Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes:...

57
Parsing of natural language sentences to syntactic and semantic graph representations Abschlussvortrag zum Forschungsprojekt Pius Meinert April 13, 2018

Transcript of Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes:...

Page 1: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Parsing of natural language sentences tosyntactic and semantic graph representationsAbschlussvortrag zum Forschungsprojekt

Pius MeinertApril 13, 2018

Page 2: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Overview

Graph Representations

Corpora

Parsing Techniques

Parser

1

Page 3: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Overview

Graph Representations

Corpora

Parsing Techniques

Parser

Semantic: AMR, UCCA, depen-dency graphsSyntactic: Constituency treederived, Use of syntactic infor-mation

1

Page 4: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Overview

Graph Representations

Corpora

Parsing Techniques

Parser

AMR, UCCA, SemEval-2014/-2015:dependency graphs, Penn Tree-bank, TIGER Corpus

1

Page 5: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Overview

Graph Representations

Corpora

Parsing Techniques

Parser

Maximum SubgraphTransition-BasedSynchronous HRG

1

Page 6: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Overview

Graph Representations

Corpora

Parsing Techniques

Parser

1

Page 7: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Abstract Meaning Representation (AMR) [Ban+13]

2

Page 8: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Abstract Meaning Representation (AMR) [Ban+13]

contrast

possible

say

YouI

person

dream

include

only —

arg0-of

arg1

arg2 arg3

2

Page 9: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Abstract Meaning Representation (AMR) [Ban+13]

rooted, directed,edge-labeled andleaf-labeled

contrast

possible

say

YouI

person

dream

include

only —

arg0-of

arg1

arg2 arg3

2

Page 10: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Tree Definition

A tree is a directed graph G = (V,A) that has a vertex r, namedroot, such that every vertex v ∈ V is reachable from r via aunique directed path. [KJ15; KO16]

3

Page 11: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Dependency Graph [KJ15]

The gene thus can prevent a plant from fertilizing itselfbv arg1 arg1 bv arg2

arg2arg1

arg1

arg3

4

Page 12: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Dependency Graph [KJ15]

unconnected

The gene thus can prevent a plant from fertilizing itselfbv arg1 arg1 bv arg2

arg2arg1

arg1

arg3

Connectedness:There exists an undirected path between every two pairs ofvertices. Nodes with in- and out-degree zero are calledsingletons. [KO16]

4

Page 13: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Dependency Graph [KJ15]

unconnected, multi-rooted

The gene thus can prevent a plant from fertilizing itselfbv arg1 arg1 bv arg2

arg2arg1

arg1

arg3

Top nodes:Nodes of in-degree zero, a graph’s equivalent to the uniqueroot in a tree. [KO16]

4

Page 14: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Dependency Graph [KJ15]

unconnected, multi-rooted, reentrancy

The gene thus can prevent a plant from fertilizing itselfbv arg1 arg1 bv arg2

arg2arg1

arg1

arg3

Reentrant nodes:Nodes with in-degree greater than one. [WXP15; DCS17; BB17]

4

Page 15: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Dependency Graph - Noncrossing [KJ15]

The gene thus can prevent a plant from fertilizing itselfbv arg1 arg1 bv arg2

arg2arg1

arg1

arg3

5

Page 16: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Dependency Graph - Noncrossing [KJ15]

Coverage ranges from 48% to 78% for various graph banks(CCGbank, Prage Semantic Dependencies, etc.). [KJ15; SCW17]

The gene thus can prevent a plant from fertilizing itselfbv arg1 arg1 bv arg2

arg2arg1

arg1

arg3

5

Page 17: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Dependency Graph - 1-Endpoint-Crossing [PKM13]

das mer em Hans es huus hälfed aastriche

6

Page 18: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Dependency Graph - 1-Endpoint-Crossing [PKM13]

das mer em Hans es huus hälfed aastriche

6

Page 19: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Dependency Graph - 1-Endpoint-Crossing [PKM13]

Account for 95.7− 97.7% of the dependency structures that areused in [Cao+17].

das mer em Hans es huus hälfed aastriche

6

Page 20: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Dependency Graph - Book Embedding [SCW17]

The company that Mark wants to buy

arg1 arg1arg2

arg1

arg1arg1

arg2arg2

arg2

7

Page 21: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Dependency Graph - Book Embedding [SCW17]

The company that Mark wants to buy

arg1 arg1arg2

arg1

arg1arg1

arg2arg2

arg2

7

Page 22: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Dependency Graph - Book Embedding [SCW17]

The company that Mark wants to buy

arg1 arg1

arg2

arg1

arg1arg1

arg2arg2

arg2

7

Page 23: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Dependency Graph - Book Embedding [SCW17]

Coverage with respect to different page numbers:PN coverage1 48− 78%2 20− 49%3 0.3− 1.7%

The company that Mark wants to buy

arg1 arg1

arg2

arg1

arg1arg1

arg2arg2

arg2

7

Page 24: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Evaluation Metric - AMR Representations

AMR graph

go–1

boy

want-01

ARG0 ARG1

ARG0 instance

instance

instance

8

Page 25: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Evaluation Metric - AMR Representations

AMR graph

go–1

boy

want-01

ARG0 ARG1

ARG0 instance

instance

instance

PENMAN notation

(w / want-01:arg0 (b / boy):arg1 (g / go-01)

:arg0 b)

8

Page 26: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Evaluation Metric - AMR Representations

AMR graph

go–1

boy

want-01

ARG0 ARG1

ARG0 instance

instance

instance

logic format

instance(a, want-01) ∧instance(b, boy) ∧instance(c, go-01) ∧ARG0(a, b) ∧ARG1(a, c) ∧ARG0(c, b)

8

Page 27: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Evaluation Metric - Smatch [CK13]

The boy wants the football

instance(x, want-01) ∧instance(y, boy) ∧instance(z, football) ∧ARG0(x, y) ∧ARG1(x, z)

The boy wants to go

instance(a, want-01) ∧instance(b, boy) ∧instance(c, go-01) ∧ARG0(a, b) ∧ARG1(a, c) ∧ARG0(c, b)

9

Page 28: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Evaluation Metric - Smatch [CK13]

The boy wants the football

instance(x, want-01) ∧instance(y, boy) ∧instance(z, football) ∧ARG0(x, y) ∧ARG1(x, z)

The boy wants to go

instance(a, want-01) ∧instance(b, boy) ∧instance(c, go-01) ∧ARG0(a, b) ∧ARG1(a, c) ∧ARG0(c, b)

inter-annotator agreement study:Smatch score ranges from 0.79 to 0.83.

9

Page 29: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Graph Parsing Techniques

Maximum Subgraph“all pairs” approach [BM06] - Consider all possible (weighted)arcs and find the maximum spanning connected subgraph.

Transition-based“stepwise” approach [BM06] - Build the graph step by step byapplying transitions to the current configuration.

Synchronous Hyperedge Replacement Grammar (SHRG)HRGs as “an intuitive generalization of context free grammars(CFGs) from strings to hypergraphs.” [Jon+12; Hab92]

10

Page 30: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Maximum Subgraph - Problem Definition[SCW17]

Input directed, weighted graph G = (V,A) (complete)

Implicit sentence s, class of graphs G

Output subgraph G′ = (V,A′ ⊆ A) with maximum totalweight such that G′ belongs to G

G′(s) = argmaxH∈G(s,G)∑

p∈H ScorePart(s,p)

Example if class of graphs G is the class of all trees,Maximum Subgraph = Maximum Spanning Tree

11

Page 31: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Maximum Subgraph - Learning and Features [MN07]

G′(s) = argmaxH∈G(s,G)∑

p∈H ScorePart(s,p)

12

Page 32: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Maximum Subgraph - Learning and Features [MN07]

Globallearning

Optimize entire graph score, not only single arcattachments.

G′(s) = argmaxH∈G(s,G)∑

p∈H ScorePart(s,p)

12

Page 33: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Maximum Subgraph - Learning and Features [MN07]

Globallearning

Optimize entire graph score, not only single arcattachments.

G′(s) = argmaxH∈G(s,G)∑

p∈H ScorePart(s,p)

Localfeatures

Restricted to a limited number of arcs (to keepinference and learning tractable).

12

Page 34: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

JAMR [Fla+14]

First published AMR parser. It solves the task by means of twophases:

Concept identification: Match spans of words to concept graphfragments.

Relation identification: Find the maximum spanning connectedsubgraph over those graph fragments.

13

Page 35: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

JAMR - Concept Identification Phase [Fla+14]

The boy wants to visit New York City

∅ boy want-01 ∅ visit-01 name

city“New”

“York”

“City”

nameop1

op2

op3

14

Page 36: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

JAMR - Concept Identification Phase [Fla+14]

The boy wants to visit New York City

c:

w:b:k = 6

b0 b1 b2 b3 b4 b5 b6

∅ boy want-01 ∅ visit-01 name

city“New”

“York”

“City”

nameop1

op2

op3

score(b, c; θ) =∑k

i=1 θ>f(wbi−1:bi ,bi−1,bi, ci)

Solve by dynamic programming: O(n2).

14

Page 37: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

JAMR - Relation Identification Phase [Fla+14]

1. Initialization:Include all edges and vertices given by the conceptidentification phase.

2. Pre-processing:Reduce the set of edges considered to one edge per pair ofnodes: Either the edge given by the first phase or the highestscoring one.

3. Core algorithm:First, add all positive edges and then greedily add the leastnegative edge that connects two components until the graph isconnected.

15

Page 38: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Transition-Based - Transition System [WXP15]

A transition system for parsing is a tuple S = (S, T, s0, St) where

• S is a set of parsing states (configurations).• T is a set of parsing actions (transitions), each of which isa function t : S→ S.

• s0 is an initialization function, mapping each inputsentence w to an initial state.

• St ⊆ S is a set of terminal states.

16

Page 39: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Transition-Based - Parsing Algorithm [WXP15]

Input: sentence w = w0...wnOutput: parsed graph G1: s← s0(w)2: while s /∈ St do3: T ← all possible actions according to s4: bestT ← argmaxt∈T score(t, s)5: s← apply bestT to s6: end while7: return G

17

Page 40: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Transition-Based - Learning and Features [MN07]

bestT ← argmaxt∈T score(t, s)

18

Page 41: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Transition-Based - Learning and Features [MN07]

Locallearning

Optimization only for single transitions, nottransition sequences.

bestT ← argmaxt∈T score(t, s)

18

Page 42: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Transition-Based - Learning and Features [MN07]

Locallearning

Optimization only for single transitions, nottransition sequences.

bestT ← argmaxt∈T score(t, s)

Globalfeatures

Features may be based on whole graph built sofar/entire transition history.

18

Page 43: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Transition-Based AMR Parser [WXP15]

Idea: Use similarities between an AMR and the dependencystructure of a sentence.

Two-stage framework:

1) dependency parser to generate dependency tree for thesentence

2) transition-based algorithm to transform dependency treeto an AMR graph

The dependency parser can be trained on a much larger dataset.

19

Page 44: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Transition-Based AMR Parser - Transition Actions [WXP15]

REENTRANCE action

want

police arrest

reentrance

⇒want

police arrestARG0

REPLACE-HEAD action

live

in

Singapore

⇒live

Singapore

20

Page 45: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

Towards a Catalogue of Linguistic Graph Banks [KO16]

• graph structures are of growing relevance to much NLPresearch

• provide common terminology and transparent statisticsfor different (collections of) graphs

• propose to establish shared community resource:https://aclweb.org/aclwiki/Graph_Parsing_(State_of_the_Art)

21

Page 46: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

References i

Laura Banarescu, Claire Bonial, Shu Cai,Madalina Georgescu, Kira Griffitt, Ulf Hermjakob,Kevin Knight, Philipp Koehn, Martha Palmer, andNathan Schneider. “Abstract Meaning Representationfor Sembanking”. In: Proceedings of the 7thLinguistic Annotation Workshop and Interoperabilitywith Discourse, LAW-ID@ACL 2013, August 8-9, 2013,Sofia, Bulgaria. 2013, pp. 178–186. url:http://aclweb.org/anthology/W/W13/W13-2322.pdf.

Page 47: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

References ii

Jan Buys and Phil Blunsom. “Robust IncrementalNeural Semantic Graph Parsing”. In: Proceedings ofthe 55th Annual Meeting of the Association forComputational Linguistics, ACL 2017, Vancouver,Canada, July 30 - August 4, Volume 1: Long Papers.2017, pp. 1215–1226. doi: 10.18653/v1/P17-1112.url:https://doi.org/10.18653/v1/P17-1112.

Page 48: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

References iii

Sabine Buchholz and Erwin Marsi. “CoNLL-X SharedTask on Multilingual Dependency Parsing”. In:Proceedings of the Tenth Conference onComputational Natural Language Learning, CoNLL2006, New York City, USA, June 8-9, 2006. 2006,pp. 149–164. url:http://aclweb.org/anthology/W/W06/W06-2920.pdf.

Page 49: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

References iv

Junjie Cao, Sheng Huang, Weiwei Sun, andXiaojun Wan. “Parsing to 1-Endpoint-Crossing,Pagenumber-2 Graphs”. In: Proceedings of the 55thAnnual Meeting of the Association for ComputationalLinguistics, ACL 2017, Vancouver, Canada, July 30 -August 4, Volume 1: Long Papers. 2017, pp. 2110–2120.doi: 10.18653/v1/P17-1193. url:https://doi.org/10.18653/v1/P17-1193.

Page 50: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

References v

Shu Cai and Kevin Knight. “Smatch: an EvaluationMetric for Semantic Feature Structures”. In:Proceedings of the 51st Annual Meeting of theAssociation for Computational Linguistics, ACL 2013,4-9 August 2013, Sofia, Bulgaria, Volume 2: ShortPapers. 2013, pp. 748–752. url:http://aclweb.org/anthology/P/P13/P13-2131.pdf.

Page 51: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

References vi

Marco Damonte, Shay B. Cohen, and Giorgio Satta.“An Incremental Parser for Abstract MeaningRepresentation”. In: Proceedings of the 15thConference of the European Chapter of theAssociation for Computational Linguistics, EACL 2017,Valencia, Spain, April 3-7, 2017, Volume 1: LongPapers. 2017, pp. 536–546. url:https://aclanthology.info/papers/E17-1051/e17-1051.

Page 52: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

References vii

Jeffrey Flanigan, Sam Thomson, Jaime G. Carbonell,Chris Dyer, and Noah A. Smith. “A DiscriminativeGraph-Based Parser for the Abstract MeaningRepresentation”. In: Proceedings of the 52nd AnnualMeeting of the Association for ComputationalLinguistics, ACL 2014, June 22-27, 2014, Baltimore, MD,USA, Volume 1: Long Papers. 2014, pp. 1426–1436. url:http://aclweb.org/anthology/P/P14/P14-1134.pdf.

Annegret Habel. Hyperedge Replacement: Grammarsand Languages. Vol. 643. Lecture Notes in ComputerScience. Springer, 1992.

Page 53: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

References viii

Bevan Jones, Jacob Andreas, Daniel Bauer,Karl Moritz Hermann, and Kevin Knight.“Semantics-Based Machine Translation withHyperedge Replacement Grammars”. In: COLING 2012,24th International Conference on ComputationalLinguistics, Proceedings of the Conference: TechnicalPapers, 8-15 December 2012, Mumbai, India. 2012,pp. 1359–1376. url:http://aclweb.org/anthology/C/C12/C12-1083.pdf.

Page 54: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

References ix

Marco Kuhlmann and Peter Jonsson. “Parsing toNoncrossing Dependency Graphs”. In: TACL 3 (2015),pp. 559–570. url:https://tacl2013.cs.columbia.edu/ojs/index.php/tacl/article/view/709.

Marco Kuhlmann and Stephan Oepen. “Towards aCatalogue of Linguistic Graph Banks”. In:Computational Linguistics 42.4 (2016), pp. 819–827.doi: 10.1162/COLI_a_00268. url:https://doi.org/10.1162/COLI_a_00268.

Page 55: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

References x

Ryan T. McDonald and Joakim Nivre. “Characterizingthe Errors of Data-Driven Dependency ParsingModels”. In: EMNLP-CoNLL 2007, Proceedings of the2007 Joint Conference on Empirical Methods inNatural Language Processing and ComputationalNatural Language Learning, June 28-30, 2007, Prague,Czech Republic. 2007, pp. 122–131. url: http://www.aclweb.org/anthology/D07-1013.

Emily Pitler, Sampath Kannan, and Mitchell Marcus.“Finding Optimal 1-Endpoint-Crossing Trees”. In: TACL1 (2013), pp. 13–24. url:https://tacl2013.cs.columbia.edu/ojs/index.php/tacl/article/view/23.

Page 56: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

References xi

Weiwei Sun, Junjie Cao, and Xiaojun Wan. “SemanticDependency Parsing via Book Embedding”. In:Proceedings of the 55th Annual Meeting of theAssociation for Computational Linguistics, ACL 2017,Vancouver, Canada, July 30 - August 4, Volume 1:Long Papers. 2017, pp. 828–838. doi:10.18653/v1/P17-1077. url:https://doi.org/10.18653/v1/P17-1077.

Page 57: Parsing of natural language sentences to syntactic and ... · arg1 arg1 arg3 Reentrantnodes: Nodeswithin-degreegreaterthanone.[WXP15;DCS17;BB17] 4. DependencyGraph-Noncrossing[KJ15]

References xii

Chuan Wang, Nianwen Xue, and Sameer Pradhan. “ATransition-based Algorithm for AMR Parsing”. In:NAACL HLT 2015, The 2015 Conference of the NorthAmerican Chapter of the Association forComputational Linguistics: Human LanguageTechnologies, Denver, Colorado, USA, May 31 - June 5,2015. 2015, pp. 366–375. url:http://aclweb.org/anthology/N/N15/N15-1040.pdf.