Incorporating Domain Knowledge in Multilingual, Goal-oriented Neural Dialogue Models

Suman Banerjee Mitesh M. Khapra

Department of Computer Science and Engineering,

Indian Institute of Technology Madras

Outline

Introduction
Related Work
- Modular Architecture
- End-to-End Architecture
- Existing Neural Models
Problem Statement
Proposed Models
- Sequential Attention Network
- GCN with Sequential Attention
Proposed Dataset
- Modified DSTC2
- Code-mixed dialogue
Results and Analysis
Conclusion

Outline

Introduction
Related Work
- Modular Architecture
- End-to-End Architecture
- Existing Neural Models
Problem Statement
Proposed Models
- Sequential Attention Network
- GCN with Sequential Attention
Proposed Dataset
- Modified DSTC2
- Code-mixed dialogue
Results and Analysis
Conclusion

Dialogue Systems

Siri

Cortana

Bixby

Google assistant

Alexa

Apple Homepod

Amazon Echo

Google Home

Two Paradigms

Challenges

Variability in natural language
Represent the meanings of utterances
Maintaining context over long turns
Incorporating world/domain knowledge

Chit-Chat

Has no specific end goals
Used for user engagement
Focus on generating natural responses

Goal-Oriented

Used to carry out a particular task
Requires background knowledge
Focus on generating informative responses that leads to task completion

Two Paradigms

Challenges

Variability in natural language
Represent the meanings of utterances
Maintaining context over long turns
Incorporating world/domain knowledge

Chit-Chat

Has no specific end goals
Used for user engagement
Focus on generating natural responses

Goal-Oriented

Used to carry out a particular task
Requires background knowledge
Focus on generating informative responses that leads to task completion

Outline

Introduction
Related Work
- Modular Architecture
- End-to-End Architecture
- Existing Neural Models
Problem Statement
Proposed Models
- Sequential Attention Network
- GCN with Sequential Attention
Proposed Dataset
- Modified DSTC2
- Code-mixed dialogue
Results and Analysis
Conclusion

Modular Architecture

Language Understanding

Dialogue State Tracking

Policy Optimizer

Language Generation

User utterance

System response

Semantic Frame

System Action

Dialogue State

I need a cheap chinese restaurant in the north of town.

request_rest(cuisine=chinese, price=cheap, area=north)

Knowledge Base

request_people( )

Sure, for how many people?

Dialogue Manager

Probabilistic methods in spoken-dialogue systems, Steve J. Young, Philosophical Transactions: Mathematical, Physical and Engineering Sciences, 2000

Drawbacks

Annotation of output labels required for each module
Fixed Assumption on the dialogue state structure
Difficult to scale to new domains
Error propagation from previous modules

Language Understanding

Dialogue State Tracking

Policy Optimizer

Language Generation

User utterance

System response

Semantic Frame

System Action

Dialogue State

I need a cheap chinese restaurant in the north of town.

request_rest(cuisine=chinese, price=cheap, area=north)

Knowledge Base

request_people( )

Sure, for how many people?

Dialogue Manager

Outline

Introduction
Related Work
- Modular Architecture
- End-to-End Architecture
- Existing Neural Models
Problem Statement
Proposed Models
- Sequential Attention Network
- GCN with Sequential Attention
Proposed Dataset
- Modified DSTC2
- Code-mixed dialogue
Results and Analysis
Conclusion

End-to-End Architecture

Can be directly trained on utterance- response pair data, no intermediate supervision required
Can be easily scaled to new domains
No fixed assumption on the dialogue state structure
Can handle out-of-vocabulary (OOV) words

User utterance

I need a cheap chinese restaurant in the north of town.

System response

Sure, for how many people?

Knowledge Base

End-to-End Dialogue System

Outline

Introduction
Related Work
- Modular Architecture
- End-to-End Architecture
- Existing Neural Models
Problem Statement
Proposed Models
- Sequential Attention Network
- GCN with Sequential Attention
Proposed Dataset
- Modified DSTC2
- Code-mixed dialogue
Results and Analysis
Conclusion

Recurrent Neural Networks

\( x_1\)

\( x_2\)

\( x_3\)

\( x_4\)

\( x_5\)

\( U \)

\( W \)

\( V \)

\( s_1 \)

\( s_2 \)

\( s_3 \)

\( s_4 \)

\( s_5 \)

\( y_1\)

\( y_2\)

\( y_3\)

\( y_4\)

\( y_5\)

\( s_i = \sigma (Ux_i + Ws_{i-1} + b)\)
\( y_i = o(Vs_i +c) \)

\( s_0\)

\( W \)

Find a cheap Chinese restaurant

\( s_i = RNN (s_{i-1},x_i)\)

Sequence-to-Sequence Models

Sequence-to-Sequence Learning with Neural Networks, Sutskever et.al., NeurIPS, 2014

Encoder

Decoder

Sequence-to-Sequence Models

Attention:

\( \alpha_{it} = f(\mathbf{h}_{i},\mathbf{d}_{t-1})\)
\( \mathbf{c}_t = \sum^{k}_{j=1}\alpha_{jt}\mathbf{h}_j\)

Neural Machine Translation by Jointly Learning to Align and Translate, Bahdanau et. al., ICLR, 2015

\( \alpha_{it}\)

\( \mathbf{c}_{t}\)

\( \mathbf{h}_{i}\)

\( \mathbf{d}_{t}\)

Encoder

Decoder

Hierarchical Recurrent Encoder Decoder

Building End-to-End Dialogue Systems Using Generative Hierarchical Neural Network Models, Serban et. al., AAAI, 2016

Memory Networks

Dialogue History :

\( \mathbf{q}^1\)

\( \mathbf{q}^b\)

\( \mathbf{q}^{b+1}\)

\( \mathbf{o}^b\)

\( \mathbf{p}^b\)

Candidates

\( \mathbf{q}^b\)

\( \mathbf{q}^{B+1}\)

\( W\)

\( \mathbf{\hat{z}}\)

\( BOW(y_i)\)

End-to-End Memory Networks, Sukhbaatar et. al., NeurIPS 2015

User \((u_1)\): Hello!

System \((s_1)\): How can I help you today?

...

System \((s_{t-1})\): How about Fancy_Pub?

Memory Representation:

\(\mathbf{m}_2 = \)

\(BOW(s_1)\)

\(A \cdot\)

Current User Utterance (Query):

User \((u_t)\): I don't like it

\(\mathbf{q} = \)

\(BOW(u_t)\)

\(C \cdot\)

Attention :
- \( a^b_i = \mathbf{q}^{bT}\mathbf{m}_i \)
- \( \mathbf{p}^b = softmax(\mathbf{a}^b) \)
- \( \mathbf{o}^b = \sum_{i=1}^e \mathbf{m}_i p^b_i\)
- \( \mathbf{q}^{b+1}= \mathbf{o}^b + \mathbf{q}^b\)

Candidate responses :

\(y_1\): Let me find another one

\(y_2\): How about The_Place

...

\(y_{c}\): Sorry, there are no other pubs

Prediction :
- \( e_i = \mathbf{q}^{B+1}\cdot W\cdot BOW(y_i)\)
- \( \mathbf{\hat{z}} = softmax(\mathbf{e})\)

Outline

Introduction
Related Work
- Modular Architecture
- End-to-End Architecture
- Existing Neural Models
Problem Statement
Proposed Models
- Sequential Attention Network
- GCN with Sequential Attention
Proposed Dataset
- Modified DSTC2
- Code-mixed dialogue
Results and Analysis
Conclusion

Goal-oriented Dialogue phases

System: Hello, what can I help you with today?

User: Hi!

User: I'd like to book a table for six people in an expensive restaurant with British food.

System: where should it be ?

User: Somewhere in the north of the town.

System: ok I am on it!

System: API_CALL (British, north, six, expensive)

System: How about The_Place?

User: No I don't like it.

System: Ok, then, what do you think about Fancy_Pub?

User: Yes! lets do it.

System: Great! I'll do the reservation.

User: What is the address?

System: Here it is: Fancy_Pub_Address

User: Thank You

System: You're welcome

The_Place R_cuisine British

The_Place R_location north

The_Place R_address The_Place_Address

The_Place R_price expensive

The_Place R_rating 10

Fancy_pub R_cuisine British

Fancy_pub R_location north

Fancy_pub R_address Fancy_pub_Address

Fancy_pub R_price expensive

Fancy_pub R_rating 8

Goal-oriented Dialogue phases

Pre-KB

System: Hello, what can I help you with today?

User: Hi!

User: I'd like to book a table for six people in an expensive restaurant with British food.

System: where should it be ?

User: Somewhere in the north of the town.

System: ok I am on it!

System: API_CALL (British, north, six, expensive)

System: How about The_Place?

User: No I don't like it.

System: Ok, then, what do you think about Fancy_Pub?

User: Yes! lets do it.

System: Great! I'll do the reservation.

User: What is the address?

System: Here it is: Fancy_Pub_Address

User: Thank You

System: You're welcome

Post-KB

The_Place R_cuisine British

The_Place R_location north

The_Place R_address The_Place_Address

The_Place R_price expensive

The_Place R_rating 10

Fancy_pub R_cuisine British

Fancy_pub R_location north

Fancy_pub R_address Fancy_pub_Address

Fancy_pub R_price expensive

Fancy_pub R_rating 8

Structural Information

Dependency Parse of sentences

Knowledge Graph

Current state of the art models ignore this rich structural information
We exploit this structural information in our model
Couple it with the sequential attention mechanism
Empirically show that such structural information aware representations improve the response generation task

Code Mixing

Speaker 1: Hi, can you help me with booking a table at a restaurant?

Speaker 2: Sure, would you like something in cheap, moderate or expensive?

Speaker 1: Hi, kya tum ek restaurant mein table book karne mein meri help karoge?

Speaker 2: Sure, aap ko kaunsi price range mein chahiye, cheap, moderate ya expensive?

Speaker 1: Hi, tumi ki ekta restaurant ey table book korte amar help korbe?

Speaker 2: Sure, aapni kon price range ey chaan, cheap, moderate na expensive?

Problem

Dialogue of n turns : \( \{ (u_1,s_1),(u_2,s_2),...,(k_1,k_2,...,k_e),...,(u_n,s_n) \}\)
Phases:
- Pre-KB : \( (u_1,s_1,u_2,s_2,...,u_i,s_i ) \)
- KB : \( (k_1,k_2,...,k_e) \)
- Post-KB : \( (u_{i+1},s_{i+1},...,u_n,s_n ) \)
At \( t^{th}\) turn the user utterance \( u_t \) is considered as the query to the system
The system is supposed to generate the response: \( s_t \)

Models:
- Sequential Attention Network - To handle the three phases sequentially
- Graph Convolutional Network based model with Sequential Attention - To incorporate structural information
Dataset
- Code-mixed dialogue dataset

Outline

Introduction
Related Work
- Modular Architecture
- End-to-End Architecture
- Existing Neural Models
Problem Statement
Proposed Models
- Sequential Attention Network
- GCN with Sequential Attention
Proposed Dataset
- Modified DSTC2
- Code-mixed dialogue
Results and Analysis
Conclusion

Single Attention Distribution

Current models use a single long RNN or Memory Network to encode the entire context
Compute a single attention distribution over these representations
This way of computing the attention overburdens the attention mechanism

Sequential Attention

Pre-KB

Post-KB

Sequential Attention

Post-KB RNN

Post-KB

\( \mathbf{h}^P_t = BiRNN(\mathbf{h}^P_{t-1},\mathbf{g}_t) \)
\( \mathbf{h}^Q_t = BiRNN(\mathbf{h}^Q_{t-1},\mathbf{q}_t) \)
\( \boldsymbol{\alpha}_t = f(\mathbf{h}^P_t,\mathbf{d}_{t-1},\mathbf{h}^Q_T)\)
\( \mathbf{h}_{post} = \sum_{j=1}^{p} \alpha_{jt}\mathbf{h}_j^P \)

Query RNN

\(\boldsymbol \alpha_t\)

\(\Big\{\)

\(\mathbf{h}_{post}\)

Sequential Attention

\(\boldsymbol \alpha_t\)

\(\Big\{\)

\(\mathbf{h}_{post}\)

\( \mathbf{p}^b_i = softmax(\mathbf{u}^bW^b_m\mathbf{h}^K_i)\)
\( \mathbf{o}^b = \sum_{j=1}^e p^b_j\mathbf{h}^K_j \)
\( \mathbf{u}^{b+1} = \mathbf{u}^b + \mathbf{o}^b \)
Final hop's output vector: \( \mathbf{h}_{kb} = \mathbf{o}^{B+1} \)

KB Memory Network

Sequential Attention

\(\boldsymbol \alpha_t\)

\(\Big\{\)

\(\mathbf{h}_{post}\)

Pre-KB

\( \mathbf{h}_t^R = BiRNN(\mathbf{h}_{t-1}^R,\mathbf{x}_t)\)
\( \boldsymbol \beta_t = f(\mathbf{h}_j^R , \mathbf{d}_{t-1} , \mathbf{h}^Q_T , \mathbf{h}_{post} , \mathbf{h}_{kb})\)
\( \mathbf{h}_{pre} = \sum_{j=1}^r \beta_{jt}\mathbf{h}^R_j \)

\(\boldsymbol \beta_t\)

\(\Big\}\)

\(\mathbf{h}_{pre}\)

End-to-End Network

Outline

Introduction
Related Work
- Modular Architecture
- End-to-End Architecture
- Existing Neural Models
Problem Statement
Proposed Models
- Sequential Attention Network
- GCN with Sequential Attention
Proposed Dataset
- Modified DSTC2
- Code-mixed dialogue
Results and Analysis
Conclusion

Graph Convolutional Network (GCN)

GCN computes representations for the nodes of a graph by looking at the neighbourhood of the node
Formally, \( \mathcal{G = (V,E)}\) be a graph
Let \( \mathcal{X} \in \mathbb{R}^{n \times m}\) be the input feature matrix for \(n\) nodes
Each node (\(\mathbf{x}_u \in \mathbb{R}^m\)) is an m-dimensional feature vector.
The output of 1-hop GCN is \( \mathcal{H} \in \mathbb{R}^{n \times d}\)
Each \( \mathbf{h}_v \in \mathbb{R}^{d}\) is a node representation that captures the 1-hop neighbourhood information

\mathbf{h}_v^{k+1} = ReLU \bigg( \sum_{u \in \mathcal{N}(v)} (W^k\mathbf{h}_u^{k} + \mathbf{b}^k) \bigg) \quad , \quad \forall v \in \mathcal{V}

Here \(k\) is the hop number
\(\mathbf{h}^1_u = \mathbf{x}_u \)
\( \mathcal{N}(v)\) is the set of neighbours of node \(v\)

Semi-supervised classification with graph convolutional networks. Kipf and Welling, ICLR, 2017.

Problem

Dialogue : \( \{ (u_1,s_1),(u_2,s_2),...,(k_1,k_2,...,k_e),...,(u_n,s_n) \} \)
Each \(k_i\) is of the form: (entity\(_1\), relation, entity\(_2\))
The KB triples can be represented as a graph : \( \mathcal{G}_k = (\mathcal{V}_k,\mathcal{E}_k) \)
- where \(\mathcal{V}_k\) is the set of entities in the KB triples
- \( \mathcal{E}_k\) is the set of edges where each edge is of the form : (entity\(_1\), entity\(_2\), relation)
At the \( t^{th}\) turn of the dialogue, given the:
- Dialogue History: H = \( (u_1,s_1,...,s_{t-1}) \)
- The current user utterance as query: Q = \( u_t\)
- The knowledge graph \(\mathcal{G}_k\)
The task is to generate the current system utterance \(s_t\)

Syntactic GCNs with RNN

\mathbf{a}_v^{k+1} = ReLU \bigg( \sum_{u \in \mathcal{N}(v)} (V^{k}_{dir(u,v)}\mathbf{a}_u^{k} + \mathbf{o}^{k}_{dir(u,v)}) \bigg), \forall v \in \mathcal{V}_H

Obtain the dependency graph for the dialogue history : \( \mathcal{G}_H =(\mathcal{V}_H,\mathcal{E}_H)\)

RNN-Encoder

Syntactic GCNs with RNN

\mathbf{a}_v^{k+1} = ReLU \bigg( \sum_{u \in \mathcal{N}(v)} (V^{k}_{dir(u,v)}\mathbf{a}_u^{k} + \mathbf{o}^{k}_{dir(u,v)}) \bigg), \forall v \in \mathcal{V}_H

\mathbf{s}_t = BiRNN_H(\mathbf{s}_{t-1},\mathbf{p}_t)

GCN

RNN - GCN

GCN with Sequential Attention

Query Attention

\[ \alpha_{jt} = f_1(\mathbf{c}^f_j, \mathbf{d}_{t-1}) \]

\[ \mathbf{h}^Q_t =\sum_{j'=1}^{|Q|} \alpha_{j't}\mathbf{c}_{j'}^f \]

History Attention

\[\beta_{jt} = f_2(\mathbf{a}^f_j, \mathbf{d}_{t-1}, \mathbf{h}^Q_t)\]

\[ \mathbf{h}^H_t = \sum_{j'=1}^{|H|} \beta_{j't}\mathbf{a}_{j'}^f \]

KB Attention

\[ \gamma_{jt} = f_3(\mathbf{r}^f_j,\mathbf{d}_{t-1}, \mathbf{h}^Q_t,\mathbf{h}^H_t)\]

\[ \mathbf{h}^K_t = \sum_{j'=1}^m \gamma_{j't}\mathbf{r}_{j'}^f \]

GCNs for code-mixed utterances

Dependency Parsers are not available for code-mixed sentences
Need an alternate way of extracting structural information
Create a global word co-occurrence matrix from the entire corpus
The context window of a word is the entire length of its sentence
Connect edges between two words if their co-occurrence frequency is above a certain threshold value
We experiment with raw frequency and Positive Pointwise Mutual Information (PPMI)\(^1\) values
Decided the threshold by taking the median of non-zero entries in the matrix

\(^1\)Word association norms mutual information, and lexicography, Church and Hanks, Computational Linguistics, 1990

The_Place is a nice restaurant that serves British food.
Fancy_pub is a nice restaurant that serves British food.
Prezzo is a nice restaurant that serves Italian food.
<restaurant> is a nice restaurant that serves <cuisine> food.

To inject proper entities in the responses we need a different mechanism
The backbone of the sentences should be generated from the vocabulary
The correct entities should be copied from the KB into the correct position of the generated response

The_Place

serves

British

food

and

the

prices

are

expensive

\( labelc \)

Chinese

British

Italian

cheap

expensive

moderate

Fancy_Pub

The_Place

Prezzo

\( Memory = \)

Copy Mechanism

Memory Network

\( P^k = softmax(r^fC^kq^k)\)

\( q^{k+1} = q^k + \sum_{j=0}^{m}P^k_jr^f_j\)

\( q^{1} = d_{t}\)

\hat{y}_t = \left\{ \begin{array}{c l} argmax(P_{vocab}) &: \text{if } argmax(P_{copy}) = \\ argmax(P_{copy}) &: \text{otherwise} \end{array}\right.

'#'

\( P_{vocab} = softmax(V'd_{t} + b')\)

\mathscr{L}_t = -\log P_{vocab}(y_{t}) - \log P_{copy}(labelc_t)

\(r^f\) : KB-GCN representations
\(C^k\) : Parameter Matrix

Mem2seq: Effectively incorporating knowledge bases into end-to-end task oriented dialog systems, Madotto et. al., ACL, 2018

Copy Mechanism

Memory

Generated

Response

Heat map for \( P_{copy}\) across all decoder time steps

Outline

Introduction
Related Work
- Modular Architecture
- End-to-End Architecture
- Existing Neural Models
Problem Statement
Proposed Models
- Sequential Attention Network
- GCN with Sequential Attention
Proposed Dataset
- Modified DSTC2
- Code-mixed dialogue
Results and Analysis
Conclusion

DSTC2 dataset

Goal-oriented dialogue dataset of Dialogue State Tracking Challenge (DSTC2)\(^1\)
Restaurant reservation domain
The dialogues contain 3 slots: area, cuisine, price range and 113 restaurants.
Users sometimes change their goals and look for alternative areas, cuisines and price ranges.

\(^1\)The second dialog state tracking challenge, Henderson et. al., SIGDIAL, 2014

Utterance	Annotations
Where is this restaurant located?	request{area}
Prezzo is located in the north part of town	inform{area= north}
Find me a cheap Chinese restarurant	search(cuisine=Chinese,price=cheap)
Do you have anything else?	search(by_alternative)

Modified DSTC2

System: Hello, what can I help you with today?

User: Hi!

User: I'd like to book a table for six people in an expensive restaurant with British food.

System: where should it be ?

User: Somewhere in the north of the town.

System: ok I am on it!

System: API_CALL (British, north, six, expensive)

The_Place R_cuisine British

The_Place R_location north

The_Place R_address The_Place_Address

The_Place R_price expensive

The_Place R_rating 10

Fancy_pub R_cuisine British

Fancy_pub R_location north

Fancy_pub R_address Fancy_pub_Address

Fancy_pub R_price expensive

Fancy_pub R_rating 8

System: How about The_Place?

User: No I don't like it.

System: Ok, then, what do you think about Fancy_Pub?

User: Yes! lets do it.

System: Great! I'll do the reservation.

User: What is the address?

System: Here it is: Fancy_Pub_Address

User: Thank You

System: You're welcome

Learning end-to-end goal-oriented dialog, Bordes et. al. , ICLR, 2017.

Outline

Introduction
Related Work
- Modular Architecture
- End-to-End Architecture
- Existing Neural Models
Problem Statement
Proposed Models
- Sequential Attention Network
- GCN with Sequential Attention
Proposed Dataset
- Modified DSTC2
- Code-mixed dialogue
Results and Analysis
Conclusion

Code-mixed Data Collection

Build on top of modified DSTC2 dataset
Collect code-mixed dialogues using this dataset in four languages :
- Hindi-English, Bengali-English, Gujarati-English and Tamil-English.

Extract Unique

Utterances

Replace entities

with placeholders

Unique

utterances

Crowdsource

code-mixing

utterance templates

Replace placeholders

with entities

code-mixed templates

Replace utterances

back into dialogue

code-mixed

utterances

code-mixed dialogue data

English

dialogue data

Sorry there is no Chinese restaurant in the west part of town

Sorry there is no Italian restaurant in the north part of town

Sorry there is no <CUISINE> restaurant in the <AREA> part of town

Data Evaluation

We code-mixed individual utterances and stitched them back into a dialogue
How do we ensure that the dialogue makes sense:
We did Human Evaluations:
- 100 randomly chosen dialogues
- 3 evaluators per language
- 3 criteria for evaluation of a dialogue:
  - Colloquialism: code-mixing was colloquial throughout the dialogue and not forced
  - Intelligibility: dialogue can be understood by a bilingual speaker
  - Coherent: dialogue looks coherent with each utterance fitting appropriately in the context

Quantification of Code-mixing

Code-mixing : Foreign language words embedded into a Native (Matrix) language sentence.

C_u(x) =\left\{ \begin{array}{ll} \frac{N(x)-\underset{L_{i} \in \mathcal{L}} \text{max} \{ t_{L_i} \}}{N(x)} &: N(x)>0\\ 0 &: N(x)=0 \end{array}\right.

where \( x\) is an utterance
\( N(x) \) is the number of language specific tokens in \(x\)
\( \mathcal{L} \) is the set of all languages and \( t_{L_i}\) is the number of tokens of language \(L_i\)

Consider the number of language switch points in an utterance : \( \frac{P(x)}{N(x)}\)

C_u(x) = 100\cdot\frac{N(x) - \underset{L_{i} \in \mathcal{L} } \text{max} \{ t_{L_i} \} + P(x)}{2N(x)}: (\textit{if}~N(x) >0)

C_{avg} = \frac{1}{U}\sum_{i=1}^{U}C_u(x_i)

Comparing the level of code-switching in corpora, Björn Gambäck and Amitava Das, LREC, 2016

"Prezzo ek accha restaurant hain in the north part of town jo tasty chinese food serve karta hain."

Quantification of Code-mixing

Comparing the level of code-switching in corpora, Björn Gambäck and Amitava Das, LREC, 2016

We replace the \( \text{max} \) with the following:

\mathit{native}(x) = \left\{ \begin{array}{c l} t_{L_n} &: t_{L_n} > 0 \\ N(x) &: t_{L_n} = 0 \end{array}\right.

C_c=\frac{100}{U}\left[ \frac{1}{2} \sum_{i=1}^{U} \left( 1-\frac{\mathit{native}(x)+P(x)}{N(x)} + \delta(x) \right) + \frac{5}{6}S\right]

With other two other factors :
- \( \delta(x) \) : for inter-utterance mixing
- \(S\) : number of code-mixed utterances out of \(U\) utterances.

Outline

Introduction
Related Work
- Modular Architecture
- End-to-End Architecture
- Existing Neural Models
Problem Statement
Proposed Models
- Sequential Attention Network
- GCN with Sequential Attention
Proposed Dataset
- Modified DSTC2
- Code-mixed dialogue
Results and Analysis
Conclusion

Baseline Results

Established initial baseline results using two generation based models:
- Sequence-to-sequence with attention
- Hierarchical Recurrent Encoder-Decoder (HRED)

per-response accuracy: exact match accuracy between the generated response and the ground truth.
BLEU, ROUGE: n-gram overlap based metric to evaluate generation quality
Entity F1: Micro-average of F1 scores between ground truth entities and generated entities.

Results on En-DSTC2

RNN + CROSS -GCN-SeA

Connect edges between query/history words and KB entities if they exactly match
Creates one global graph, encoded using one GCN
Then separated into different contexts to perform the sequential attention

Results on code-mixed data

Effect of using more GCN hops

PPMI vs Raw Frequencies

Using the PPMI scores gives a better contextual graph compared to using raw frequency
Evident across all other languages except English

Dependency or co-occurrence structure really needed ?

Dependency edges

Random edges

Ablations

RNN

GCN

RNN-GCN

Encoder :

Attention :

Bahdanau

Sequential

GCN

RNN-GCN

Sequential

RNN

GCN

RNN-GCN

Ablations

GCNs do not outperform RNNs independently:
- performance of GCN-Bahdanau attention < RNN-Bahdanau attention
Our Sequential attention outperforms Bahdanau attention:
- GCN-Bahdanau attention < GCN-Sequential attention
- RNN-Bahdanau attention < RNN-Sequential attention (BLEU & ROUGE)
- RNN+GCN-Bahdanau attention < RNN+GCN-Sequential attention
Combining GCNs with RNNs helps:
- RNN-Sequential attention < RNN+GCN-Sequential attention
Best results are always obtained by the final model which combines RNN, GCN and Sequential attention

Conclusion

A single attention distribution overburdens the attention mechanism
Separated the history into Pre-KB, KB and Post-KB parts and attended sequentially over them
Showed that structure-aware representations are useful in goal-oriented dialogue
Used GCNs to infuse structural information of dependency graphs into the learned representations
Introduced a goal-oriented code-mixed dialogue dataset for four languages
Quantified the amount of code-mixing present in the dataset
When dependency parsers are not available, we used word co-occurrence frequencies and PPMI values to extract a contextual graph
Obtained state-of-the-art performance on the modified DSTC2 dataset and its code-mixed versions

Future Work

Extend the model to multidomain goal-oriented dialogue (restaurants, hotels, taxi)
Conditional code-mixed response generation
Better copy mechanism
Use the whole Knowledge-Graph instead of dialogue specific KB triples
Use semantic graphs along with dependency parse trees

Publications

A Dataset for building Code-Mixed Goal Oriented Conversation Systems, Suman Banerjee, Nikita Moghe, Siddhartha Arora and Mitesh M. Khapra, In the Proceedings of the 27th International Conference on Computational Linguistics, COLING, Santa Fe, New-Mexico, USA, August 2018.

Graph Convolutional Network with Sequential Attention For Goal-Oriented Dialogue Systems, Suman Banerjee and Mitesh M. Khapra, Transactions of the Association for Computational Linguistics (TACL), 2019. (Under Review)

Questions?

Language Understanding

User utterance

Predicted

Intent

I need a cheap chinese restaurant in the north of town.

Intent Classification

request_rest
request_address
request_phone
.
.
.
book_table

Given a collection of utterances \( u_i \) and intent labels \( l_i : D = \{ (u_1,l_1),(u_2,l_2), \dots, (u_n,l_n) \} \), train a model to predict the intent for each utterance.

Classifier