a decoder, supervised learning which maximizes the likelihood of tokens always suffers from the exposure bias. Although both reinforcement learning (RL) and imitation learning (IL) have been widely used to alleviate the bias, the lack of direct comparison leads to only a partial image on their benefits. In this work, we present an empirical study on how RL and IL can help boost the performance of generating paraphrases, with the pointer-generator as a base model 1 . Experiments on the benchmark datasets show that (1) imitation learning is constantly better than reinforcement learning; and (2) the pointer-generator models with imitation learning outperform the state-of-theart methods with a large margin. 2 In this work, we view scheduled sampling as an imitation learning algorithm similar to DAG-GER (Ross et al., 2011).

show abstract

Section: Related Workmentioning

confidence: 99%

An Empirical Comparison on Imitation Learning and Reinforcement Learning for Paraphrase Generation

Du¹,

Ji²

2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

View full text Add to dashboard Cite

show abstract

“…We first process top NP chunks because they are the most stable between languages. Interestingly, NPs are also used as anchor points to learn monolingual paraphrases (Ibrahim et al, 2003). The phrasal structure categories can be extracted from automatic parsers using methods in (Xia, 2001).…”

Section: Grammar Induction By Synchronousmentioning

confidence: 99%

Machine translation using probabilistic synchronous dependency insertion grammars

Ding

Palmer

2005

Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics - ACL '05

107

View full text Add to dashboard Cite

Syntax-based statistical machine translation (MT) aims at applying statistical models to structured data. In this paper, we present a syntax-based statistical machine translation system based on a probabilistic synchronous dependency insertion grammar. Synchronous dependency insertion grammars are a version of synchronous grammars defined on dependency trees. We first introduce our approach to inducing such a grammar from parallel corpora. Second, we describe the graphical model for the machine translation task, which can also be viewed as a stochastic tree-to-tree transducer. We introduce a polynomial time decoding algorithm for the model. We evaluate the outputs of our MT system using the NIST and Bleu automatic MT evaluation software. The result shows that our system outperforms the baseline system based on the IBM models in both translation speed and quality.

show abstract

“…In the automatic evaluation of machine translation, paraphrases may help to alleviate problems presented by the fact that there are often alternative and equally valid ways of translating a text (Pang et al, 2003). In question answering, discovering paraphrased answers may provide additional evidence that an answer is correct (Ibrahim et al, 2003).…”

Section: Introductionmentioning

confidence: 99%

“…In this paper we introduce a novel method for extracting paraphrases that uses bilingual parallel corpora. Past work (Barzilay and McKeown, 2001;Barzilay and Lee, 2003;Pang et al, 2003;Ibrahim et al, 2003) has examined the use of monolingual parallel corpora for paraphrase extraction. Examples of monolingual parallel corpora that have been used are multiple translations of classical French novels into English, and data created for machine translation evaluation methods such as Bleu (Papineni et al, 2002) which use multiple reference translations.…”

Section: Introductionmentioning

confidence: 99%

Paraphrasing with bilingual parallel corpora

Bannard

Callison-Burch

2005

Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics - ACL '05

322

324

View full text Add to dashboard Cite

Previous work has used monolingual parallel corpora to extract and generate paraphrases. We show that this task can be done using bilingual parallel corpora, a much more commonly available resource. Using alignment techniques from phrasebased statistical machine translation, we show how paraphrases in one language can be identified using a phrase in another language as a pivot. We define a paraphrase probability that allows paraphrases extracted from a bilingual parallel corpus to be ranked using translation probabilities, and show how it can be refined to take contextual information into account. We evaluate our paraphrase extraction and ranking methods using a set of manual word alignments, and contrast the quality with paraphrases extracted from automatic alignments.

show abstract

Extracting Structural Paraphrases from Aligned Monolingual Corpora

Cited by 25 publications

References 1 publication

An Empirical Comparison on Imitation Learning and Reinforcement Learning for Paraphrase Generation

An Empirical Comparison on Imitation Learning and Reinforcement Learning for Paraphrase Generation

Machine translation using probabilistic synchronous dependency insertion grammars

Paraphrasing with bilingual parallel corpora

Contact Info

Product

Resources

About