Paraphrase Database


paraphrase.org (@ppdb)

Notes:

A relatively recent advance in NLP has been the automatic construction of paraphrase databases (containing phrasal patterns with approximately equivalent meaning), built by finding phrases that occur in distributionally similar contexts. Any approach must include a generation component that can accurately paraphrase database queries back to the user in natural language.

Sequences of words in the reference are considered to be paraphrases of a sequence of words in the hypothesis if that phrase pair occurs in the paraphrase database. The support verb construction expression is matched against the paraphrase database (developed in nooj4nlp.net linguistic engine) and the corresponding candidates are retrieved with the inflectional features of the support verb in the original expression. To identify these possible entailment relationships we use three knowledge resources, namely WordNet, ParaPara (a large paraphrase database from Johns Hopkins University), and the DIRT paraphrase database. The DIRT Paraphrase Database paraphrases have been used successfully by several RTE (Recognizing Textual Entailment) systems.

Sekine’s Paraphrase Database is collected using an unsupervised method, and focuses on phrases connecting two Named Entities. Paraphrase databases and a hand-built knowledge base can be used to resolve underspecified representations. A generic paraphrase database is a valuable resource and may be created using parallel news corpora, such as an Arabic-English newswire bitext containing a million sentences. According to Michael Minock, developer of the C-Phrase web-based natural language front end to relational databases, standard, off-the-shelf relational databases are sufficiently expressive to back NLIs.

In Text Summarization, alternative paraphrases can be used to change the length of a summary. Discriminative edit models (discriminative model) may be used for paraphrase scoring. Using a Porter stemmer and a unigram paraphrase database allows more lexical variations. One system also makes use of a Dictionary of Synonyms derived from WordNet to discover the potential collocational errors in learners’ input, as well as a Paraphrase Database gathered from the learners themselves to help diagnose un-collocational learner phrase. When there are no proper cases, the system asks users for para-phrasing and adds the paraphrase to the paraphrase database.

  • Lexical Entailment Systems
  • Paraphrase Scoring
  • Predicate Argument Aligner
  • Recognizing Textual Entailment (RTE Systems)

Wikipedia:

See also:

FrameNet | FrameNet & Dialog SystemsParaphrasing & Dialog Systems 2014 | SPG (Statistical Paraphrase Generation)


PPDB: The Paraphrase Database. J Ganitkevitch, B Van Durme, C Callison-Burch – HLT-NAACL, 2013 – aclweb.org Abstract We present the 1.0 release of our paraphrase database, PPDB. Its English portion, PPDB: Eng, contains over 220 million paraphrase pairs, consisting of 73 million phrasal and 8 million lexical paraphrases, as well as 140 million paraphrase patterns, which capture … Cited by 41 Related articles All 13 versions

Extending the METEOR machine translation evaluation metric to the phrase level M Denkowski, A Lavie – … Technologies: The 2010 Annual Conference of …, 2010 – dl.acm.org … We introduce an additional paraphrase matcher which matches phrases (one or more successive words) if one phrase is considered a paraphrase of the other by a paraphrase database. For English, we use the paraphrase database developed by Snover et al. … Cited by 26 Related articles All 3 versions

On the role of lexical and world knowledge in rte3 P Clark, WR Murray, J Thompson, P Harrison… – Proceedings of the ACL …, 2007 – dl.acm.org … 3.2 The DIRT Paraphrase Database Paraphrases have been used successfully by several RTE systems (eg, Hickl et al., 2005). With re- spect to our earlier analysis, we examined Lin and Pantel’s (2001) paraphrase database … Cited by 42 Related articles All 15 versions

C-Phrase: A system for building robust natural language interfaces to databases M Minock – Data & Knowledge Engineering, 2010 – Elsevier … The first is that standard, off-the-shelf relational databases are sufficiently expressive to back NLIs. The second is that any approach must include a generation component that can accurately paraphrase database queries back to the user in natural language. … Cited by 32 Related articles All 6 versions

Recognizing textual entailment with logical inference P Clark, P Harrison – Text Analysis Conference (TAC 2008) Workshop- …, 2008 – Citeseer … For verbs, the axioms are of the form: isa(V,verb-sense) [& subject(V,X)] [& object(V,Y)] ? .. All possible senses are considered in the elaboration. We discuss the benefits and limi- tations of this shortly). • The DIRT inference rule (paraphrase) database (Lin and Pantel, 2001). … Cited by 26 Related articles All 3 versions

Using bilingual parallel corpora for cross-lingual textual entailment Y Mehdad, M Negri, M Federico – … of the 49th Annual Meeting of the …, 2011 – dl.acm.org … the precision of the extracted paraphrases. In our work we used available2 paraphrase databases for English and Spanish which have been extracted using the method previously outlined. Moreover, in order to experiment … Cited by 42 Related articles All 10 versions

An Entailment-Based Approach to the QA4MRE Challenge. P Clark, P Harrison, X Yao – CLEF (Online Working Notes/Labs/Workshop), 2012 – Citeseer … fragments. To identify these possible entailment relationships we use three knowledge resources, namely WordNet, ParaPara (a large paraphrase database from Johns Hopkins University), and the DIRT para- phrase database. … Cited by 4 Related articles All 4 versions

Augmenting WordNet for deep understanding of text P Clark, C Fellbaum, JR Hobbs, P Harrison… – Proceedings of the …, 2008 – dl.acm.org … We are testing our work with BLUE, Boeing’s Language Understanding Engine, which we first describe. We then present the WordNet augmentations that we are de- veloping, and our experience with these as well as with the DIRT paraphrase database. Page 3. … Cited by 17 Related articles All 8 versions

ReEscreve: a translator-friendly multi-purpose paraphrasing software tool A Barreiro, LM Cabral – … of the Workshop Beyond Translation Memories …, 2009 – linguateca.pt … Then the support verb construction expression is matched against the paraphrase database (developed in NooJ) and the corresponding candidates are retrieved with the inflectional features of the support verb in the original expression. … Cited by 13 Related articles All 4 versions

The DCU dependency-based metric in WMT-MetricsMATR 2010 Y He, J Du, A Way, J van Genabith – … of the Joint Fifth Workshop on …, 2010 – dl.acm.org … 4 Capturing Variations in Language In (Owczarzak et al., 2007), lexical variations at the word-level are captured by WordNet. We use a Porter stemmer and a unigram paraphrase database to allow more lexical variations. With … Cited by 14 Related articles All 19 versions

Improving lexical embeddings with semantic knowledge M Yu, M Dredze – Proceedings of the 52nd Annual Meeting of the …, 2014 – aclweb.org … We extend the objective to include prior knowledge about synonyms from semantic resources; we consider both the Paraphrase Database (Ganitkevitch et al., 2013) and WordNet (Fellbaum, 1999), which an- notate semantic relatedness between words. … Cited by 4 Related articles All 8 versions

Exploiting paraphrases and deferred sense commitment to interpret questions more reliably P Clark, P Harrison – Proceedings of the 23rd International Conference …, 2010 – dl.acm.org … In our work on posing questions to a bi- ology knowledge base, we address this brittleness in two ways: First, we exploit the DIRT paraphrase database to intro- duce alternative phrasings of a question; Second, we defer word sense and se- mantic role commitment until … Cited by 3 Related articles All 8 versions

Echo Chamber: A Game for Eliciting a Colloquial Paraphrase Corpus. C Brockett, WB Dolan – AAAI Spring Symposium: Knowledge Collection …, 2005 – aaai.org … “Battleship” Phase “Hangman” Phase Player Model Database Paraphrase Database Fig, 1. Data collection and evaluation in Echo Chamber Automated Validation Page 5. attracting sufficient numbers of returning players to sustain a data collection effort . … Cited by 7 Related articles All 4 versions

The Multilingual Paraphrase Database J Ganitkevitch, C Callison-Burch – Proceedings of the Ninth …, 2014 – robotics.upenn.edu Abstract We release a massive expansion of the paraphrase database (PPDB) that now includes a collection of paraphrases in 23 different languages. The resource is derived from large volumes of bilingual parallel data. Our collection is extracted and ranked using state … Cited by 1 Related articles All 4 versions

BLUE-Lite: a knowledge-based lexical entailment system for RTE6 P Clark, P Harrison – Proc. of TAC, 2010 – Citeseer … sentences. To compare lexical items, BLUE-Lite exploits linguistic and world knowledge drawn from WordNet and the DIRT paraphrase database. … snow#n2 –WN-substance- of? snowball#n4 2.2.2 The DIRT Paraphrase Database In … Cited by 14 Related articles All 9 versions

Combining Machine Translation Output with Open Source: The Carnegie Mellon Multi-Engine Machine Translation Scheme K Heafield, A Lavie – The Prague Bulletin of Mathematical Linguistics, 2010 – degruyter.com … In fact, we replaced the position-based artificial alignments of (Heafield et al., 2009) with the paraphrase database, finding similar performance. The MEMT/Alignment directory contains a Java class that calls the publicly available METEOR code to perform pairwise alignments. … Cited by 14 Related articles All 17 versions

Machine reading as a process of partial question-answering P Clark, P Harrison – Proceedings of the NAACL HLT 2010 First …, 2010 – dl.acm.org … 3.1 Paraphrases A relatively recent advance in NLP has been the automatic construction of paraphrase databases (containing phrasal patterns with approximately equivalent meaning), built by finding phrases that occur in distributionally similar contexts (eg, Dras et al, 2005). … Cited by 2 Related articles All 10 versions

ETS: Discriminative edit models for paraphrase scoring M Heilman, N Madnani – Proceedings of the First Joint Conference on …, 2012 – dl.acm.org … probability: p(e1|e2) ? ? f p(e1|f )p(f |e2) We used the same phrasal paraphrase database as in TERp (Snover et al., 2009a), which was extracted from an Arabic-English newswire bitext containing a million sentences. A few … Cited by 5 Related articles All 9 versions

A statistics-based semantic textual entailment system P Pakray, U Barman, S Bandyopadhyay… – Advances in Artificial …, 2011 – Springer … sentence pairs. It tries to determine if the logic for the H sentence subsumes some inference- elaborated version of the T sentence, using WordNet and the DIRT paraphrase database as its sources of knowledge. The Monte … Cited by 7 Related articles All 6 versions

The PASCAL recognising textual entailment challenge I Dagan, O Glickman, B Magnini – Machine learning challenges. …, 2006 – Springer … http://brahms.isi.edu:8080/textmap/ – Relation Recognition dataset, from University of Illinois at Urbana- Champaign. http://l2r.cs.uiuc.edu/˜cogcomp/ – DIRT paraphrase database (online demo), from the University of southern California. … Cited by 740 Related articles All 27 versions

Facilitating translation using source language paraphrase lattices J Du, J Jiang, A Way – Proceedings of the 2010 Conference on Empirical …, 2010 – dl.acm.org Page 1. Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, pages 420–429, MIT, Massachusetts, USA, 9-11 October 2010. cO2010 Association for Computational Linguistics Facilitating … Cited by 24 Related articles All 21 versions

Recognizing textual entailment: Rational, evaluation and approaches–erratum I Dagan, B Dolan, B Magnini… – Natural Language …, 2010 – Cambridge Univ Press … pairs, to, one, identify where and what kinds of world knowledge are needed to identify and justify the entailment and, two, to discuss several existing resources and their capacity for supplying that knowledge (such as WordNet, the DIRT paraphrase database, FrameNet). … Cited by 114 Related articles All 19 versions

Constructing a textual KB from a biology TextBook P Clark, P Harrison, N Balasubramanian… – Proceedings of the Joint …, 2012 – dl.acm.org … In the simplest case this is just structure matching, but more commonly the system explores rewrites of the sentences using four synonym and paraphrase resources, namely: WordNet (Fellbaum, 1998); the DIRT paraphrase database (Lin and Pantel, 2001); the ParaPara … Cited by 1 Related articles All 8 versions

Study of the AKBC/Requirements for Passing an Elementary Science Test P Clark, P Harrison… – Proceedings of the AKBC- …, 2013 – openreview.net … We currently use: a parse-derived logical form database; an OpenIE triple (proposition) store (Etzioni et al., 2011); The Bio101 ontology (Chaudhri et al, 2013); WordNet (Fellbaum, 1998); the PPDB paraphrase database (Chan et al, 2011), derived from a large corpus of parallel … Cited by 1 Related articles

Retrofitting Word Vectors to Semantic Lexicons M Faruqui, J Dodge, SK Jauhar, C Dyer, E Hovy… – arXiv preprint arXiv: …, 2014 – arxiv.org … text corpora. Although such statistics are informative, they disre- gard easily accessible (and often carefully curated) information archived in se- mantic lexicons such as WordNet, FrameNet, and the Paraphrase Database. This … Cited by 1 Related articles All 2 versions

UoW: NLP techniques developed at the University of Wolverhampton for Semantic Similarity and Textual Entailment R Gupta, H Béchara, I El Maarouf, C Orasan – SemEval 2014, 2014 – aclweb.org … 3.2 Paraphrasing Features We used the PPDB paraphrase database (Ganitke- vitch et al., 2013) to get the paraphrases. We used lexical and phrasal paraphrases of “L” size. … We extended each set with paraphrases for each n- gram available from paraphrase database. … Cited by 1 Related articles All 6 versions

A study of the knowledge base requirements for passing an elementary science test P Clark, P Harrison, N Balasubramanian – Proceedings of the 2013 …, 2013 – dl.acm.org … We currently use: a parse-derived logical form database; an OpenIE triple (proposition) store [6]; The Bio101 ontology [5]; WordNet [7]; the PPDB paraphrase database [4], derived from a large corpus of parallel texts using bilingual pivoting; and the DIRT paraphrase database … Cited by 2 Related articles All 2 versions

PARMA: A Predicate Argument Aligner. T Wolfe, B Van Durme, M Dredze, N Andrews, C Beller… – ACL (2), 2013 – aclweb.org … Juri Ganitkevitch, Benjamin Van Durme, and Chris Callison-Burch. 2013. Ppdb: The paraphrase database. In North American Chapter of the Asso- ciation for Computational Linguistics (NAACL). Xianpei Han and Le Sun. 2011. … Cited by 5 Related articles All 12 versions

Incorporating Paraphrasing in Translation Memory Matching and Retrieval R Gupta, O Constantin – … of the 17th Annual Conference of EAMT, 2014 – researchgate.net … This means that even if a paraphrased segment is available in the TM, the TM systems have no way to retrieve such segments. In this pa- per we try to mitigate this problem by using ex- isting paraphrase databases. … 2.3 PPDB:The Paraphrase Database … Cited by 1 Related articles

Recognize Textual Entailment by the lexical and semantic matching Y Du, C Yao, J Liu – Computer Application and System …, 2010 – ieeexplore.ieee.org … The system obtains the accuracy of 6l.5 on RTE-5 test set. In addition, the knowledge resources are involved in the RTE system [8,9,10], such as DIRT paraphrase database, WordNet, Wikipedia and so on. They give great help for this task. II. … Cited by 4 Related articles All 2 versions

Do Scripts solve NLP? P Clark, BP Works – 2008 – Citeseer … As a point of interest, the DIRT paraphrase database does include paraphrases for “remove X from Y” (eg, “pull X from Y”) but “force X to get out of Y” is not one of them. One can view this matching problem as an example of the “recognizing textual entailment” challenge. … Cited by 1 Related articles All 4 versions

NICT speech and language resources and corpora S Nakamura, K Torisawa, H Kawai… – Proceedings of Oriental …, 2010 – desceco.org … score. A-6. Paraphrase database of Japanese patterns This resource consists of string patterns with two slots, such as “X causes Y” and their paraphrases, extracted from more than 5 billion dependency parsed sentences. For … Cited by 1 Related articles

Probabilistic soft logic for semantic textual similarity I Beltagy, K Erk, R Mooney – Proceedings of Association for …, 2014 – cs.utexas.edu Page 1. Probabilistic Soft Logic for Semantic Textual Similarity Islam Beltagy§ Katrin Erk† Raymond Mooney§ §Department of Computer Science †Department of Linguistics The University of Texas at Austin Austin, Texas 78712 … Cited by 8 Related articles All 6 versions

Paraphrase extraction from parallel news corpora B Mizrahi – 2006 – Citeseer … For instance, in Text Summarization, we can use alternative paraphrases to change the length of a summary. So a generic paraphrase database is a valuable resource and this study focuses on creating one such database using parallel news corpora. … Cited by 1 Related articles All 2 versions

Building a Free, General-Domain Paraphrase Database for Japanese M Mizukami, G Neubig, S Sakti, T Toda… – Proc. COCOSDA, 2014 – isw3.naist.jp ABSTRACT Previous works have used parallel corpora and alignment techniques from phrase-based statistical machine translation to extract and generate paraphrases. In Japanese, paraphrases for a number of paraphrase categories or domains have been … Related articles All 3 versions

Augmenting FrameNet Via PPDB P Rastogi, B Van Durme – ACL 2014, 2014 – anthology.aclweb.org … In this work we take a different approach and attempt to directly increase the coverage of the FrameNet corpus by automatically expanding the collection of training examples via PPDB, The Paraphrase Database (Ganitkevitch et al., 2013). … PPDB: The paraphrase database. … Related articles All 11 versions

The Meaning Factory: Formal Semantics for Recognizing Textual Entailment and Determining Semantic Similarity N Contradiction – researchgate.net … Paraphrasing techniques ? Rephrase sentences by using PPDB, The Paraphrase Database (Ganitkevitch et al., 2013) t A group of kids is playing in a yard and an old man is standing in the background … a man Paraphrase Database (PPDB) RTE with the semantic parser Boxer …

Generating Comprehension Questions Using Paraphrase YM Tseng, YT Huang, MC Chen, YS Sun – Technologies and Applications …, 2014 – Springer … Besides coreference, resources like the ParaPhrase DataBase (PPDB) [5], WordNet and context-sensitive inference rules for predicates [12] are also included. These resources provide a diversity of paraphrases, from lexical, phras- al, syntactic to referential. … Related articles All 3 versions

MWE S Hartmann, I Gurevych – spraakbanken.gu.se … Alternative: Generate Paraphrases from Parallel Text ? Monolingual Translation Tables ? Multilingual Translation Tables: EN?DE & DE? EN leads to EN paraphrases („Pivoting“) ? Resource based on Pivoting: PPDB („The Paraphrase Database“), Ganitkevitch et al. (2013) … Related articles

Unsupervised Phrasal Near-Synonym Generation from Text Corpora D Gupta, J Carbonell, A Gershman, S Klein, D Miller – 2015 – cs.cmu.edu … The Paraphrase Database: We also compare our methods to the machine translation technique by Ganit- kevitch et al. (2013), PPDB 1.0. … Ganitkevitch, J., Van Durme, B., & Callison-Burch, C. (2013). Ppdb: The paraphrase database. In Proceedings of NAACL- HLT (pp. … Related articles All 2 versions

Poetry of the Crowd: A Human Computation Algorithm to Convert Prose into Rhyming Verse Q Chen, C Lei, W Xu, E Pavlick… – … AAAI Conference on …, 2014 – seas.upenn.edu … Source Sentences Paraphrase Database (PPDB) Tokenize Word Substiution Phrase Substitution … [Ganitkevitch, VanDurme, and Callison-Burch 2013] Ganitkevitch, J.; VanDurme, B.; and Callison-Burch, C. 2013. PPDB: The paraphrase database. In Proceedings of NAACL. … Related articles All 7 versions

Intelligent Translation Memory Matching and Retrieval Metric Exploiting Linguistic Technology R Gupta, H Bechara, C Orasan – Conference Chairs and Editors of the … – tradulex.com … We used the PPDB paraphrase database (Ganitkevitch et al., 2013) to identify paraphrases. After extracting these features, we employed a support vector machine (SVM) in order to build a regression model to predict semantic similarity. … 2013. Ppdb: The paraphrase database. … Related articles All 2 versions

Evaluation of the New Paraphrase and Question Formulation Capability in AURA P Clark – 2010 – cs.utexas.edu … same thing. To make sense of unanticipated phrasings in a question, the NewQF makes use of the DIRT paraphrase database to explore alternative phrasings when a phrase in a question cannot be directly understood. As … All 5 versions

A Unified Probabilistic Approach for Semantic Clustering of Relational Phrases A Grycner, G Weikum, J Pujara… – 4th Workshop on …, 2014 – people.mpi-inf.mpg.de … Unlike PATTY, WiseNet or our PSL models, both of the aforementioned systems work with untyped relational phrases. The PPDB paraphrase database [11] uses a very different approach, employing bilingual texts. … PPDB: The paraphrase database. … Related articles All 4 versions

End-User Programming System with Natural Language Text and Direct Manipulation N Kaneko, T Onisawa – SCIS & ISIS, 2006 – jlc.jst.go.jp … After the reasoning, the system performs translation or paraphrasing according to the result of the reasoning. When there are no proper cases, the system asks users for paraphrasing and adds the paraphrase to the paraphrase database. … Related articles All 2 versions

Generating Acrostics via Paraphrasing and Heuristic Search B Stein, M Hagen, C Bräutigam – uni-weimar.de … and Hovy, 2011). We include the paraphrase database (Ganitkevitch et al., 2013)—a database of extracted patterns from such large scale corpora—as one source of potential paraphrases in our algorithm. Compared to the … Related articles All 4 versions

PARADIGM: Paraphrase Diagnostics through Grammar Matching J Weese, J Ganitkevitch, C Callison-Burch – EACL 2014, 2014 – aclweb.org … The size of the extracted grammars is shown in Table 2. We also used version 0.2 of the SCFG-based paraphrase collection known as the ParaPhrase DataBase or PPDB (Ganitkevitch et al., 2013). … 2013. PPDB: The paraphrase database. In Proc. NAACL. … Related articles All 7 versions

Sentence simplifications for Multi-word Expressions S Narayan – 2014 – typo.uni-konstanz.de … 1179, Edinburgh, Scotland, UK. Association for Computa- tional Linguistics. [Ganitkevitch et al., 2013] Ganitkevitch, J., Van Durme, B., and Callison-Burch, C. (2013). Ppdb: The paraphrase database. In Proceedings of the 2013 … Related articles

Extracting Topically Related Synonyms from Twitter using Syntactic and Paraphrase Data MA Antoniak – 2015 – digital.lib.washington.edu … than previous synonyms resources such as WordNet (Miller, 1995), the Paraphrase Database (PPDB) (Ganitkevitch et al., 2013), or normalization lexicons (Han et al., 2012) (Xu et al., 2013). … Ganitkevitch et al. (2013) created the Paraphrase Database (PPDB)1, a database of …

Automatic Identification of English Collocation Errors based on Dependency Relations ZM Gao – Sponsors: National Science Council, Executive Yuan, …, 2013 – aclweb.org … by Chinese learners of English. They draw on a learner corpus, a reference corpus, a dictionary of synonyms derived from WordNet, and a paraphrase database compiled using learner data. Addressing the same problem of … Related articles All 6 versions

Machine Translation within One Language as a Paraphrasing Technique P Barancíková, A Tamchyna – V?era Kurková, Lukáš Bajer (Eds.) – itat.ics.upjs.sk … paraphrasing tables. A new paraphrase database PPDB [12] for Czech language should be re- leased any time now. Furthermore … 1998. [12] Juri Ganitkevitch and Chris Callison-Burch. The Multilin- gual Paraphrase Database. In Proceedings … Related articles All 2 versions

Lexical entailment J Wieting – 2014 – ideals.illinois.edu … information. We use synonyms, antonyms and hypernyms from WordNet, and lexical relationships from the paraphrase database [Ganitkevitch et al., 2013] as a source of knowledge and then create a new entailment measure. … Related articles

A Programming System for Text-Editing Task Using Japanese Natural Language Text and Direct Manipulation N Kaneko, T Onisawa – … , Man and Cybernetics, 2006. SMC’06. …, 2006 – ieeexplore.ieee.org … Afterreasoning, the system performs translation or paraphrasing according to the result of the reasoning. When there are no proper cases,the system asks users for para- phrasing and adds the paraphrase to the paraphrase database. … Related articles

Use of Multi-Strategy to Textual Entailment Recognition Y DU, M HE – Journal of Computational Information Systems, 2011 – jofcis.com … They are involved in the RTE system[7,9,10], such as DIRT paraphrase database, WordNet and Wikipedia. In the following, we will first describe the structure of the textual entailment recognition system. Section 3 describes the lexical and semantic matching method. … Related articles

An inference-based approach to recognizing entailment P Clark, P Harrison – Proc. of TAC, 2009 – nist.gov … Our source of inference rules is the DIRT inference rule (paraphrase) database (Lin and Pantel, 2001, Pantel et al, 2007). The database contains 12 mil- lion rules, discovered automatically from text, of form: (X relation1 Y) ? (X relation2 Y) … Cited by 17 Related articles All 5 versions

Semi-Markov Phrase-Based Monolingual Alignment. X Yao, B Van Durme, C Callison-Burch, P Clark – EMNLP, 2013 – aclweb.org Page 1. Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 590–600, Seattle, Washington, USA, 18-21 October 2013. cO2013 Association for Computational Linguistics Semi-Markov Phrase-based Monolingual Alignment … Cited by 4 Related articles All 12 versions

cRhyme: A Computer Engine for Generating Rhyming Sentences G Shotan, R Ferrer – stanford.edu … References [1] I. Androutsopoulos and P. Malakasiotis. A survey of para- phrasing and textual entailment methods. J. Artif. Int. Res., 38(1):135–187, May 2010. [2] J. Ganitkevitch, B. Van Durme, and C. Callison-Burch. Ppdb: The paraphrase database. … Related articles

Exploiting Parallel News Streams for Unsupervised Event Extraction C Zhang, S Soderland, DS Weld – Transactions of the …, 2015 – tacl2013.cs.columbia.edu Page 1. Exploiting Parallel News Streams for Unsupervised Event Extraction Congle Zhang, Stephen Soderland & Daniel S. Weld Computer Science & Engineering University of Washington Seattle, WA 98195, USA {clzhang, soderlan, weld}@cs.washington.edu Abstract …

Back to Basics for Monolingual Alignment: Exploiting Word Similarity and Contextual Evidence MA Sultan, S Bethard, T Sumner – Transactions of the …, 2014 – tacl2013.cs.columbia.edu … We use the Paraphrase Database (PPDB) (Ganitkevitch et al., 2013), which is a large resource of lexical and phrasal paraphrases constructed using bilingual pivoting (Bannard and Callison-Burch, 2005) over large parallel corpora. 3 System … Related articles All 8 versions

Linguistic steganography on Twitter: hierarchical language modeling with manual interaction A Wilson, P Blunsom, AD Ker – IS&T/SPIE …, 2014 – proceedings.spiedigitallibrary.org … 3.1 The Translation Model The system transforms the cover object of these using the recently released Paraphrase Database (PPDB).26 This is a database of paraphrase rules, extracted from a number of parallel bilingual corpora using the approach detailed in Ref. … Related articles All 6 versions

UMBC EBIQUITY-CORE: Semantic textual similarity systems L Han, A Kashyap, T Finin, J Mayfield… – Proceedings of the …, 2013 – aclweb.org … Association for Computational Linguistics. [Ganitkevitch et al. 2013] Juri Ganitkevitch, Ben- jamin Van Durme, and Chris Callison-Burch. 2013. PPDB: The paraphrase database. In HLT-NAACL 2013. [Han and Finin2013] Lushan Han and Tim Finin. 2013. … Cited by 19 Related articles All 13 versions

Phrase-level System Combination for Machine Translation Based on Target-to-Target Decoding WY Ma, K McKeown – 2012 – academiccommons.columbia.edu … Fellbaum, 1998) respectively. Sequences of words in the reference are considered to be paraphrases of a sequence of words in the hypothesis if that phrase pair occurs in the TERp’s own paraphrase database. One valuable … Cited by 1 Related articles All 8 versions

Discriminative Improvements to Distributional Sentence Similarity. Y Ji, J Eisenstein – EMNLP, 2013 – jiyfeng.github.io … Morgan Kauf- mann Publishers Inc. Juri Ganitkevitch, Benjamin Van Durme, and Chris Callison-Burch. 2013. PPDB: The Paraphrase Database. In Proceedings of NAACL, pages 758–764. Association for Computational Linguistics. Weiwei Guo and Mona Diab. 2012. … Cited by 3 Related articles All 8 versions

Extracting context-rich entailment rules from wikipedia revision history E Cabrio, B Magnini, A Ivanova – Proceedings of the 3rd Workshop on …, 2012 – dl.acm.org … relevant to the proposed approach. As for paraphrase, Sekine’s Paraphrase Database (Sekine, 2005) is collected using an unsupervised method, and focuses on phrases connecting two Named Entities. In the Microsoft Research … Cited by 3 Related articles All 9 versions

SemEval-2014 Task 3: Cross-level semantic similarity D Jurgens, MT Pilehvar, R Navigli – SemEval 2014, 2014 – anthology.aclweb.org Page 37. Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), pages 17–26, Dublin, Ireland, August 23-24, 2014. SemEval-2014 Task 3: Cross-Level Semantic Similarity David Jurgens, Mohammad … Cited by 11 Related articles All 9 versions

OpenLogos MT and the SAL representation language B Scott, A Barreiro – 2009 – rua.ua.es … se- mantically equivalent words or expressions (synonyms or paraphrasing capabilities), following three main steps: (1) recognition of a word, phrase or expression in a text and annotation; (2) annotated expressions are matched against a paraphrase database (de- veloped in … Cited by 10 Related articles All 4 versions

Joshua 5.0: Sparser, better, faster, server M Post, J Ganitkevitch, L Orland… – Proceedings of the …, 2013 – anthology.aclweb.org … In Proceedings of the Workshop on Statistical Machine Translation. Juri Ganitkevitch, Chris Callison-Burch, and Benjamin Van Durme. 2013. Ppdb: The paraphrase database. In Proceedings of HLT/NAACL. D. Graff, J. Kong, K. Chen, and K. Maeda. 2003. English gigaword. … Cited by 9 Related articles All 16 versions

The English Adjective Lexical Collocation S Aisah – 2009 – publication.gunadarma.ac.id … The system also makes use of a Dictionary of Synonyms derived from Word Net to discover the potential collocational errors in learners’ input, as well as a Paraphrase Database gathered from the learners themselves to help diagnose un-collocational learner phrase. 2 Page 4. … Related articles All 2 versions

Automatic Evaluation Of Computer Science thesis Using Domain Ontology MM Hussain, SK Srivatsa – ijser.org … First, the authors used a system called BLUE (Boeing Language Understanding Engine) to perform a full semantic interpretation of both sentences. Then, they used knowledge obtained from WordNet and DIRT paraphrase database to infer a relationship. … Related articles All 2 versions

Understanding Instructions on Large Scale for Human-Robot Interaction J Xie, X Chen – Proceedings of the 2014 IEEE/WIC/ACM International …, 2014 – dl.acm.org Page 1. Understanding Instructions on Large Scale for Human-Robot Interaction Jiongkun Xie and Xiaoping Chen Multi-Agents Systems Lab., University of Science and Technology of China, He Fei, China devilxjk@mail.ustc.edu.cn, xpchen@ustc.edu.cn … Related articles All 3 versions

The Meaning Factory: Formal Semantics for Recognizing Textual Entailment and Determining Semantic Similarity J Bjerva, J Bos, R van der Goot, M Nissim – SemEval 2014, 2014 – aclweb.org … Juri Ganitkevitch, Benjamin VanDurme, and Chris Callison-Burch. 2013. PPDB: The paraphrase database. In Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2013), Atlanta, Georgia, June. … Cited by 2 Related articles All 10 versions

Lexicon propagation for learning a large-scale semantic parser J Xie, X Chen – Audio, Language and Image Processing ( …, 2014 – ieeexplore.ieee.org … The paraphrase database they require is specific for QA domain, which makes their approach hard to be used in other domains. Particularly, it is hard to employ their approach for interpreting instructions, since there is no such … Related articles

Semantic parsing using distributional semantics and probabilistic logic I Beltagy, K Erk, R Mooney – ACL 2014, 2014 – acl2014.org … Juri Ganitkevitch, Benjamin Van Durme, and Chris Callison-Burch. 2013. PPDB: The paraphrase database. In Proceedings of North American Chap- ter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT-13). … Cited by 5 Related articles All 11 versions

Large-Scale Paraphrasing for Natural Language Understanding. J Ganitkevitch – HLT-NAACL, 2013 – Citeseer … In Proceedings of *SEM. Association for Computational Linguistics. Juri Ganitkevitch, Chris Callison-Burch, and Benjamin Van Durme. 2013. Ppdb: The paraphrase database. In Proceedings of HLT/NAACL. Philipp Koehn, Franz Josef Och, and Daniel Marcu. 2003. … Related articles All 7 versions

A Review of NLP Based Upon Semantic Analysis P Kaur, V Pushe, R Kaur – 2014 – ijcsmc.com … [9]. Juri Ganitkevitch, Benjamin Van Durme, and Chris Callison-Burch. 2013. PPDB: The paraphrase database. In Proceedings of North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL- HLT-13). [10]. … Related articles All 2 versions

Exploring the Utility of ResearchCyc for Reasoning from Natural Language C Manning, A Ng – 2006 – DTIC Document … substitutions of less-informative predicates. Then again, there isn’t an extensive paraphrase database and it’s not clear how robust this method would be, but the sparsity would at least trim down the search space. 3. QA 594 T … Related articles

Improving the quality of text understanding by delaying ambiguity resolution DS Kim, K Barker, B Porter – … of the 23rd International Conference on …, 2010 – dl.acm.org … representations. (Clark and Harrison, 2010) uses paraphrase databases and a hand-built knowledge base to resolve underspecified representations. Different architectures have been proposed to improve the pipeline architecture. … Cited by 5 Related articles All 8 versions

Reduction of ambiguity due to synonym and Homographs in Punjabi Language N Kaur, V Pushe – ijecs.in … [9]. Juri Ganitkevitch, Benjamin Van Durme, and Chris Callison-Burch. 2013. PPDB: The paraphrase database. In Proceedings of North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT-13). [10]. … Related articles All 2 versions

A novel approach to make NLP predictive and non-ambigious in Punjabi Language P Kaur, EV Pushe – 2014 – ijcsma.com … [13]. Juri Ganitkevitch, Benjamin Van Durme, and Chris Callison-Burch. 2013. PPDB: The paraphrase database. In Proceedings of North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT-13). [14]. … Related articles All 3 versions

Adapting Spoken Dialog Systems Towards Domains and Users M Sun – 2015 – cs.cmu.edu … human judgment, requiring no additional domain 9 Page 20. February 13, 2015 DRAFT corpus [58]. We also use the Paraphrase database developed by Ganitkevitch et al. [62], which provides various sizes — higher coverage …

Improving fuzzy matching through syntactic knowledge T Vanallemeersch, V Vandeghinste – Conference Chairs and Editors of …, 2014 – asling.org … Lexical knowledge may be exploited by matching words in flat sequences through lexical similarity. For instance, Gupta (2014) uses a paraphrase database. Considering tree-based matching methods, the aspect of speed should not be neglected. … Related articles All 3 versions

Towards a probabilistic model for lexical entailment E Shnarch, J Goldberger, I Dagan – … of the TextInfer 2011 Workshop on …, 2011 – dl.acm.org … They utilized both WordNet and the DIRT paraphrase database (Lin and Pantel, 2001). With WordNet, they used one set of relations to identify the concept of a term while another set of relations was used to identify entailment between concepts. … Cited by 4 Related articles All 11 versions

DLS @CU: Sentence Similarity from Word Alignment MA Sultan, S Bethard, T Sumner – SemEval 2014, 2014 – aclweb.org … Burch. 2013. PPDB: The Paraphrase Database. In Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics, NAACL-HLT’13, pages 758-764, Atlanta, Georgia, USA. … All 6 versions

Natural Language Semantics using Probabilistic Logic I Beltagy, RJ Mooney, K Erk – cs.utexas.edu Page 1. Natural Language Semantics using Probabilistic Logic Islam Beltagy Department of Computer Sciences University of Texas at Austin Austin, TX 78712 beltagy@cs.utexas.edu Doctoral Dissertation Proposal Supervising Professors: Raymond J. Mooney, Katrin Erk … Related articles All 2 versions

Japanese Argument Reordering Based on Dependency Structure for Statistical Machine Translation GOH Chooi-Ling, T Watanabe… – IEICE TRANSACTIONS on …, 2012 – search.ieice.org … decoding. In previous work, more resources, such as parallel corpora other than the one used for building translation model, were needed to build the paraphrase databases, but only a parser is needed for word reordering. … Related articles All 6 versions

Be principled! A Probabilistic Model for Lexical Entailment E Shnarch, J Goldberger, I Dagan – cs.bgu.ac.il … They utilized both WordNet and the DIRT paraphrase database (Lin and Pantel, 2001). With WordNet, they used one set of relations to identify the concept of a term while another set of relations was used to identify entailment between concepts. … Related articles

An Introduction to Question Answering over Linked Data C Unger, A Freitas, P Cimiano – Reasoning Web. Reasoning on the Web …, 2014 – Springer Page 1. An Introduction to Question Answering over Linked Data Christina Unger 1 , André Freitas 2 , and Philipp Cimiano 1 1 CITEC, Bielefeld University, Inspiration 1, 33615 Bielefeld 2 Insight, National University of Galway (NUIG), Galway Abstract. … Related articles All 4 versions

Implementation of Reduction of Ambiguity due to Synonyms in Punjabi Language N Kaur, V Pushe – 2014 – ijcsma.com … [9]. Juri Ganitkevitch, Benjamin Van Durme, and Chris Callison-Burch. 2013. PPDB: The paraphrase database. In Proceedings of North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT-13). [10]. … Related articles All 2 versions

Cross-Lingual Textual Entailment and Applications Y Mehdad – 2012 – eprints-phd.biblio.unitn.it Page 1. PhD Dissertation International Doctorate School in Information and Communication Technologies DISI – University of Trento Cross-Lingual Textual Entailment and Applications Yashar Mehdad Advisor: Prof. Marcello Federico … Related articles

UTexas: Natural Language Semantics using Distributional Semantics and Probabilistic Logic I Beltagy, S Roller, G Boleda, K Erk… – SemEval 2014, 2014 – anthology.aclweb.org … Juri Ganitkevitch, Benjamin Van Durme, and Chris Callison-Burch. 2013. PPDB: The paraphrase database. In Proceedings of North American Chap- ter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT-13). … Cited by 2 Related articles All 8 versions

Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks KS Tai, R Socher, CD Manning – arXiv preprint arXiv:1503.00075, 2015 – arxiv.org … 2014). These systems are heavily feature engineered, generally using a combination of surface form overlap features and lexical distance features de- rived from WordNet or the Paraphrase Database (Ganitkevitch et al., 2013). …

Textual Entailment A Iftene – EUROLAN 2007 Summer School Alexandru Ioan Cuza …, 2009 – profs.info.uaic.ro Page 1. “Al. I. Cuza” University of Ia?i Faculty of Computer Science TEXTUAL ENTAILMENT PhD Student Adrian Iftene Supervisor Professor Dr. Dan Cristea – 2009 – Page 2. Abstract Recognising Textual Entailment (RTE) was … Cited by 17 Related articles All 5 versions

Applied textual entailment O Glickman – 2006 – eprints.pascal-network.org Page 1. BAR ILAN UNIVERSITY APPLIED TEXTUAL ENTAILMENT Oren Glickman Department of Computer Science Ph.D. Thesis Submitted to the Senate of Bar Ilan University Ramat Gan, Israel June 2006 Page 2. This work … Cited by 20 Related articles All 6 versions

User review sites as a resource for large-scale sociolinguistic studies D Hovy, A Johannsen, A Søgaard – dirkhovy.com Page 1. DRAFT User review sites as a resource for large-scale sociolinguistic studies Dirk Hovy Center for Language Technology University of Copenhagen, Denmark Njalsgade 140 dirk@cst.dk Anders Johannsen Center for … Related articles

Data-driven approaches for paraphrasing across language variations W Xu – 2014 – cs.nyu.edu Page 1. DATA-DRIVEN APPROACHES FOR PARAPHRASING ACROSS LANGUAGE VARIATIONS by Wei Xu A dissertation submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy Department of Computer Science New York University … Cited by 1 Related articles All 11 versions

The integration of machine translation and translation memory Y He – 2011 – localisation.ie Page 1. The Integration of Machine Translation and Translation Memory Yifan He BA, MA A dissertation submitted in fulfilment of the requirements for the award of Doctor of Philosophy (Ph.D.) to the Dublin City University School of Computing Supervisors: Prof. … Cited by 5 Related articles All 9 versions

Asymmetric Distributional Similarity Measures to Recognize Textual Entailment by Generality S Pais – 2013 – pastel.archives-ouvertes.fr Page 1. Asymmetric Distributional Similarity Measures to Recognize Textual Entailment by Generality Sebasti˜ao Pais To cite this version: Sebasti˜ao Pais. Asymmetric Distributional Similarity Measures to Recognize Textual Entail- ment by Generality. Other. … Related articles All 18 versions

Hybrid System Combination for Machine Translation: An Integration of Phrase-level and Sentence-level Combination Approaches WY Ma – 2014 – academiccommons.columbia.edu Page 1. Hybrid System Combination for Machine Translation: An Integration of Phrase-level and Sentence-level Combination Approaches Wei-Yun Ma Submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy … Related articles All 2 versions

Unsupervised learning of relation detection patterns E Gonzàlez Pellicer, J Turmo Borras – 2012 – tdx.cat Page 1. ADVERTIMENT. L’accés als continguts d’aquesta tesi doctoral i la seva utilització ha de respectar els drets de la persona autora. Pot ser utilitzada per a consulta o estudi personal, així com en activitats o materials d’investigació i docència en els termes establerts a l’art. … Related articles All 3 versions

Development and Utility of Automatic Language Processing Technologies. Volume 2 B Ore, J Gwinnup, S Thorn, M Hutt, D Hoeferlin… – 2014 – DTIC Document Page 1. AFRL-RH-WP-TR-2014-0052 Development and Utility of Automatic Language Processing Technologies, Volume II Brian Ore Jeremy Gwinnup Stephen Thorn Michael Hutt David Hoeferlin William Coate David Snyder … Related articles

Inducing Implicit Arguments via Cross-document Alignment: A Framework and its Applications M Roth – 2014 – archiv.ub.uni-heidelberg.de Page 1. Inducing Implicit Arguments via Cross-document Alignment A Framework and its Applications Juni 2014 Dissertation zur Erlangung der Doktorwürde der Neuphilologischen Fakultät der Ruprecht-Karls-Universität Heidelberg vorgelegt von Michael Roth Page 2. … Cited by 1 Related articles All 4 versions

Machine Translation in Microblogs W Ling, LC Ist – 2013 – Citeseer Page 1. Machine Translation in Microblogs Wang Ling Ph.D. Thesis Proposal Draft Version: July 8, 2013 Language Technologies Institute School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 Thesis … Related articles All 4 versions

Predication Driven Textual Entailment MA Moruz – 2011 – profs.info.uaic.ro Page 1. “Al. I. Cuza” University of Iasi Faculty of Computer Science Predication Driven Textual Entailment 2011 PhD Student Mihai-Alex Moruz Supervisor Prof. Dr. Dan Cristea Thesis version updated and modified according to the recommendations of the reviewers. Page 2. i … Cited by 5 Related articles

Efficient Global Learning of Entailment Graphs J Berant, N Alon, I Dagan, J Goldberger – Computational Linguistics, 2011 – tau.ac.il Page 1. Efficient Global Learning of Entailment Graphs Jonathan Berant ? Computer Science Department, Stanford University Noga Alon ?? The Blavatnik School of Computer Science, Tel Aviv University Ido Dagan † Computer Science Department, Bar-Ilan University … Related articles All 3 versions

Word meaning in context: A probabilistic model and its application to Question Answering G Dinu – 2011 – scidok.sulb.uni-saarland.de Page 1. Word meaning in context: A probabilistic model and its application to Question Answering Georgiana Dinu Dissertation Presented to the Faculty of Philosophy II of Saarland University in Candidacy for the Degree of Doctor of Philosophy … Cited by 1 Related articles All 3 versions