Paraphrasing (computational linguistics): Difference between revisions

Revision as of 11:29, 21 August 2021

Revision as of 06:08, 23 August 2021

Line 1:

{{short description|Automatic generation or recognition of paraphrased text}}

{{about|automated generation and recognition of paraphrases||Paraphrase (disambiguation)}}

'''Paraphrase''' or '''paraphrasing''' in [[computational linguistics]] is the [[natural language processing]] task of detecting and generating [[paraphrase]]s. Applications of paraphrasing are varied including information retrieval, [[question answering]], [[Automatic summarization|text summarization]], and [[plagiarism detection]].<ref name=Socher /> Paraphrasing is also useful in the [[evaluation of machine translation]],<ref name=Callison>{{cite conference |last=Callison-Burch |first=Chris |title=Syntactic Constraints on Paraphrases Extracted from Parallel Corpora |book-titleconference=EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing |date=October 25–27, 2008 |place=Honolulu, Hawaii |pages=196–205|url=https://dl.acm.org/citation.cfm?id=1613743}}</ref> as well as [[semantic parsing]]<ref>Berant, Jonathan, and Percy Liang. "[http://www.aclweb.org/anthology/P14-1133 Semantic parsing via paraphrasing]." Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Vol. 1. 2014.</ref> and [[natural language generation|generation]] of new samples to expand existing [[Text corpus|corpora]].<ref name=Barzilay />

== Paraphrase generation ==

=== Multiple sequence alignment ===

Barzilay and Lee<ref name=Barzilay>{{cite conference|last1=Barzilay|first1=Regina|last2=Lee|first2=Lillian|title=Learning to Paraphrase: An Unsupervised Approach Using Multiple-Sequence Alignment|book-titleconference=Proceedings of HLT-NAACL 2003|date=May–June 2003|url=http://www.cs.cornell.edu/home/llee/papers/statpar.home.html}}</ref> proposed a method to generate paraphrases through the usage of monolingual [[parallel text|parallel corpora]], namely news articles covering the same event on the same day. Training consists of using [[multiple sequence alignment|multi-sequence alignment]] to generate sentence-level paraphrases from an unannotated corpus. This is done by

* finding recurring patterns in each individual corpus, i.e. "{{mvar|X}} (injured/wounded) {{mvar|Y}} people, {{mvar|Z}} seriously" where {{mvar|X, Y, Z}} are variables

Line 14:

=== Phrase-based Machine Translation ===

Paraphrase can also be generated through the use of [[statistical machine translation#Phrase-based translation|phrase-based translation]] as proposed by Bannard and Callison-Burch.<ref name=Bannard>{{cite conference |last1=Bannard|first1=Colin|last2=Callison-Burch|first2=Chris|title=Paraphrasing Bilingual Parallel Corpora |book-titleconference=Proceedings of the 43rd Annual Meeting of the ACL |place=Ann Arbor, Michigan|pages=597–604|year=2005|url=https://dl.acm.org/citation.cfm?id=1219914}}</ref> The chief concept consists of aligning phrases in a [[pivot language]] to produce potential paraphrases in the original language. For example, the phrase "under control" in an English sentence is aligned with the phrase "unter kontrolle" in its German counterpart. The phrase "unter kontrolle" is then found in another German sentence with the aligned English phrase being "in check", a paraphrase of "under control".

The probability distribution can be modeled as <math>\Pr(e_2 | e_1)</math>, the probability phrase <math>e_2</math> is a paraphrase of <math>e_1</math>, which is equivalent to <math>\Pr(e_2|f) \Pr(f|e_1)</math> summed over all <math>f</math>, a potential phrase translation in the pivot language. Additionally, the sentence <math>e_1</math> is added as a prior to add context to the paraphrase. Thus the optimal paraphrase, <math>\hat{e_2}</math> can be modeled as:

Line 28:

=== Recursive Autoencoders ===

Paraphrase recognition has been attempted by Socher et al<ref name=Socher>{{Citation |last1=Socher|first1=Richard |last2=Huang |first2=Eric |last3=Pennington |first3=Jeffrey |last4=Ng |first4=Andrew |last5=Manning |first5=Christopher |title=Dynamic Pooling and Unfolding Recursive Autoencoders for Paraphrase Detection |book-titlechapter=Advances in Neural Information Processing Systems 24 |year=2011 |url=http://www.socher.org/index.php/Main/DynamicPoolingAndUnfoldingRecursiveAutoencodersForParaphraseDetection}}</ref> through the use of recursive [[autoencoder]]s. The main concept is to produce a vector representation of a sentence along with its components through recursively using an autoencoder. The vector representations of paraphrases should have similar vector representations; they are processed, then fed as input into a [[artificial neural network|neural network]] for classification.

Given a sentence <math>W</math> with <math>m</math> words, the autoencoder is designed to take 2 <math>n</math>-dimensional [[word embedding]]s as input and produce an <math>n</math>-dimensional vector as output. The same autoencoder is applied to every pair of words in <math>S</math> to produce <math>\lfloor m/2 \rfloor</math> vectors. The autoencoder is then applied recursively with the new vectors as inputs until a single vector is produced. Given an odd number of inputs, the first vector is forwarded as is to the next level of recursion. The autoencoder is then trained to reproduce every vector in the full recursion tree including the initial word embeddings.

Line 40:

== Evaluation ==

There are multiple methods that can be used to evaluate paraphrases. Since paraphrase recognition can be posed as a classification problem, most standard evaluations metrics such as [[accuracy]], [[f1 score]], or an [[receiver operating characteristic|ROC curve]] do relatively well. However, there is difficulty calculating f1-scores due to trouble produce a complete list of paraphrases for a given phrase along with the fact that good paraphrases are dependent upon context. A metric designed to counter these problems is ParaMetric.<ref name=Burch2>{{cite conference |last1=Callison-Burch |first1=Chris |last2=Cohn |first2=Trevor |last3=Lapata |first3=Mirella |title=ParaMetric: An Automatic Evaluation Metric for Paraphrasing |book-titleconference=Proceedings of the 22nd International Conference on Computational Linguistics|place=Manchester |year=2008 |pages=97–104 |doi=10.3115/1599081.1599094 |s2cid=837398 |url=https://pdfs.semanticscholar.org/be0d/0df960833c1bea2a39ba9a17e5ca958018cd.pdf |doi-access=free}}</ref> ParaMetric aims to calculate the precision and recall of an automatic paraphrase system by comparing the automatic alignment of paraphrases to a manual alignment of similar phrases. Since ParaMetric is simply rating the quality of phrase alignment, it can be used to rate paraphrase generation systems as well assuming it uses phrase alignment as part of its generation process. A noted drawback to ParaMetric is the large and exhaustive set of manual alignments that must be initially created before a rating can be produced.

The evaluation of paraphrase generation has similar difficulties as the evaluation of [[machine translation]]. Often the quality of a paraphrase is dependent upon its context, whether it is being used as a summary, and how it is generated among other factors. Additionally, a good paraphrase usually is lexically dissimilar from its source phrase. The simplest method used to evaluate paraphrase generation would be through the use of human judges. Unfortunately, evaluation through human judges tends to be time consuming. Automated approaches to evaluation prove to be challenging as it is essentially a problem as difficult as paraphrase recognition. While originally used to evaluate machine translations, bilingual evaluation understudy ([[BLEU]]) has been used successfully to evaluate paraphrase generation models as well. However, paraphrases often have several lexically different but equally valid solutions which hurts BLEU and other similar evaluation metrics.<ref name=Chen>{{cite conference |last1=Chen |first1=David |last2=Dolan |first2=William |title=Collecting Highly Parallel Data for Paraphrase Evaluation |book-titleconference=Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies |place=Portland, Oregon |year=2008 |pages=190–200 |url=https://dl.acm.org/citation.cfm?id=2002497}}</ref>

Metrics specifically designed to evaluate paraphrase generation include paraphrase in n-gram change (PINC)<ref name=Chen /> and paraphrase evaluation metric (PEM)<ref name=Liu>{{cite conference|last1=Liu|first1=Chang|last2=Dahlmeier|first2=Daniel|last3=Ng|first3=Hwee Tou|title=PEM: A Paraphrase Evaluation Metric Exploiting Parallel Texts |book-titleconference=Proceedings of the 2010 Conference on Empricial Methods in Natural Language Processing |place=MIT, Massachusetts |year=2010 |pages=923–932 |url=http://www.aclweb.org/anthology/D10-1090}}</ref> along with the aforementioned ParaMetric. PINC is designed to be used in conjunction with BLEU and help cover its inadequacies. Since BLEU has difficulty measuring lexical dissimilarity, PINC is a measurement of the lack of n-gram overlap between a source sentence and a candidate paraphrase. It is essentially the [[Jaccard index|Jaccard distance]] between the sentence excluding n-grams that appear in the source sentence to maintain some semantic equivalence. PEM, on the other hand, attempts to evaluate the "adequacy, fluency, and lexical dissimilarity" of paraphrases by returning a single value heuristic calculated using [[N-gram]]s overlap in a pivot language. However, a large drawback to PEM is that must be trained using a large, in-___domain parallel corpora as well as human judges.<ref name=Chen /> In other words, it is tantamount to training a paraphrase recognition system in order to evaluate a paraphrase generation system.

== See also ==