carma - constructional analyzer using recursively multiple ... · carma constructional analyzer...

26
CARMA Constructional Analyzer using Recursively Multiple AVMs Ely Edison Matos [email protected] September 6, 2018 FrameNet Brasil Project - UFJF

Upload: others

Post on 17-Oct-2020

16 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: CARMA - Constructional Analyzer using Recursively Multiple ... · CARMA Constructional Analyzer using Recursively Multiple AVMs ElyEdisonMatos ely.matos@ufjf.edu.br September6,2018

CARMA

Constructional Analyzer using Recursively Multiple AVMs

Ely Edison [email protected]

September 6, 2018

FrameNet Brasil Project - UFJF

Page 2: CARMA - Constructional Analyzer using Recursively Multiple ... · CARMA Constructional Analyzer using Recursively Multiple AVMs ElyEdisonMatos ely.matos@ufjf.edu.br September6,2018

Table of contents

1. Introduction

2. Premises

3. Computational Processing

4. Limitations and Outlook

1

Page 3: CARMA - Constructional Analyzer using Recursively Multiple ... · CARMA Constructional Analyzer using Recursively Multiple AVMs ElyEdisonMatos ely.matos@ufjf.edu.br September6,2018

Introduction

Page 4: CARMA - Constructional Analyzer using Recursively Multiple ... · CARMA Constructional Analyzer using Recursively Multiple AVMs ElyEdisonMatos ely.matos@ufjf.edu.br September6,2018

Context

FNBr is working on NLU (Natural Language Understanding) projects.

FNBr approach to NLU comprises three main elements:

1. Linguistic Knowledge: Lexicon, Constructions, GF, POS, Roles,Syntax, etc.

2. World Knowledge: Ontologies and external datasets

3. Situational Context: Frames and Frame Elements

NLU processes must use linguistic knowledge cognitively to get anapproximated shape of a world knowledge in a given situationalcontext.

2

Page 5: CARMA - Constructional Analyzer using Recursively Multiple ... · CARMA Constructional Analyzer using Recursively Multiple AVMs ElyEdisonMatos ely.matos@ufjf.edu.br September6,2018

CARMA

CARMA1 is a constructional analyzer: given a raw sentence, it tries toidentify the constructions in the sentence.

If these constructions evoke a frame, it helps to identify the SituationalContext.

1this is a new version of [4]

3

Page 6: CARMA - Constructional Analyzer using Recursively Multiple ... · CARMA Constructional Analyzer using Recursively Multiple AVMs ElyEdisonMatos ely.matos@ufjf.edu.br September6,2018

Why constructional analysis?

o celular quebrou a telaDET NOUN VERB DET NOUNThe cellphone break.PST the screen

det nsubj det

obj

’The screen in cellphone broke’/Cxn Split_object

o menino quebrou a cadeiraDET NOUN VERB DET NOUNThe boy break.PST the chair

det nsubj det

obj

’The boy broke the chair’/Cxn Transitive_action

4

Page 7: CARMA - Constructional Analyzer using Recursively Multiple ... · CARMA Constructional Analyzer using Recursively Multiple AVMs ElyEdisonMatos ely.matos@ufjf.edu.br September6,2018

Resources

CARMA is using 4 different resources:

1. FNBr framenet• the network of frames and LUs, including all lexicon stuff (words,

lexemes, lemmas,..)

2. FNBr constructicon• the network of constructions

3. FNBr ontology• a Generative Lexicon based ontology defining extended qualia

relations between LUs (based on SIMPLE ontology[1])

4. UD parser• to get the syntactic structure of sentence using UD POS and

relations.

5

Page 8: CARMA - Constructional Analyzer using Recursively Multiple ... · CARMA Constructional Analyzer using Recursively Multiple AVMs ElyEdisonMatos ely.matos@ufjf.edu.br September6,2018

Premises

Page 9: CARMA - Constructional Analyzer using Recursively Multiple ... · CARMA Constructional Analyzer using Recursively Multiple AVMs ElyEdisonMatos ely.matos@ufjf.edu.br September6,2018

AVM

Figure 1: AVM structure

6

Page 10: CARMA - Constructional Analyzer using Recursively Multiple ... · CARMA Constructional Analyzer using Recursively Multiple AVMs ElyEdisonMatos ely.matos@ufjf.edu.br September6,2018

AVM

Figure 2: Everything as AVM

! Recursive AVMs: the value can be another AVM

7

Page 11: CARMA - Constructional Analyzer using Recursively Multiple ... · CARMA Constructional Analyzer using Recursively Multiple AVMs ElyEdisonMatos ely.matos@ufjf.edu.br September6,2018

Constraints

CARMA is a constraint-based system: the AVM attributes must berestricted by a (set of) possible/acceptable value(s)

Constructions are defined by constraining construction elements todependency relations, as proposed by Property Grammar [2]

8

Page 12: CARMA - Constructional Analyzer using Recursively Multiple ... · CARMA Constructional Analyzer using Recursively Multiple AVMs ElyEdisonMatos ely.matos@ufjf.edu.br September6,2018

Construction definition

cxn_split_object:type: cxnclass: cxn_split_objectregion: cxn_split_objectattributes:

nsubj:features: {optional: false, head: false}value: [ud_nsubj]

verb:features: {optional: false, head: true}value: [pos_verb]

obj:features: {optional: false, head: false}value: [ud_obj]

x_part:type: xevalue: [rel_is_part_of]

x_frame:type: xevalue: [frm_undergoing]

constraints:- {arg1: verb, constraint: dominance, arg2: nsubj}- {arg1: verb, constraint: dominance, arg2: obj}- {arg1: nsubj, arg2: x_part, constraint: hasword}- {arg1: obj, arg2: x_part, constraint: hasword}

9

Page 13: CARMA - Constructional Analyzer using Recursively Multiple ... · CARMA Constructional Analyzer using Recursively Multiple AVMs ElyEdisonMatos ely.matos@ufjf.edu.br September6,2018

Computational Processing

Page 14: CARMA - Constructional Analyzer using Recursively Multiple ... · CARMA Constructional Analyzer using Recursively Multiple AVMs ElyEdisonMatos ely.matos@ufjf.edu.br September6,2018

Topology

CARMA

is a recursive hierarchical network

and an elaborated pattern-matching system

So, it is amenable to some Machine Learning techniques

10

Page 15: CARMA - Constructional Analyzer using Recursively Multiple ... · CARMA Constructional Analyzer using Recursively Multiple AVMs ElyEdisonMatos ely.matos@ufjf.edu.br September6,2018

RCN

RCN: Recursive Cortical Network[3]

Figure 3: Overview of RCN (source:[3]) 11

Page 16: CARMA - Constructional Analyzer using Recursively Multiple ... · CARMA Constructional Analyzer using Recursively Multiple AVMs ElyEdisonMatos ely.matos@ufjf.edu.br September6,2018

RCN

? RCN resembles AVM

Figure 4: Detail of of RCN (source:[3])

12

Page 17: CARMA - Constructional Analyzer using Recursively Multiple ... · CARMA Constructional Analyzer using Recursively Multiple AVMs ElyEdisonMatos ely.matos@ufjf.edu.br September6,2018

RCN Processing

RCN can be used for generation and inference (parsing)

Inference

• Belief propagation

• Forward-pass

• Backward-pass

13

Page 18: CARMA - Constructional Analyzer using Recursively Multiple ... · CARMA Constructional Analyzer using Recursively Multiple AVMs ElyEdisonMatos ely.matos@ufjf.edu.br September6,2018

CARMA processing

In CARMA we are interested in the parsing process

Resources are stored in some persistent medium

• Lexicon on FNBr database (MySQL)

• Frames, Constructions, Ontology exported to Neo4j graph database

14

Page 19: CARMA - Constructional Analyzer using Recursively Multiple ... · CARMA Constructional Analyzer using Recursively Multiple AVMs ElyEdisonMatos ely.matos@ufjf.edu.br September6,2018

CARMA processing

1. User inputs a sentence.

2. The sentence is parsed for UD (currently using UDPipe parser)

3. FNBr database is queried for wordforms, lexemes and lemmas

4. A type network is built with lexical stuff

5. Graph database is queried to complete the type network

6. Type network is traversed to create a token network

7. Word nodes are activated, constraints are calculated and theactivation spreads in token network until a root node

8. Activated constructions nodes correspond to constructions detectedin the sentence

9. Conflicts (more than one construction activated) are resolved basedon MAP (maximum a posteriori)

15

Page 20: CARMA - Constructional Analyzer using Recursively Multiple ... · CARMA Constructional Analyzer using Recursively Multiple AVMs ElyEdisonMatos ely.matos@ufjf.edu.br September6,2018

CARMA processing

Figure 5: Partial view of activated network

16

Page 21: CARMA - Constructional Analyzer using Recursively Multiple ... · CARMA Constructional Analyzer using Recursively Multiple AVMs ElyEdisonMatos ely.matos@ufjf.edu.br September6,2018

Limitations and Outlook

Page 22: CARMA - Constructional Analyzer using Recursively Multiple ... · CARMA Constructional Analyzer using Recursively Multiple AVMs ElyEdisonMatos ely.matos@ufjf.edu.br September6,2018

Limitations

• Current version is at very beginning

• UD parsing for Brazilian Portuguese is very limited and error prone

• Some basic linguistic phenomenons are not handled yet (e.g. NullInstantiation)

• and many others...

17

Page 23: CARMA - Constructional Analyzer using Recursively Multiple ... · CARMA Constructional Analyzer using Recursively Multiple AVMs ElyEdisonMatos ely.matos@ufjf.edu.br September6,2018

Outlook

• How to implement a learning process?

• How to use the analysis in the context of construction alignment

• How many constraint types?

• and many others...

18

Page 24: CARMA - Constructional Analyzer using Recursively Multiple ... · CARMA Constructional Analyzer using Recursively Multiple AVMs ElyEdisonMatos ely.matos@ufjf.edu.br September6,2018

Thank you!

18

Page 25: CARMA - Constructional Analyzer using Recursively Multiple ... · CARMA Constructional Analyzer using Recursively Multiple AVMs ElyEdisonMatos ely.matos@ufjf.edu.br September6,2018

References i

N. Bel, F. Busa, N. Calzolari, E. Gola, A. Lenci, M. Monachini,A. Ogonowski, I. Peters, W. Peters, N. Ruimy, M. Villegas, andA. Zampolli.SIMPLE: A General Framework for the Development ofMultilingual Lexicons.Proceedings of the 2nd International Conference on LanguageResources and Evaluation, 2000.

P. Blache.Property Grammars: A Fully Constraint-Based Theory.In Christiansen H. et al. (eds.), Constraint Solving and LanguageProcessing, Sptinger-Verlag, Berlin Heidelberg, pages 1–16, 2005.

19

Page 26: CARMA - Constructional Analyzer using Recursively Multiple ... · CARMA Constructional Analyzer using Recursively Multiple AVMs ElyEdisonMatos ely.matos@ufjf.edu.br September6,2018

References ii

D. George, W. Lehrach, K. Kansky, M. Lazaro-Gredilla, C. Laan,B. Marthi, X. Lou, Z. Meng, and Y. Liu.A generative vision model that trains with high data efficiencyand breaks text-based CAPTCHAs.Science, 10(October):1–19, 1126.

E. Matos, T. Torrent, V. Almeida, A. Laviola, L. Lage, N. Marção,and T. Tavares.Constructional Analysis Using Constrained SpreadingActivation in a FrameNet-Based Structured ConnectionistModel.The AAAI 2017 Spring Symposium on Computational ConstructionGrammar and Natural Language Understanding, Technical ReportSS-17-02, pages 222–229, 2017.

20