Extracting Paraphrases from a Parallel Corpus

By Regina Barzilay, K. McKeown. Annual Meeting of the Association for Computational Linguistics, 2001

556 citations recorded by the source corpus.

While paraphrasing is critical both for interpretation and generation of natural language, current systems use manual or semi-automatic methods to collect paraphrases. We present an unsupervised learning algorithm for identification of paraphrases from a corpus of multiple English translations of the same source text. Our approach yields phrasal and single word lexical paraphrases as well as syntactic paraphrases.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/8d7a692d8763a38283db54e19f1dcc694a34e706

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

Citations in the corpus

Sequence-to-Sequence Data Augmentation for Dialogue Language Understanding (2018, background): “Paraphrasing is the most studied techniques in natural language processing for generating alternative expressions (Barzilay and McKeown, 2001; Bannard and Callison-Burch, 2005; Callison-Burch, 2008).”
Large-Scale, Diverse, Paraphrastic Bitexts via Sampling and Clustering (2019, background): “Barzilay and McKeown (2001) sought to extract lexical paraphrastic expression from such sources.”
A Probabilistic Classification Approach for Lexical Textual Entailment (2005, background): “Recent works on paraphrase and entailment rule acquisition (Barzilay and McKeown 2001; Lin and Pantel 2001; Szpektor et al. 2004) learn lexical syntactic paraphrase patterns.”
Generating Phrasal and Sentential Paraphrases: A Survey of Data-Driven Methods (2010, background): “Ibrahim, Katz, and Lin (2003) propose an approach that applies a modiﬁed version of the dependency path distributional similarity algorithm proposed by Lin and Pantel (2001) to the same monolingual parallel corpus (multiple translations of literary works) used by Barzilay and McKeown (2001).”
Large Scale Acquisition of Paraphrases for Learning Surface Patterns (2008, methodology): “Barzilay and McKeown (2001) used a monolingual parallel corpus to obtain paraphrases.”
Evaluating Evaluation Methods for Generation in the Presence of Variation (2005, unknown): “[6–10]).”
Learning to Paraphrase: An Unsupervised Approach Using Multiple-Sequence Alignment (2003, methodology): “Our ﬁrst step is to cluster sentences into groups from which to learn useful patterns; for the multiple-sequence techniques we will use, this means that the sentences within clusters should describe similar events and have similar structure, as in the sentences of Figure 2.”
Paraphrase-Driven Learning for Open Question Answering (2013, methodology): “The learning algorithms presented in this paper are similar to algorithms used for paraphrase extraction from sentence-aligned corpora (Barzilay and McKeown, 2001; Barzilay and Lee, 2003; Quirk et al., 2004; Bannard and Callison-Burch, 2005; Callison-Burch, 2008; Marton et al., 2009).”
Pushing the Limits of Paraphrastic Sentence Embeddings with Millions of Machine Translations (2017, background): “Many researchers have developed methods for generating or ﬁnding naturally-occurring sentential para-phrase pairs (Barzilay and McKeown, 2001; Dolan et al., 2004; Dolan and Brockett, 2005; Quirk et al., 2004; Coster and Kauchak, 2011; Xu et al., 2014, 2015; Lan et al., 2017).”
Scaling Web-based Acquisition of Entailment Relations (2004, background): “These include multiple translations of the same text (Barzilay and McKeown, 2001) and corresponding articles from multiple news sources (Shinyama et al.”
Knowledge-Based Textual Inference via Parse-Tree Transformations (2015, background): “Much work has been dedicated to unsupervised learning of such relations from comparable corpora (Barzilay & McKeown , 2001; Barzilay & Lee, 2003; Pang, Knight, & Marcu, 2003), by querying the Web (Ravichandran & Hovy, 2002; Szpektor et al., 2004), or from a local corpus (Lin & Pantel, 2001;…”
Data Augmentation Approaches in Natural Language Processing: A Survey (2021, background): “Paraphrasing-based Methods As common phenomena in natural language, paraphrases are alternative ways to convey the same information as the original form [37, 38].”
Collecting Highly Parallel Data for Paraphrase Evaluation (2011, background): “One popular approach exploits multiple translations of the same data (Barzilay and McKeown, 2001; Pang et al., 2003).”
Improved Statistical Machine Translation Using Paraphrases (2006, methodology): “Many methods for extracting paraphrases (Barzilay and McKeown, 2001; Pang et al., 2003) make use of monolingual parallel corpora, such as multiple translations of classic French novels into English, or the multiple reference translations used by many automatic evaluation metrics for machine translat”
Revisiting Recurrent Networks for Paraphrastic Sentence Embeddings (2017, background): “Future work will explore additional data sources, including from aligning different translations of novels (Barzilay and McKeown, 2001), aligning new articles of the same topic (Dolan et al., 2004), or even possibly using machine translation systems to translate bilingual text into paraphrastic…”
Measuring Semantic Similarity by Latent Relational Analysis (2005, methodology): “In the VSM approach of Turney and Littman [2005], we create vectors, r 1 and r 2 , that represent features of R 1 and R 2 , and measure the similarity of R 1 and R 2 by the cosine of the angle between n r r r We make a vector, r , to characterize the relationship be-tween two words, X and Y , by…”
Unsupervised Construction of Large Paraphrase Corpora: Exploiting Massively Parallel News Sources (2004, background): “The importance of learning to manipulate monolingual paraphrase relationships for applications like summarization, search, and dialog has been highlighted by a number of recent efforts (Barzilay & McKeown 2001; Shinyama et al. 2002; Lee & Barzilay 2003; Lin & Pantel 2001).”
Paraphrasing with Bilingual Parallel Corpora (2005, background): “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.”