Registration form for ReproNLP 2023

JavaScript isn't enabled in your browser, so this file can't be opened. Enable and reload.

This is the registration form participants in the ReproNLP 2023 Shared Task need to complete as a first step. Once we have received your registration we will send you the ReproGen instructions for participants and give you access to the shared task information for the tracks and papers you have selected in the form.

The registration form will remain open throughout ReproNLP 2023 (i.e. until August 2023).

For full information about the ReproNLP Shared Task please see https://repronlp.github.io/

Team name (you can change this before results are published) *

Names and affiliations of team members *

Name and email address of main contact *

Track A: Which paper(s) are you planning to reproduce for Track A? Select all that apply (you can change your mind at any time). *

van der Lee et al. (2017): PASS: A Dutch data-to-text system for soccer, targeted towards specific audiences: https://www.aclweb.org/anthology/W17-3513.pdf [1 human evaluation study; Dutch; 20 evaluators; 1 quality criterion; primary scores]

Dušek et al. (2018): Findings of the E2E NLG Challenge: https://www.aclweb.org/anthology/W18-6539.pdf [1 human evaluation study; English; MTurk; 2 quality criteria; primary scores]

Qader et al. (2018): Generation of Company descriptions using concept-to-text and text-to-text deep models: dataset collection and systems evaluation: https://www.aclweb.org/anthology/W18-6532.pdf [1 human evaluation study; English; 19 evaluators; 4 quality criteria; primary scores]

Santhanam & Shaikh (2019): Towards Best Experiment Design for Evaluating Dialogue System Output: https://www.aclweb.org/anthology/W19-8610.pdf [3 human evaluation studies differing in experimental design; English; 40 evaluators; 2 quality criteria; reproduction target: correlation scores between 3 studies]

Nisioi et al. (2017): Exploring Neural Text Simplification Models: https://aclanthology.org/P17-2014.pdf one automatic evaluation study; reproduction target: two automatic scores]; [one human evaluation study; 70 sentences; 9 system outputs; 4 quality criteria; reproduction target: primary scores]

Not planning to participate in Track A

Required

Track B: If you are planning to participate in Track B, which of your own studies are you planning to reproduce? Please include a URL (arxiv.org only if not published elsewhere). Enter 'N/A' if not planning to participate in Track B. *

Track C: Which paper(s) are you planning to reproduce for Track C? Select all that apply (you can change your mind at any time). *

Vamvas & Sennrich (2022): As Little as Possible, as Much as Necessary: Detecting Over and Undertranslations with Contrastive Conditioning: https://aclanthology.org/2022.acl-short.53.pdf [1 human evalution study (of 2 in paper); English to German; 2 evaluators; 1 quality criteria; 1 system; approx. 800 outputs; reproduction target: primary scores]

Lin et al. (2022): Other Roles Matter! Enhancing Role-Oriented Dialogue Summarization via Role Interactions: https://aclanthology.org/2022.acl-long.182.pdf [1 human evaluation study; Chinese; 3 evaluators; 3 quality criteria; 200 outputs per system; 4 systems; reproduction target: primary scores]

Lux & Vu (2022): Language-Agnostic Meta-Learning for Low-Resource Text-to-Speech with Articulatory Features: https://aclanthology.org/2022.acl-long.472.pdf [1 human evaluation; German; Student evaluators (34 responses); 1 quality criterion; 12 outputs per system; 2 systems; reproduction target: primary scores]

Chakrabarty et al. (2022): It's not Rocket Science: Interpreting Figurative Language in Narratives: https://aclanthology.org/2022.tacl-1.34.pdf [2 human evaluation studies (of 4 in paper); English; MTurk; 1 quality criterion; 25 outputs per system, 5/8 systems (varies between idiom and simile studies); reproduction target: primary scores]

Puduppully & Lapata (2021): Data-to-text Generation with Macro Planning: https://aclanthology.org/2021.tacl-1.31.pdf [first human evaluation (relative); English; MTurk; 2 quality criteria; 20 outputs per system; 5 systems, reproduction target: primary scores] [second human evaluation (absolute); English; MTurk; 3 quality criteria; 80 outputs per system; 5 systems; reproduction target: primary scores]

Not planning to participate in Track C

Required

I agree to the above information being stored in this form for the purposes of organising the ReproGen Shared Task 2022 only. I understand that none of the information will be published in any form without my consent. If I submit a report to ReproGen, I consent to its contents being included in a summary report for the shared task, to be published in the same proceedings as the shared task papers. *

I agree

I do not agree

Required

Submit

Clear form

Never submit passwords through Google Forms.

This content is neither created nor endorsed by Google. Report Abuse - Terms of Service - Privacy Policy

Forms