README.md

## Dataset Overview 

### Where to find the data and its documentation 

#### What is the webpage for the dataset (if it exists)? 

https://github.com/google-research-datasets/Taskmaster/tree/master/TM-3-2020 

#### What is the link to where the original dataset is hosted? 

https://github.com/google-research-datasets/Taskmaster/tree/master/TM-3-2020 

#### What is the link to the paper describing the dataset (open access preferred)? 

https://arxiv.org/pdf/2012.12458.pdf 

#### Provide the BibTex-formatted reference for the dataset. Please use the correct published version (ACL anthology, etc.) instead of google scholar created Bibtex. 

```
@article{byrne2020tickettalk,
  title={TicketTalk: Toward human-level performance with end-to-end, transaction-based dialog systems},
  author={Byrne, Bill and Krishnamoorthi, Karthik and Ganesh, Saravanan and Kale, Mihir Sanjay},
  journal={arXiv preprint arXiv:2012.12458},
  year={2020}
}
``` 

@article{byrne2020tickettalk,
  title={TicketTalk: Toward human-level performance with end-to-end, transaction-based dialog systems},
  author={Byrne, Bill and Krishnamoorthi, Karthik and Ganesh, Saravanan and Kale, Mihir Sanjay},
  journal={arXiv preprint arXiv:2012.12458},
  year={2020}
} 

#### If known, provide the name of at least one person the reader can contact for questions about the dataset. 

Karthik Krishnamoorthi 

#### If known, provide the email of at least one person the reader can contact for questions about the dataset. 

[email protected] 

#### Does the dataset have an active leaderboard? 

no 

### Languages and Intended Use 

#### Is the dataset multilingual? 

no 

#### What dialects are covered? Are there multiple dialects per language? 

NA 

#### What languages/dialects are covered in the dataset? 

English 

#### Whose language is in the dataset? 

NA 

#### What is the license of the dataset? 

cc-by-4.0: Creative Commons Attribution 4.0 International 

#### What is the intended use of the dataset? 

Dialogues 

#### What primary task does the dataset support? 

Dialog Response Generation 

#### Provide a short description of the communicative goal of a model trained for this task on this dataset. 

a movie ticketing dialog dataset with 23,789 annotated conversations.  

### Credit 

#### In what kind of organization did the dataset curation happen? 

other 

#### Name the organization(s). 

NA 

#### Who created the original dataset? List the people involved in collecting the dataset and their affiliation(s). 

Google researchers 

#### Who funded the data creation? 

Google 

#### Who contributed to the data card and adding the dataset to GEM? List the people+affiliations involved in creating this data card and who helped integrate this dataset into GEM. 

Tosin Adewumi (Luleå University of Technology) 

### Structure 

#### List and describe the fields present in the dataset. 

gem_id
utterances
instruction_id
conversation_id

#### How was the dataset structure determined? 

NA 

#### How were the labels chosen? 

NA 

#### Provide a JSON formatted example of a typical instance in the dataset. 

```json
GEM-TASKMASTER-TEST-0,0,"<U>correct<C><U>i'll love to see a movie tonight<A>Sure. What movie would you like to see?<U>i havn't decided yet.can you help with any?<A>No problem. Can you tell me what city you’re in?<U>in currently in oak valley,arkansas.<PN>find_movies<PAN>location<PAV>Oak Valley, Arkansas<PR>find_movies<PRAN>name.movie<PRAV>No Time To Die<PRAV>Emma<A>Ok. There are a couple of popular films out in your area: No Time To Die and Emma. Do either of those sound interesting?<U>i'm quite familiar with no time to die but tell me more about emma.<PN>get_movie_attribute<PAN>attribute<PAV>description.plot<PAN>name.movie<PAV>Emma<PR>get_movie_attribute<PRAN>description.plot<PRAV>In this adaptation of Jane Austen's classic novel, pretty socialite Emma Woodhouse, played by Gwyneth Paltrow, entertains herself by playing matchmaker for those around her<A>OK. Here’s the description of Emma: In this adaptation of Jane Austen's classic novel, pretty socialite Emma Woodhouse, played by Gwyneth Paltrow, entertains herself by playing matchmaker for those around her.<U>hum i love that description,i'll love to book two tickets to emma<PN>find_theaters<PAN>location<PAV>Oak Valley, Arkansas<PAN>name.movie<PAV>Emma<PR>find_theaters<PRAN>name.theater<PRAV>AMC Mercado 24<PN>find_showtimes<PAN>date.showing<PAV>tonight<PAN>name.movie<PAV>Emma<PAN>name.theater<PAV>AMC Mercado 24<PR>find_showtimes<PRAN>time.showing<PRAV>5:00pm<PRAV>7:10pm<PRAV>9:45pm<A>OK. Emma is playing at AMC Mercado 24 today at 5:00pm, 7:10pm, and 9:45pm. Which time would you like?<U>7:10pm is fine<A>All right. Let me confirm that you’d like two tickets for Emma at AMC Mercado 24 tonight at 7:10pm. Is that all correct?",[A]Is it OK to go ahead and purchase these tickets?,dlg-32b67f97-6fcb-4135-b0bc-ac6aa248b889
``` 

GEM-TASKMASTER-TEST-0,0,"<U>correct<C><U>i'll love to see a movie tonight<A>Sure. What movie would you like to see?<U>i havn't decided yet.can you help with any?<A>No problem. Can you tell me what city you’re in?<U>in currently in oak valley,arkansas.<PN>find_movies<PAN>location<PAV>Oak Valley, Arkansas<PR>find_movies<PRAN>name.movie<PRAV>No Time To Die<PRAV>Emma<A>Ok. There are a couple of popular films out in your area: No Time To Die and Emma. Do either of those sound interesting?<U>i'm quite familiar with no time to die but tell me more about emma.<PN>get_movie_attribute<PAN>attribute<PAV>description.plot<PAN>name.movie<PAV>Emma<PR>get_movie_attribute<PRAN>description.plot<PRAV>In this adaptation of Jane Austen's classic novel, pretty socialite Emma Woodhouse, played by Gwyneth Paltrow, entertains herself by playing matchmaker for those around her<A>OK. Here’s the description of Emma: In this adaptation of Jane Austen's classic novel, pretty socialite Emma Woodhouse, played by Gwyneth Paltrow, entertains herself by playing matchmaker for those around her.<U>hum i love that description,i'll love to book two tickets to emma<PN>find_theaters<PAN>location<PAV>Oak Valley, Arkansas<PAN>name.movie<PAV>Emma<PR>find_theaters<PRAN>name.theater<PRAV>AMC Mercado 24<PN>find_showtimes<PAN>date.showing<PAV>tonight<PAN>name.movie<PAV>Emma<PAN>name.theater<PAV>AMC Mercado 24<PR>find_showtimes<PRAN>time.showing<PRAV>5:00pm<PRAV>7:10pm<PRAV>9:45pm<A>OK. Emma is playing at AMC Mercado 24 today at 5:00pm, 7:10pm, and 9:45pm. Which time would you like?<U>7:10pm is fine<A>All right. Let me confirm that you’d like two tickets for Emma at AMC Mercado 24 tonight at 7:10pm. Is that all correct?",[A]Is it OK to go ahead and purchase these tickets?,dlg-32b67f97-6fcb-4135-b0bc-ac6aa248b889 

#### Describe and name the splits in the dataset if there are more than one. 

train
dev
test 

#### Describe any criteria for splitting the data, if used. If there are differences between the splits (e.g., if the training annotations are machine-generated and the dev and test ones are created by humans, or if different numbers of annotators contributed to each example), describe them here. 

NA 

#### What does an outlier of the dataset in terms of length/perplexity/embedding look like? 

NA 

## Dataset in GEM 

### Rationale 

#### What does this dataset contribute toward better generation evaluation and why is it part of GEM? 

Dialogue generation that makes sense 

#### Do other datasets for the high level task exist? 

yes 

#### Does this dataset cover other languages than other datasets for the same task? 

no 

#### What else sets this dataset apart from other similar datasets in GEM? 

NA 

#### What aspect of model ability can be measured with this dataset? 

NA 

### GEM Additional Curation 

#### Has the GEM version of the dataset been modified in any way (data, processing, splits) from the original curated data? 

yes 

#### What changes have been made to he original dataset? 

other 

#### For each of these changes, described them in more details and provided the intended purpose of the modification 

gem_id field was added to the 3 data splits 

#### Does GEM provide additional splits to the dataset? 

no 

### Getting Started 

#### Getting started with in-depth research on the task. Add relevant pointers to resources that researchers can consult when they want to get started digging deeper into the task. 

https://github.com/google-research-datasets/Taskmaster/tree/master/TM-3-2020 

#### Technical terms used in this card and the dataset and their definitions 

NA 

## Previous Results 

### Previous Results 

#### What aspect of model ability can be measured with this dataset? 

BLEU: 60 

#### What metrics are typically used for this task? 

BLEU 

#### List and describe the purpose of the metrics and evaluation methodology (including human evaluation) that the dataset creators used when introducing this task. 

automatic evaluation 

#### Are previous results available? 

yes 

#### What evaluation approaches have others used? 

NA 

#### What are the most relevant previous results for this task/dataset? 

NA 

## Dataset Curation 

### Original Curation 

#### Original curation rationale 

NA 

#### What was the communicative goal? 

a movie ticketing dialog dataset with 23,789 annotated conversations. 

#### Is the dataset aggregated from different data sources? 

no 

### Language Data 

#### How was the language data obtained? 

Crowdsourced 

#### If crowdsourced, where from? 

Participatory experiment 

#### What further information do we have on the language producers? 

NA 

#### Does the language in the dataset focus on specific topics? How would you describe them? 

Ticketing 

#### Was the text validated by a different worker or a data curator? 

not validated 

#### Were text instances selected or filtered? 

not filtered 

### Structured Annotations 

#### Does the dataset have additional annotations for each instance? 

none 

#### Was an annotation service used? 

no 

### Consent 

#### Was there a consent policy involved when gathering the data? 

no 

#### If not, what is the justification for reusing the data? 

NA 

### Private Identifying Information (PII) 

#### Does the source language data likely contain Personal Identifying Information about the data creators or subjects? 

no PII 

#### Provide a justification for selecting `no PII` above. 

It's based on ticketing without personal information 

### Maintenance 

#### Does the original dataset have a maintenance plan? 

no 

## Broader Social Context 

### Previous Work on the Social Impact of the Dataset 

#### Are you aware of cases where models trained on the task featured in this dataset ore related tasks have been used in automated systems? 

no 

### Impact on Under-Served Communities 

#### Does this dataset address the needs of communities that are traditionally underserved in language technology, and particularly language generation technology? Communities may be underserved for exemple because their language, language variety, or social or geographical context is underepresented in NLP and NLG resources (datasets and models). 

no 

### Discussion of Biases 

#### Are there documented social biases in the dataset? Biases in this context are variations in the ways members of different social categories are represented that can have harmful downstream consequences for members of the more disadvantaged group. 

unsure 

#### Does the distribution of language producers in the dataset accurately represent the full distribution of speakers of the language world-wide? If not, how does it differ? 

NA 

## Considerations for Using the Data 

### PII Risks and Liability 

#### Considering your answers to the PII part of the Data Curation Section, describe any potential privacy to the data subjects and creators risks when using the dataset. 

NA 

### Licenses 

#### Based on your answers in the Intended Use part of the Data Overview Section, which of the following best describe the copyright and licensing status of the dataset? 

open license - commercial use allowed 

#### Based on your answers in the Language part of the Data Curation Section, which of the following best describe the copyright and licensing status of the underlying language data? 

public domain 

### Known Technical Limitations 

#### Describe any known technical limitations, such as spurrious correlations, train/test overlap, annotation biases, or mis-annotations, and cite the works that first identified these limitations when possible. 

NA 

#### When using a model trained on this dataset in a setting where users or the public may interact with its predictions, what are some pitfalls to look out for? In particular, describe some applications of the general task featured in this dataset that its curation or properties make it less suitable for. 

NA 

#### What are some discouraged use cases of a model trained to maximize the proposed metrics on this dataset? In particular, think about settings where decisions made by a model that performs reasonably well on the metric my still have strong negative consequences for user or members of the public. 

NA