Programme – ALTA 2021

8th December (Wednesday) Workshop Day 1 (all times AEDT)

  • 14:00 Tutorial on Machine Translation and Summarization – Inigo Jauregi, Jacob Parnell, and Massimo Piccardi
  • 16:00 Social Gathering/Mentoring – Kumospace
  • 17:00 End of Day 1

9th December (Thursday) Workshop Day 2 (all times AEDT)

  • 9:00 ALTA Keynote – Barbara Plank: Tackling scarce and biased data for more inclusive Natural Language Processing
  • 10:00 Social Gathering/Brunch/Mentorship – Kumospace
  • 10:30 Welcome to Day 2
  • 10:40 Oral Presentations 1 (Long: 10m + 3m QA, Short: 8m + 2m)

    • Combining Shallow and Deep Representations for Text-Pair Classification
      Vincent Nguyen, Sarvnaz Karimi and Zhenchang Xing

    • Robustness Analysis of Grover for Machine-Generated News Detection
      Rinaldo Gagiano, Maria Myung-Hee Kim, Xiuzhen Zhang and Jennifer Biggs

    • Using Word Embeddings to Quantify Ethnic Stereotypes in 12 years of Spanish News.
      Danielly Sorato, Diana Zavala-Rojas and Maria del Carme Colominas Ventura

    • Multi-modal Intent Classification for Assistive Robots with Large-scale Naturalistic Datasets
      Karun Varghese Mathew, Venkata S Aditya Tarigoppula and Lea Frermann

    • Does QA-based intermediate training help fine-tuning language models for text classification?
      Shiwei Zhang and Xiuzhen Zhang

    • Using Discourse Structure to Differentiate Focus Entities from Background Entities in Scientific Literature
      Antonio Jimeno Yepes, Ameer Albahem and Karin Verspoor

  • 11:52 Afternoon Break/Lunch/Social Gathering/Mentorship (includes papers from Session 1)
  • 14:00 Oral Presentations 2 (Long: 10m + 3m QA, Short: 8m + 2m)

    • An Approach to the Frugal Use of Human Annotators to Scale up Auto-coding for Text Classification Tasks
      Li'An Chen and Hanna Suominen

    • Exploring the Vulnerability of Natural Language Processing Models via Universal Adversarial Texts
      Xinzhe Li, Ming Liu, Xingjun Ma and Longxiang Gao

    • Phone Based Keyword Spotting for Transcribing Very Low Resource Languages
      Eric Le Ferrand, Steven Bird and Laurent Besacier

    • Exploring Story Generation with Multi-task Objectives in Variational Autoencoders
      Zhuohan Xie, Jey Han Lau and Trevor Cohn

  • 14:52 Break: Social Gathering/Mentorship
  • 15:07 Oral Presentations 3 (Long: 10m + 3m QA, Short: 8m + 2m)

    • Evaluating Hierarchical Document Categorisation
      Qian Sun, Aili Shen, Hiyori Yoshikawa, Chunpeng Ma, Daniel Beck, Tomoya Iwakura and Timothy Baldwin

    • Cross-Domain Language Modeling: An Empirical Investigation
      Vincent Nguyen, Sarvnaz Karimi, Maciej Rybinski and Zhenchang Xing

    • BERT's The Word : Sarcasm Target Detection using BERT
      Pradeesh Parameswaran, Andrew Trotman, Veronica Liesaputra and David Eyers

    • A Computational Acquisition Model for Multi-modal Word Learning from Scratch
      Uri Berger, Gabriel Stanovsky, Omri Abend and Lea Frermann

    • Retrodiction as Delayed Recurrence: the Case of Adjectives in Italian and English
      Raquel G. Alhama, Francesca Zermiani and Atiqah Khaliq

    • Automatic Post-Editing for Translating Chinese Novels to Vietnamese
      Thanh Vu and Dai Quoc Nguyen

  • 16:07 Poster Session (all papers in Oral presentations 1 and 2)
  • 17:30 End of Day 2

10th December (Friday) Workshop Day 3 (all times AEDT)

  • 10:00 Welcome to Day 3
  • 10:05 Oral Presentations 4 (Long: 10m + 3m QA, Short: 8m + 2m)

    • Inductive Biases for Low Data VQA: A Data Augmentation Approach
      Narjes Askarian, Ehsan Abbasnejad, Ingrid Zukerman, Wray Buntine and Reza Haffari

    • Evaluation of Review Summaries via Question-Answering
      Nannan Huang and Xiuzhen Zhang

    • Curriculum Learning Effectively Improves Low Data VQA
      Narjes Askarian, Ehsan Abbasnejad, Ingrid Zukerman, Wray Buntine and Reza Haffari

    • Document Level Hierarchical Transformer
      Najam Zaidi, Trevor Cohn and Gholamreza Haffari

  • 11:00 ALTA Keynote – Ben Hutchinson: NLP Ethics Into Context
  • 12:00 Break/Lunch/Social Gathering/Mentorship – Kumospace
  • 13:30 Oral Presentation 5 (Long: 10m + 3m QA, Short: 8m + 2m)

    • Harnessing Privileged Information for Hyperbole Detection
      Rhys Biddle, Maciek Rybinski, Qian Li, Cecile Paris and Guandong Xu

    • Principled Analysis of Energy Discourse across Domains with Thesaurus-based Automatic Topic Labeling
      Thomas Scelsi, Alfonso Martinez Arranz and Lea Frermann

    • Generating and Modifying Natural Language Explanations
      Abdus Salam, Rolf Schwitter and Mehmet Orgun

    • Findings on Conversation Disentanglement
      Rongxin Zhu, Jey Han Lau and Jianzhong Qi

  • 14:22 Overview of the 2021 ALTA Shared Task: Automatic Grading of Evidence, 10 Years Later – Diego Molla-Aliod

    • Quick, get me a Dr. BERT: Automatic Grading of Evidence using Transfer Learning
      Pradeesh Parameswaran, Andrew Trotman, Veronica Liesaputra, David Eyers

    • An Ensemble Model for Automatic Grading of Evidence
      Yuting Guo, Yao Ge, Ruqi Liao, Abeed Sarker

    • Handling Variance of Pretrained Language Models in Grading Evidence in the Medical Literature
      Fajri Koto, Biaoyan Fang

  • 15:02 ALTA General Meeting
  • 15:17 Best Paper Awards
  • 15:22 Poster Session (All papers in Oral sessions 3 and 4)
  • 17:00 ALTA Keynote – Dirk Hovy: More than words – Integrating social factors into language modeling
  • 18:00 Social Gathering/Mentorship – Kumospace
  • 16:30 End of Day 3