DeeLIO 2022 will be the Third Workshop on Knowledge Extraction and Integration for Deep Learning Architectures. DeeLIO aims to bring together the knowledge interpretation, extraction and integration lines of research in deep learning, and cover the area in between. DeeLIO will be a hybrid event on May, 27 following ACL 2022.

Workshop Schedule

The workshop starts at 9:20am local time (IST, UTC/GMT +1).

All times in the schedule below are in local time (IST, UTC/GMT +1).

9:20 am Opening remarks (Chair: Eneko Agirre)

9:30 am Keynote 1: Tal Linzen (Chair: Eneko Agirre)

Title: Beyond Probing Classifiers: Deconstructing the Function and Structure of Vector Representations

10:30 am Coffee Break

11:00 am On-site Poster Session (Chair: Eneko Agirre)

Cross-lingual Semantic Role Labelling with the ValPaL Database Knowledge

Chinmay Choudhary and Colm O’Riordan

How Do Transformer-Architecture Models Address Polysemy of Korean Adverbial Postpositions?

Seongmin Mun and Guillaume Desagulier

Trans-KBLSTM: An External Knowledge Enhanced Transformer BiLSTM Model for Tabular Reasoning

Yerram Varun, Aayush Sharma and Vivek Gupta

On Masked Language Models for Contextual Link Prediction

Angus Brayne, Maciej Wiatrak and Dane Corneil

12:30 pm Lunch

14:00 pm Virtual Poster session (Chair: Marianna Apidianaki)

Cross-lingual Semantic Role Labelling with the ValPaL Database Knowledge

Chinmay Choudhary and Colm O’Riordan

How Do Transformer-Architecture Models Address Polysemy of Korean Adverbial Postpositions?

Seongmin Mun and Guillaume Desagulier

Query Generation with External Knowledge for Dense Retrieval

Sukmin Cho, Soyeong Jeong, Wonsuk Yang and Jong C. Park

Uncovering Values: Detecting Latent Moral Content from Natural Language with Explainable and Non-Trained Methods

Luigi Asprino, Luana Bulla, Stefano De Giorgis, Aldo Gangemi, Ludovica Marinucci and Misael Mongiovi

Jointly Identifying and Fixing Inconsistent Readings from Information Extraction Systems

Ankur Padia, Francis Ferraro and Tim Finin

KIQA: Knowledge-Infused Question Answering Model for Financial Table-Text Data

Rungsiman Nararatwong, Natthawut Kertkeidkachorn and Ryutaro Ichise

Trans-KBLSTM: An External Knowledge Enhanced Transformer BiLSTM Model for Tabular Reasoning

Yerram Varun, Aayush Sharma and Vivek Gupta

Fast Few-shot Debugging for NLU Test Suites

Christopher Malon, Kai Li and Erik Kruus

On Masked Language Models for Contextual Link Prediction

Angus Brayne, Maciej Wiatrak and Dane Corneil

What Makes Good In-Context Examples for GPT-3?

Jiachang Liu, Dinghan Shen, Yizhe Zhang, Bill Dolan, Lawrence Carin and Weizhu Chen

15:00 pm Coffee Break

15:30 pm Keynote 2: Yejin Choi (Chair: Jeremy Barnes)
Title: Knowledge is Power: Symbolic Knowledge Distillation and Commonsense Morality

16:30 pm Short Break

16:40 pm Keynote 3: Allyson Ettinger (Chair: Eneko Agirre)

Title: "Understanding" and prediction: Controlled examinations of meaning sensitivity in pre-trained models

17:40 pm Closing remarks (Chair: Eneko Agirre)