Paraphrasing with Bilingual Parallel Corpora
By Colin Bannard, Chris Callison-Burch. 2005
644 citations recorded by the source corpus.
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 phrase-based 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.
Subfields: Artificial Intelligence, Natural Language Processing, Machine Translation
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Mohit Bansal
- Luke S. Zettlemoyer
- Graham Neubig
- Percy Liang
- Jianfeng Gao
- Yejin Choi
- Noah A. Smith
- Richard Socher
In Natural Language Processing
- Graham Neubig
- Mohit Bansal
- Luke S. Zettlemoyer
- Mirella Lapata
- Yejin Choi
- Percy Liang
- Kevin Gimpel
- Noah A. Smith
In Machine Translation
- Philipp Koehn
- Matt Post
- Kevin Gimpel
- Jörg Tiedemann
- John Wieting
- Liane Guillou
- Benjamin Van Durme
- Markus Freitag
Citations in the corpus
- BLEURT: Learning Robust Metrics for Text Generation (2020, methodology): “Backtranslation: We generate paraphrases and perturbations with backtranslation, that is, round trips from English to another language and then back to English with a translation model (Bannard and Callison-Burch, 2005; Ganitkevitch et al., 2013; Sennrich et al., 2016).”
- Adversarial Example Generation with Syntactically Controlled Paraphrase Networks (2018, methodology): “In particular, bilingual pivoting (Bannard and Callison-Burch, 2005) finds quality para-”
- (Meta-) Evaluation of Machine Translation (2007, methodology): “, 2006)–ParaEval matches hypothesis and reference translations using paraphrases that are extracted from parallel corpora in an unsupervised fashion (Bannard and Callison-Burch, 2005).”
- Ask the Right Questions: Active Question Reformulation with Reinforcement Learning (2017, background): “Early work extracted word or phrase pairs ( e, e 0 ) from a phrase table such that e translates into a foreign phrase f and f translates back to e 0 [Bannard and Callison-Burch, 2005].”
- Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation (2017, background): “Attention is also being paid to what Barnard (2016) refers to as localisation, that is, the association of linguistic expressions with parts of images, and the ability to generate descriptions of specific image regions. Recent work includes that of Karpathy and Fei-Fei (2015), Johnson et al. (2016) ”
- Results of the WMT19 Metrics Shared Task: Segment-Level and Strong MT Systems Pose Big Challenges (2019, background): “0 extracts the knowledge from the Paraphrase Database (PPDB; Bannard and Callison-Burch, 2005) and integrates it into Meteor-based metrics.”
- Optimizing Statistical Machine Translation for Text Simplification (2016, methodology): “It is created by extracting English paraphrases from bilingual parallel corpora using a technique called “bilingual pivoting” (Bannard and Callison-Burch, 2005).”
- Paraphrasing Revisited with Neural Machine Translation (2017, methodology): “The intuition behind Bannard and Callison-Burch’s (2005) bilingual pivoting method is that two English strings e1 and e2 that translate to the same foreign string f can be assumed to have the same meaning.”
- ParaNMT-50M: Pushing the Limits of Paraphrastic Sentence Embeddings with Millions of Machine Translations (2017, methodology): “Bannard and Callison-Burch (2005) used methods from statistical machine translation to find lexical and phrasal paraphrases in parallel text.”
- From Paraphrase Database to Compositional Paraphrase Model and Back (2015, methodology): “, 2013), a collection of confidence-rated paraphrases created using the pivoting technique of Bannard and Callison-Burch (2005) over large parallel corpora.”
- Transforming Question Answering Datasets Into Natural Language Inference Datasets (2018, methodology): “, 1996), paraphrase (Lin and Pantel, 2001; Bannard and Callison-Burch, 2005) and summarization (Jones, 1993), highlighting the close connection between these tasks.”
- Sentence Compression Beyond Word Deletion (2008, background): “Some English text is translated to a foreign language, and then translated back into English (Bannard and Callison-Burch, 2005):”
- PPDB 2.0: Better paraphrase ranking, fine-grained entailment relations, word embeddings, and style classification (2015, methodology): “…scores against the 5-point human judgments for four different ways of ranking the paraphrases: 1) the original paraphrase probability defined by Bannard and Callison-Burch (2005), 2) the heuristic ranking that Ganitkevitch et al. (2013) defined for PPDB 1.0, 3) the cosine similarity of…”
- Learning Paraphrastic Sentence Embeddings from Back-Translated Bitext (2017, background): “The most relevant work uses bilingual corpora, e.g., Zhao et al. (2008) and Bannard and Callison-Burch (2005), the latter leading to PPDB.”
- PowerTransformer: Unsupervised Controllable Revision for Biased Language Correction (2020, methodology): “13 OpusParcus was created by automatically aligning the subtitles sentences using several probabilistic metrics, including likelihood under a round-trip translation paraphrasing model (Bannard and Callison-Burch, 2005) and pointwise mutual information.”