A Context-aware Natural Language Generation Dataset for Dialogue - PowerPoint PPT Presentation

. . . . . . . . . . . . . . A Context-aware Natural Language Generation Dataset for Dialogue Systems Ondřej Dušek and Filip Jurčíček Institute of Formal and Applied Linguistics Charles University in Prague May 28, 2016 LREC RE-WOCHAT workshop 1/ 13 Ondřej Dušek & Filip Jurčíček . . . . . . . . . . . . . . . . . . . . . . . . . . A Context-aware NLG Dataset for Dialogue Systems

• “Ordinary” NLG dataset (in our setting): • input DA (meaning) + natural language sentence(s) • Our set: • input DA + natural language sentences + preceding context • If the generator knows how the user asked, it should be able to . . . . . . . . . . . . . . Introduction Introduction produce a more natural response 2/ 13 Ondřej Dušek & Filip Jurčíček . . . . . . . . . . . . . . . . . . . . . . . . . . A Context-aware NLG Dataset for Dialogue Systems • A new NLG dataset for dialogue systems • English public transport domain

• Our set: • input DA + natural language sentences + preceding context • If the generator knows how the user asked, it should be able to . . . . . . . . . . . Introduction . . Introduction produce a more natural response 2/ 13 Ondřej Dušek & Filip Jurčíček A Context-aware NLG Dataset for Dialogue Systems inform(from_stop="Fulton Street", vehicle=bus, direction="Rector Street", departure_time=9:13pm, line=M21) Go by the 9:13pm bus on the M21 line from Fulton Street directly to . . . . . . . . . . . . . . . Rector Street . . . . . . . . . . . . • A new NLG dataset for dialogue systems • English public transport domain • “Ordinary” NLG dataset (in our setting): • input DA (meaning) + natural language sentence(s)

• If the generator knows how the user asked, it should be able to . . . . . . . . . . . . Introduction . Introduction produce a more natural response 2/ 13 Ondřej Dušek & Filip Jurčíček A Context-aware NLG Dataset for Dialogue Systems I'm headed to Rector Street inform(from_stop="Fulton Street", vehicle=bus, direction="Rector Street", departure_time=9:13pm, line=M21) Go by the 9:13pm bus on the M21 line from Fulton Street directly to Rector Street . . . . . . . . . . . . . . . . . . . . . . . . . . . • A new NLG dataset for dialogue systems • English public transport domain • “Ordinary” NLG dataset (in our setting): • input DA (meaning) + natural language sentence(s) • Our set: • input DA + natural language sentences + preceding context NEW →

. . . . . . . . . . . . . . Introduction Introduction produce a more natural response 2/ 13 Ondřej Dušek & Filip Jurčíček A Context-aware NLG Dataset for Dialogue Systems I'm headed to Rector Street inform(from_stop="Fulton Street", vehicle=bus, direction="Rector Street", departure_time=9:13pm, line=M21) Go by the 9:13pm bus on the M21 line from Fulton Street directly to . . . . . . . . . . . . . . Rector Street . . . . . . . . . . . . • A new NLG dataset for dialogue systems • English public transport domain • “Ordinary” NLG dataset (in our setting): • input DA (meaning) + natural language sentence(s) • Our set: • input DA + natural language sentences + preceding context • If the generator knows how the user asked, it should be able to

. . . . . . . . . . . . . . Introduction Introduction produce a more natural response 2/ 13 Ondřej Dušek & Filip Jurčíček A Context-aware NLG Dataset for Dialogue Systems I'm headed to Rector Street inform(from_stop="Fulton Street", vehicle=bus, direction="Rector Street", departure_time=9:13pm, line=M21) Heading to Rector Street from Fulton Street, take a bus line M21 at . . . . . . . . . . . . . . 9:13pm. . . . . . . . . . . . . • A new NLG dataset for dialogue systems • English public transport domain • “Ordinary” NLG dataset (in our setting): • input DA (meaning) + natural language sentence(s) • Our set: • input DA + natural language sentences + preceding context • If the generator knows how the user asked, it should be able to

• collecting our set . . . . . . . . . . . . . . . Introduction Outline of this talk 2. How to obtain naturally looking contextual data 3. A summary of the collected set 3/ 13 Ondřej Dušek & Filip Jurčíček . . . . . . . . . . . . . . . . . . . . . . . . . A Context-aware NLG Dataset for Dialogue Systems 1. Why should we look at preceding context: entrainment

. . . . . . . . . . . . . . . . Introduction Outline of this talk 2. How to obtain naturally looking contextual data 3. A summary of the collected set 3/ 13 Ondřej Dušek & Filip Jurčíček . . . . . . . . . . . . . . . . . . . . . . . . A Context-aware NLG Dataset for Dialogue Systems 1. Why should we look at preceding context: entrainment • collecting our set

. . . . . . . . . . . . . . . . Introduction Outline of this talk 2. How to obtain naturally looking contextual data 3. A summary of the collected set 3/ 13 Ondřej Dušek & Filip Jurčíček . . . . . . . . . . . . . . . . . . . . . . . . A Context-aware NLG Dataset for Dialogue Systems 1. Why should we look at preceding context: entrainment • collecting our set

• “Mutual linguistic convergence” • speakers primed (influenced) by previously said • Reusing words and syntax • Occurs naturally, subconscious • Found to help dialogue success (Friedberg et al. ‘12) • Several experiments, successful • Limited, partially or completely rule-based . . . . . . . . . Entrainment/alignment/adaptation in dialogue . . Motivation Why context? Entrainment . Entrainment in dialogue systems (Lopes et al. ‘13, ‘15; He et al. ‘14) 4/ 13 Ondřej Dušek & Filip Jurčíček . . . . . . . . . . . . . . . . . . . . . . . . . . . . A Context-aware NLG Dataset for Dialogue Systems

• Reusing words and syntax • Occurs naturally, subconscious • Found to help dialogue success (Friedberg et al. ‘12) • Several experiments, successful • Limited, partially or completely rule-based . . . . . . . . . . Motivation . . . Why context? Entrainment Entrainment/alignment/adaptation in dialogue Entrainment in dialogue systems (Lopes et al. ‘13, ‘15; He et al. ‘14) 4/ 13 Ondřej Dušek & Filip Jurčíček . . . . . . . . . . . . . . . . . . . . . . . . . . . A Context-aware NLG Dataset for Dialogue Systems • “Mutual linguistic convergence” • speakers primed (influenced) by previously said

• Occurs naturally, subconscious • Found to help dialogue success (Friedberg et al. ‘12) • Several experiments, successful • Limited, partially or completely rule-based . . . . . . . . . . Motivation . . . Why context? Entrainment Entrainment/alignment/adaptation in dialogue Entrainment in dialogue systems (Lopes et al. ‘13, ‘15; He et al. ‘14) 4/ 13 Ondřej Dušek & Filip Jurčíček . . . . . . . . . . . . . . . . . . . . . . . . . . . A Context-aware NLG Dataset for Dialogue Systems • “Mutual linguistic convergence” • speakers primed (influenced) by previously said • Reusing words and syntax

• Found to help dialogue success (Friedberg et al. ‘12) • Several experiments, successful • Limited, partially or completely rule-based . . . . . . . . . . . Why context? Entrainment Motivation . Entrainment/alignment/adaptation in dialogue Entrainment in dialogue systems (Lopes et al. ‘13, ‘15; He et al. ‘14) 4/ 13 Ondřej Dušek & Filip Jurčíček A Context-aware NLG Dataset for Dialogue Systems how bout the next ride Sorry, I did not find a later option. . . . . . . . . . . . . . . . . . . . . . . . . . . . . I'm sorry, the next ride was not found. • “Mutual linguistic convergence” • speakers primed (influenced) by previously said • Reusing words and syntax • Occurs naturally, subconscious

• Found to help dialogue success (Friedberg et al. ‘12) • Several experiments, successful • Limited, partially or completely rule-based . . . . . . . . . Motivation Why context? Entrainment Entrainment/alignment/adaptation in dialogue Entrainment in dialogue systems . (Lopes et al. ‘13, ‘15; He et al. ‘14) 4/ 13 Ondřej Dušek & Filip Jurčíček A Context-aware NLG Dataset for Dialogue Systems how bout the next ride Sorry, I did not find a later option. I'm sorry, the next ride was not found. what is the distance of this trip distance of 10.4 miles. It is around 10.4 miles. . . . . . . . . . . . . . . . . . . The distance is 10.4 miles. . . . . . . . . . . . . • “Mutual linguistic convergence” • speakers primed (influenced) by previously said • Reusing words and syntax • Occurs naturally, subconscious The .... trip covers a .........