Ontology Induction (Chen et al., 2013 & 2014)Frame-semantic parsing on ASR results (Das et al., 2013)

• frame slot candidate• lexical unit slot filler

1st Issue: How to induce domain-specific concepts?

locale_by_use

food expensiveness

seeking

relational_quantity

PREP_FOR

PREP_FOR

NN AMOD

AMOD

AMOD

desiring

DOBJ

type

food pricerange

DOBJ

AMOD AMOD

AMOD

taskarea

PREP_IN

• Domain: restaurant recommendation in an in-car setting (WER = 37%)o Dialogue slots: addr, area, food, phone,

postcode, pricerange, task, type speak on topic addr

area

food

phone

part orientationaldirectionlocalepart inner outer

foodorigin

contactingpostcode

price range tasktype

sending

commerce scenarioexpensivenessrange

seekingdesiringlocating

locale by usebuilding

reference ontology w/ the most frequent dependencies

Can a dialogue system automatically learn open domain knowledge and then understand users?

Unsupervised Learning and Modeling of Knowledge and Intent for Spoken Dialogue SystemsYun-Nung (Vivian) Chen

yvchen@cs.cmu.edu

Goal Framework

Restaurant Asking

Conversations

target

foodprice

seeking

quantity

PREP_FOR

PREP_FOR

NN AMOD

AMODAMOD

Domain-Specific OntologyUnlabeled Collection

Knowledge Acquisition

Ontology InductionStructure Learning

Domain-Specific Ontologyprice=“cheap”, target=“restaurant”

behavior=navigation

SLU Modeling by MF

SLU Component

“can i have a cheap restaurant”

Semantic DecodingBehavior Prediction

Knowledge Acquisition SLU Modeling by Matrix Factorization

Structure Learning (Chen et al., 2015a)Typed syntactic dependencies on ASR https://github.com/yvchen/MRRW/

ccomp

amoddobj

nsubj det

can i havea cheap restaurantcapability expensiveness locale_by_use

induced ontology

Semantic Decoding (Chen et al., 2015b)• concept semantic slot

Behavior Prediction• concept user behavior

1) Given unlabeled conversations, how can a system automatically induce and organize domain-specific concepts?

2) With the automatically acquired knowledge, how can a system understand utterances?

1Utterance 1

i would like a cheap restaurant

Feature Observation Semantic Concept (Slot / Behavior)

Train

… …

…

cheap restaurant foodexpensiveness

1

target

11

find a restaurant for chinese foodUtterance 2

1 1

food

1 1

1 Test

1

1

.97.90 .95.85

.93 .92.98.05 .05

Feature Relation Model Concept Relation Model

Reasoning with Matrix Factorization

Semantic Concept Induction

SLU Model

Semantic Representation

“can I have a cheap restaurant”Ontology Induction

Unlabeled Collection

SLU Modeling by MF

Ff Fs

Feature Model

Rf

RsRelation Propagation

Model

Feature Relation Model

Concept Relation Model

.

Knowledge Acquisition

Structure Learning

o Relation Propagation Model Feature Knowledge Graph Concept Knowledge Graph

Assumption: The domain-specific features/concepts have more dependency to each other.Relation matrices allow each node to propagate scores to its neighbors in

the knowledge graph, so that domain-specific features/concepts have higher scores during training.

2nd Issue: Hidden semantics cannot be observed but may benefit understanding performance.

Good! Good!?

Feature Relation Model Concept Relation Model

Rf

Rs‧

1

Feature Concept

Train

cheap restaurant foodexpensiveness

1

locale_by_use

11

1 1

food

1 1

1 Test

1

1

Ontology Induction

i like

1 1

capability

1

Utterance 1i would like a cheap restaurant

… …

find a restaurant with chinese foodUtterance 2

show me a list of cheap restaurantsTest Utterance .90 .97 .95.85

hidden semantics

o Matrix Factorization (MF) Model implicit feedback

Objective:

1

𝑓 +¿ ¿𝑓 −𝑓 −

𝑢𝑥

MF learns a set of well-ranked concepts per utterance.

Chen et al., “Unsupervised Induction and Filling of Semantic Slots for Spoken Dialogue Systems Using Frame-Semantic Parsing,” in Proc. of ASRU, 2013.Chen et al., “Leveraging Frame Semantics and Distributional Semantics for Unsupervised Semantic Slot Induction in Spoken Dialogue Systems,” in Proc. of SLT, 2014.Chen et al., “Jointly Modeling Inter-Slot Relations by Random Walk on Knowledge Graphs for Unsupervised Spoken Language Understanding,” in Proc. of NAACL, 2015a.Chen et al., “Matrix Factorization with Knowledge Graph Propagation for Unsupervised Spoken Language Understanding,” in Proc. of ACL-IJCNLP, 2015b.