| 13:00–13:30 | Session 1: Regular Papers Q&A (Chair: Yuji Matsumoto) |
Generic Oracles for Structured Prediction
Proof Net Structure for Neural Lambek Categorial Parsing
Findings: Neural Combinatory Constituency Parsing (Pre-Recorded Presentation)
Findings: Rule Augmented Unsupervised Constituency Parsing (Pre-Recorded Presentation)
| 13:30–14:05 | Session 2: Regular Papers Q&A (Chair: Stephan Oepen) |
The Reading Machine: A Versatile Framework for Studying Incremental Parsing Strategies
Semi-Automatic Construction of Text-to-SQL Data for Domain Transfer
Levi Graph AMR Parser using Heterogeneous Attention
Translate, then Parse! A Strong Baseline for Cross-Lingual AMR Parsing
Great Service! Fine-grained Parsing of Implicit Arguments
| 14:05–14:35 | Session 3: Regular Papers Q&A (Chair: Reut Tsarfaty) |
A Falta de Pan, Buenas Son Tortas: The Efficacy of Predicted UPOS Tags for Low Resource UD Parsing
Multilingual Dependency Parsing for Low-Resource African Languages: Case Studies on Bambara, Wolof, and Yoruba
Findings: Climbing the Tower of Treebanks: Improving Low-Resource Dependency Parsing via Hierarchical Source Selection
Findings: Annotations Matter: Leveraging Multi-task Learning to Parse UD and SUD (Pre-Recorded Presentation)
| 14:35–15:05 | Session 4: Regular Papers Q&A (Chair: Djamé Seddah) |
Bidirectional Domain Adaptation Using Weighted Multi-Task Learning
Strength in Numbers: Averaging and Clustering Effects in Mixture of Experts for Graph-Based Dependency Parsing
A Modest Pareto Optimisation Analysis of Dependency Parsers in 2021
Applying Occam’s Razor to Transformer-Based Dependency Parsing: What Works, What Doesn’t, and What is Really Necessary
| 15:05–15:15 | Break |
| 15:15–16:00 | Session 5: Invited Talk (Chair: Kenji Sagae) |
Incorporating Compositionality and Morphology into End-to-End Models
| 16:00–16:45 | Session 6: Shared Task Q&A (Chairs: Gosse Bouma, Djamé Seddah, Dan Zeman) |
From Raw Text to Enhanced Universal Dependencies: The Parsing Shared Task at IWPT 2021
COMBO: A New Module for EUD Parsing
Splitting EUD Graphs into Trees: A Quick and Clatty Approach
Graph Rewriting for Enhanced Universal Dependencies
Biaffine Dependency and Semantic Graph Parsing for EnhancedUniversal Dependencies
Enhanced Universal Dependency Parsing with Automated Concatenation of Embeddings
RobertNLP at the IWPT 2021 Shared Task: Simple Enhanced UD Parsing for 17 Languages
The DCU-EPFL Enhanced Dependency Parser at the IWPT 2021 Shared Task
TGIF: Tree-Graph Integrated-Format Parser for Enhanced UD with Two-Stage Generic- to Individual-Language Finetuning
End-to-end mBERT based Seq2seq Enhanced Dependency Parser with Linguistic Typology knowledge
| 16:45–17:00 | Session 7: SIGPARSE Business Meeting (Chairs: Kenji Sagae, Stephan Oepen) |