Meaning Representations: Recent Advances in Parsing and Generation
Module Description
| Course | Module Abbreviation | Credit Points |
|---|---|---|
| BA-2010 | AS-FL | 8 LP |
| BA-2010 | AS-CL | 8 LP |
| BA-2010[100%|75%] | CS-CL | 6 LP |
| BA-2010[50%] | BS-CL | 6 LP |
| Master | SS-CL, SS-TAC, SS-FAL | 8 LP |
| Lecturer | Juri Opitz |
| Module Type | |
| Language | Englisch |
| First Session | 09.11.2020 |
| Time and Place | Monday, 09:15-10:45, Online |
| End of Commitment Period | tbd. |
Prerequisite for Participation
Assessment
Content
After an overview over different kinds of meaning representations for sentences and discourse, we will discuss recent approaches to generating such representations from text (parsing) and generating text from these representations (generation).
Module Overview
Agenda
| Datum | Sitzung | Materialien |
| 9.11.2020 | Welcome (JO) | Course overview |
| 16.11.2020 | Introduction to Meaning Representations (LG) | slides |
| 23.11.2020 | (Evaluation) Metrics (ML) | slides |
| 30.11.2020 | Neural Seq2Seq (Sutskever et al. 2013 or Vaswani et al. 2017: NM) | slides |
| 7.12.2020 | Neural Seq2Seq for AMR parsing and generation (Konstas et al. 2017: CR) and (van Noord and Bos 2017: SU) | slides (CR), slides (SU) |
| 14.12.2020 | AMR parsing with MT pretraining (Xu et al. 2020: NM) | slides |
| 11.1.2021 | Graph encoders for text2amr (Song et al. 2018: KH) | slides |
| 18.1.2021 | AMR parsing with graph prediction (Cai and Lam 2020: PM) | slides |
| 25.1.2021 | Transition-based AMR parsing (Wang et al. 2015: JG) and (Lindemann et al. 2020: SL) | |
| 1.2.2021 | Cross-lingual AMR parsing (Damonte et al. 2017: BI) and (Blloshmi et al. 2020: YG) | |
| 8.2.2021 | DRS Parsing (Liu et al. 2018: LG) | |
| 15.2.2021 | Paper of your choice (Zhong et al. 2020 - "Grounded Adaptation for Zero-shot Executable Semantic Parsing": SL) | |
| 22.2.2021 | Wrap-up, project discussion |
Literatur
