Natural Language Processing PIC at IBM Research AI - QASP_Workshop

Question Answering and Semantic Parsing (QASP) Workshop

QASP is a part of the IBM AI Research Week.

Registration Link:


Call for Posters:

Machine Reading and Question Answering (MRQA) is an important research topic for evaluating how well AI systems understand natural language, and also very critical for industry applications such as search engines and speech and dialogue systems. In a typical MRQA setup, a system must answer a question by reading one or more context documents. Successful MRQA systems must understand a wide range of natural language situations, and a wide variety of question and document types. A lot of research has spread around the Stanford QA dataset (SQuAD) and recently the Google Natural Questions challenge.

Meanwhile, semantic parsers like AMR and SRL (Semantic Role Labeling) map sentences to formal representations of their underlying meaning. Recently, algorithms have been developed to learn to recover increasingly expressive representations with ever weaker forms of supervision. These advances have enabled many applications, including question answering, relation extraction etc.

This workshop aims to achieve two goals. First, to bring together researchers (university and industry) in the field to discuss the state of the art and opportunities for future research. Second, to create a stage for presenting the variety of current approaches, thereby providing a unique opportunity for new entrants to the field.

We welcome posters showing novel ideas in:

  • Novel techniques in QA
  • Techniques in QA using SP
  • Novel techniques in SP 
  • Techniques in SP helping other NLP applications

Submission method: 

  • Please email your posters title and extended abstract (no more than 500 words) to:
  • Deadline: Sep 10th, 2019

Invited Speakers:

  1.Mohit Iyyer (UMass, Amherst)                                           2. Nianwen Xue (Brandeis University)

 3.  Niranjan Balasubramanian (Stony Brook University)           4.  Lu Wang (Northeastern University)

 5.  Salim Roukos (IBM Research AI)


  1.  Avi Sil (Chair, NLP PIC and Team Lead, Question Answering, IBM Research AI)
  2.   Yunyao Li (Sr. Manager, Scalable Knowledge Intelligence Group, IBM Research AI)
  3.   Radu Florian (Sr. Manager, NLP Group, IBM Research AI)


Important Dates:

  • Call for Posters: Aug 12th, 2019
  • Poster submission deadline: Sep 10th, 2019
  • Notification of acceptance: Sep 15th, 2019
  • Workshop date: September 20th (Friday), 2019


Friday, 9/20

09:00 AM - 04:30 PM

The MIT Samberg Conference Center 

Workshop Schedule:

  • 8.50 - 9.00 : Opening Remarks

  • 9.00 - 9.50: Invited Talk - Salim Roukos
    Talk Title: Overview of IBM's effort on QA and AMR parsing
  • 9.50 - 10.40 : Invited Talk - Mohit Iyyer
    Talk Title: Contextual question answering and generation

  • 10.40 - 11.10 : Posters and Coffee

  • 11.10 - 12.00 : Invited Talk - Lu Wang
    Talk Title: Semantic-Driven Text Summarization and Generation

  • 12.00 - 1.30 : Lunch

  • 1.30 - 2.20: Invited talk - Nianwen Xu
    Talk Title: Developing a Uniform Meaning Representation for Natural Language Processing

  • 2.20 - 3.10 : Invited talk - Niranjan Balasubramanian
    Talk Title: Multi-hop Reasoning in Text-based QA

  • 3.10 - 3.40 : Panel

  • 3.40 - 4.20 : Posters and Coffee

  • 4.20 - 4.30 : Best poster award

Accepted Posters:

  • Pruning a BERT-based QA system
    Scott McCarley

  • Knowledge graph construction via AMR subgraph classification: An evaluation
    Alex Lưu, Yu Xing, Nianwen Xue
  • Information-Theoretic Evaluation of Question Generation for QA
    Arafat Sultan
  • Improving Transition-based Parsing of AMR
    Austin Blodgett, Miguel Ballesteros, Ramon Austudillo, Tahira Naseem, Young-suk Lee

  • Rewarding Smatch: Transition-Based AMR Parsing with Reinforcement Learning
    Tahira Naseem, Abhishek Shah, Hui Wan, Radu Florian, Salim Roukos, Miguel Ballesteros

  • Lingua Franca Named Entity Recognition
    Parul Awasthy

  • Generating Hypothetical Questions
    Pardis Malekzadeh, Mohit Iyyer

  • Generating Question-Answer Hierarchies
    Kalpesh Krishna and Mohit Iyyer
  • Question Answering Model Generalization using Paraphrase Information
    Bhanu Pratap Singh and Preethi Raghavan

  • Advancing Seq2seq Models with Joint Paraphrase Learning
    So Yeon (Tiffany) Min, Preethi Raghavan, Peter Szolovits

  • Learning Unsupervised Representations for Semi-Structured Tables
    Dung Thai and Mohit Iyyer

  • Natural Question Answering
    Lin Pan, Rishav Chakravarti, Anthony Ferritto, Michael Glass, Alfio Gliozzo, Salim Roukos, Radu Florian, Avirup Sil

  • From Boolean Questions to Multi-task learning-base Natural Language Understanding
    Xinyu Hua, Radu Florian and Avirup Sil

  • Towards Universal Semantic Understanding of Natural Languages
    Huaiyu Zhu, Yunyao Li and Siddhartha Brahma

Program Committee:

  1. Ramon Austodillo
  2. Arafat Sultan
  3. Young Suk-Lee
  4. Vittorio Castelli
  5. Rishav Chakravarti
  6. Anthony Ferritto
  7. Lin Pan
  8. Yunyao Li
  9. Huaiyu Zhu
  10. Siddhartha Brahma