Cross-lingual CCG Induction Kilian Evang @texttheater University - PowerPoint PPT Presentation

Introduction Derivation Projection Experiments Conclusions References Cross-lingual CCG Induction Kilian Evang @texttheater University of D¨ usseldorf 2019-06-04 NAACL-HLT 1 / 23

Introduction Derivation Projection Experiments Conclusions References Outline Introduction Derivation Projection Experiments Conclusions 2 / 23

Introduction Derivation Projection Experiments Conclusions References Combinatory Categorial Grammar We sang NP S \ NP < 0 S 3 / 23

Introduction Derivation Projection Experiments Conclusions References Combinatory Categorial Grammar We saw the car that John bought NP (S \ NP) / NP NP / N N (N \ N) / (S / NP) N (S \ NP) / NP ∗ NP T > S / (S \ NP) > 1 S / NP > 0 N \ N < 0 N > 0 > 0 NP NP > 0 S \ NP < 0 S 4 / 23

Introduction Derivation Projection Experiments Conclusions References Appeal • coordination • universal rules • syntax-semantics interface 5 / 23

Introduction Derivation Projection Experiments Conclusions References Most CCG Parsers • trained on large treebanks, or • hand-crafted 6 / 23

Introduction Derivation Projection Experiments Conclusions References David Blackwell, CC-BY-NC What about low-resource languages? 7 / 23

Introduction Derivation Projection Experiments Conclusions References Unsupervised CCG Induction? target-language text + magic = target-language CCG parser (Bisk and Hockenmaier, 2013; Bisk et al., 2015) 8 / 23

Introduction Derivation Projection Experiments Conclusions References Cross-lingual CCG Induction? English CCG parser + parallel corpus + magic = target-language CCG parser 9 / 23

Introduction Derivation Projection Experiments Conclusions References Cross-lingual CCG Induction via Derivation Projection parallel corpus + English CCG derivations + word alignments + derivation projection = target-language CCG derivations = target-language training data 10 / 23

Introduction Derivation Projection Experiments Conclusions References Derivation Projection • project lexical categories along word alignments • n:1 alignment → merge • word order difference → flip slash 11 / 23

Introduction Derivation Projection Experiments Conclusions References Example 1/3 S 2 < 0 S 2 \ NP 1 > 0 NP 3 ∗ N 4 > 0 NP 1 (S 2 \ NP 1 ) / NP 3 N 4 / N 5 N 5 He had three sons Aveva tre figli 12 / 23

Introduction Derivation Projection Experiments Conclusions References Example 1/3 S 2 < 0 S 2 \ NP 1 > 0 NP 3 ∗ N 4 > 0 NP 1 (S 2 \ NP 1 ) / NP 3 N 4 / N 5 N 5 He had three sons Aveva tre figli N 4 / N 5 12 / 23

Introduction Derivation Projection Experiments Conclusions References Example 1/3 S 2 < 0 S 2 \ NP 1 > 0 NP 3 ∗ N 4 > 0 NP 1 (S 2 \ NP 1 ) / NP 3 N 4 / N 5 N 5 He had three sons Aveva tre figli N 4 / N 5 N 5 12 / 23

Introduction Derivation Projection Experiments Conclusions References Example 1/3 S 2 < 0 S 2 \ NP 1 > 0 NP 3 ∗ N 4 > 0 NP 1 (S 2 \ NP 1 ) / NP 3 N 4 / N 5 N 5 He had three sons Aveva tre figli S 2 / NP 3 N 4 / N 5 N 5 12 / 23

Introduction Derivation Projection Experiments Conclusions References Example 1/3 S 2 < 0 S 2 \ NP 1 > 0 NP 3 ∗ N 4 > 0 NP 1 (S 2 \ NP 1 ) / NP 3 N 4 / N 5 N 5 He had three sons Aveva tre figli S 2 / NP 3 N 4 / N 5 N 5 > 0 N 4 12 / 23

Introduction Derivation Projection Experiments Conclusions References Example 1/3 S 2 < 0 S 2 \ NP 1 > 0 NP 3 ∗ N 4 > 0 NP 1 (S 2 \ NP 1 ) / NP 3 N 4 / N 5 N 5 He had three sons Aveva tre figli S 2 / NP 3 N 4 / N 5 N 5 > 0 N 4 ∗ NP 3 12 / 23

Introduction Derivation Projection Experiments Conclusions References Example 1/3 S 2 < 0 S 2 \ NP 1 > 0 NP 3 ∗ N 4 > 0 NP 1 (S 2 \ NP 1 ) / NP 3 N 4 / N 5 N 5 He had three sons Aveva tre figli S 2 / NP 3 N 4 / N 5 N 5 > 0 N 4 ∗ NP 3 > 0 S 2 12 / 23

Introduction Derivation Projection Experiments Conclusions References Example 2/3 NP 1 > 0 N 2 > 0 N 2 / N 3 > 0 NP 1 / N 2 (N 2 / N 3 ) / (N 4 / N 5 ) N 4 / N 5 N 3 a very decorative plant una pianta molto decorativa 13 / 23

Introduction Derivation Projection Experiments Conclusions References Example 2/3 NP 1 > 0 N 2 > 0 N 2 / N 3 > 0 NP 1 / N 2 (N 2 / N 3 ) / (N 4 / N 5 ) N 4 / N 5 N 3 a very decorative plant una pianta molto decorativa NP 1 / N 2 13 / 23

Introduction Derivation Projection Experiments Conclusions References Example 2/3 NP 1 > 0 N 2 > 0 N 2 / N 3 > 0 NP 1 / N 2 (N 2 / N 3 ) / (N 4 / N 5 ) N 4 / N 5 N 3 a very decorative plant una pianta molto decorativa NP 1 / N 2 N 3 13 / 23

Introduction Derivation Projection Experiments Conclusions References Example 2/3 NP 1 > 0 N 2 > 0 N 2 / N 3 > 0 NP 1 / N 2 (N 2 / N 3 ) / (N 4 / N 5 ) N 4 / N 5 N 3 a very decorative plant una pianta molto decorativa NP 1 / N 2 N 3 (N 2 \ N 3 ) / (N 4 \ N 5 ) 13 / 23

Introduction Derivation Projection Experiments Conclusions References Example 2/3 NP 1 > 0 N 2 > 0 N 2 / N 3 > 0 NP 1 / N 2 (N 2 / N 3 ) / (N 4 / N 5 ) N 4 / N 5 N 3 a very decorative plant una pianta molto decorativa NP 1 / N 2 N 3 (N 2 \ N 3 ) / (N 4 \ N 5 ) N 4 \ N 5 13 / 23

Introduction Derivation Projection Experiments Conclusions References Example 2/3 NP 1 > 0 N 2 > 0 N 2 / N 3 > 0 NP 1 / N 2 (N 2 / N 3 ) / (N 4 / N 5 ) N 4 / N 5 N 3 a very decorative plant una pianta molto decorativa NP 1 / N 2 N 3 (N 2 \ N 3 ) / (N 4 \ N 5 ) N 4 \ N 5 > 0 N 2 \ N 3 13 / 23

Introduction Derivation Projection Experiments Conclusions References Example 2/3 NP 1 > 0 N 2 > 0 N 2 / N 3 > 0 NP 1 / N 2 (N 2 / N 3 ) / (N 4 / N 5 ) N 4 / N 5 N 3 a very decorative plant una pianta molto decorativa NP 1 / N 2 N 3 (N 2 \ N 3 ) / (N 4 \ N 5 ) N 4 \ N 5 > 0 N 2 \ N 3 < 0 N 2 13 / 23

Introduction Derivation Projection Experiments Conclusions References Example 2/3 NP 1 > 0 N 2 > 0 N 2 / N 3 > 0 NP 1 / N 2 (N 2 / N 3 ) / (N 4 / N 5 ) N 4 / N 5 N 3 a very decorative plant una pianta molto decorativa NP 1 / N 2 N 3 (N 2 \ N 3 ) / (N 4 \ N 5 ) N 4 \ N 5 > 0 N 2 \ N 3 < 0 N 2 > 0 NP 1 13 / 23

Introduction Derivation Projection Experiments Conclusions References Example 3/3 S 5 \ NP 6 > 0 S 3 \ NP 4 > 0 (S 5 \ NP 6 ) / (S 3 \ NP 4 ) (S 3 \ NP 4 ) / PR 7 < 1 > 0 × (S 1 \ NP 2 ) / (S 3 \ NP 4 ) (S 5 \ NP 6 ) \ (S 1 \ NP 2 ) ((S 3 \ NP 4 ) / PR 7 ) / NP 8 NP 8 PR 7 Do n’t mess it up Versau es nicht 14 / 23

Introduction Derivation Projection Experiments Conclusions References Example 3/3 S 5 \ NP 6 > 0 S 3 \ NP 4 > 0 (S 5 \ NP 6 ) / (S 3 \ NP 4 ) (S 3 \ NP 4 ) / PR 7 < 1 > 0 × (S 1 \ NP 2 ) / (S 3 \ NP 4 ) (S 5 \ NP 6 ) \ (S 1 \ NP 2 ) ((S 3 \ NP 4 ) / PR 7 ) / NP 8 NP 8 PR 7 Do n’t mess it up Versau es nicht NP 8 14 / 23

Introduction Derivation Projection Experiments Conclusions References Example 3/3 S 5 \ NP 6 > 0 S 3 \ NP 4 > 0 (S 5 \ NP 6 ) / (S 3 \ NP 4 ) (S 3 \ NP 4 ) / PR 7 < 1 > 0 × (S 1 \ NP 2 ) / (S 3 \ NP 4 ) (S 5 \ NP 6 ) \ (S 1 \ NP 2 ) ((S 3 \ NP 4 ) / PR 7 ) / NP 8 NP 8 PR 7 Do n’t mess it up Versau es nicht NP 8 (S 5 \ NP 6 ) \ (S 3 \ NP 4 ) 14 / 23

Introduction Derivation Projection Experiments Conclusions References Example 3/3 S 5 \ NP 6 > 0 S 3 \ NP 4 > 0 (S 5 \ NP 6 ) / (S 3 \ NP 4 ) (S 3 \ NP 4 ) / PR 7 < 1 > 0 × (S 1 \ NP 2 ) / (S 3 \ NP 4 ) (S 5 \ NP 6 ) \ (S 1 \ NP 2 ) ((S 3 \ NP 4 ) / PR 7 ) / NP 8 NP 8 PR 7 Do n’t mess it up Versau es nicht (S 3 \ NP 4 ) / NP 8 NP 8 (S 5 \ NP 6 ) \ (S 3 \ NP 4 ) 14 / 23

Introduction Derivation Projection Experiments Conclusions References Example 3/3 S 5 \ NP 6 > 0 S 3 \ NP 4 > 0 (S 5 \ NP 6 ) / (S 3 \ NP 4 ) (S 3 \ NP 4 ) / PR 7 < 1 > 0 × (S 1 \ NP 2 ) / (S 3 \ NP 4 ) (S 5 \ NP 6 ) \ (S 1 \ NP 2 ) ((S 3 \ NP 4 ) / PR 7 ) / NP 8 NP 8 PR 7 Do n’t mess it up Versau es nicht (S 3 \ NP 4 ) / NP 8 NP 8 (S 5 \ NP 6 ) \ (S 3 \ NP 4 ) > 0 S 3 \ NP 4 14 / 23

Introduction Derivation Projection Experiments Conclusions References Example 3/3 S 5 \ NP 6 > 0 S 3 \ NP 4 > 0 (S 5 \ NP 6 ) / (S 3 \ NP 4 ) (S 3 \ NP 4 ) / PR 7 < 1 > 0 × (S 1 \ NP 2 ) / (S 3 \ NP 4 ) (S 5 \ NP 6 ) \ (S 1 \ NP 2 ) ((S 3 \ NP 4 ) / PR 7 ) / NP 8 NP 8 PR 7 Do n’t mess it up Versau es nicht (S 3 \ NP 4 ) / NP 8 NP 8 (S 5 \ NP 6 ) \ (S 3 \ NP 4 ) > 0 S 3 \ NP 4 < 0 S 5 \ NP 6 14 / 23

Introduction Derivation Projection Experiments Conclusions References Training • Parallel corpus: tatoeba.org • English parser: EasyCCG trained on CCGrebank • Word aligments: GIZA++ • Target-language parser: EasyCCG trained on projected derivations 15 / 23

Cross-lingual CCG Induction Kilian Evang @texttheater University - PowerPoint PPT Presentation

Introduction Derivation Projection Experiments Conclusions References Cross-lingual CCG Induction Kilian Evang @texttheater University of D usseldorf 2019-06-04 NAACL-HLT 1 / 23 Introduction Derivation Projection Experiments

Treebank Translation for Cross-Lingual Parser Induction Jrg Tiedemann 1 eljko Agi 2 Joakim

Cross-lingual NLP Sara Stymne Uppsala University Department of Linguistics and Philology

Cross-lingual Information Retrieval Pavel Pecina Institute of Formal and Applied Linguistics

WMT 2016 Shared Task on Cross-lingual Pronoun Prediction . Liane Guillou, Christian Hardmeier,

Cross-Lingual Cross-Document Coreference with Entity Linking Sean Monahan, John Lehmann, Timothy

Cross-Lingual Cross-Document Coreference with Entity Linking Sean Monahan, John Lehmann, Timothy

Bleaching Text: Abstract Features for Cross-lingual Gender Prediction. Rob van der Goot, Nikola

From Dictionaries to Cross-lingual Lexical Resources Guadalupe Aguado-de-Cea, Elena

Cross-lingual similarity calculation for plagiarism detection and more Tools and resources

Cross-lingual and temporal Wikipedia analysis G ob ol os-Szab o Julianna MTA SZTAKI

The Multilingual and Cross- lingual Web PD Dr. Gnter Neumann LT lab German Research Center

Co-training Embeddings of Knowledge Graphs and Entity Descriptions for Cross-lingual Entity

Pronunciation Extraction Through Cross-Lingual Word-to-Phoneme Alignment Felix Stahlberg, Tim

External and Intrinsic Plagiarism Detection using a Cross-Lingual Retrieval and Segmentation

Building a Cross-lingual Relatedness Thesaurus using a Graph Similarity Measure Lukas

Learning Cross-lingual Distributed Logical Representations for Semantic Parsing Yanyan Zou and

Global income inequality: current trends, issues of justice and politics Branko Milanovic

Exhibitions Amber Evangelista UNCLASSIFIED Exhibitions at VPM Launch a new

Status Update on the TAPICC Initiative David Filip Klaus Fleischmann (Allison Ferch, Jim

Economic impacts of TTIP in Ireland Department of Jobs, Enterprise and Innovation Martin H.

Street Light Control Project SWEDE Conference May 3-5, 2017 Overview Goal: Implement dynamic

BS Exercises WRS - 16 BR/TSD/TPR International Telecommunication Union 12-16 December 2016,

A Small Macroeconomic Model of the EU-Accession Countries* Bruno Merlevede, Joseph Plasmans, and

AFL Record Magazine Presentation (text) Jamie Radford Slide 1-2 - Title Slides Slide 3 About