メインコンテンツへスキップする
Moodle
  • ホームページ
  • お知らせ
  • 固有のIDでログイン
  • さらに
日本語
Deutsch Englisch Español Français Italiano עברית 日本語
ログイン
ホームページ お知らせ 固有のIDでログイン
  1. コース
  2. 言語情報研究所
  3. 計算言語学
  4. WiSe 2023/24

WiSe 2023/24

Discourse Representations

  • 教官: Katalin Balogh
  • 教官: Tatiana Bladier

Semantic Annotation: Theory and Practice (WiSe 2023/24)

  • 教官: Long Chen
  • 教官: Kilian Evang

Semantic Annotation: Theory and Practice (WiSe 2023/24)

This course introduces several different theories of semantic annotation, including UD, semantic roles, frame semantics, AMR, and parallel meaning bank. The students will learn the theoretical backgrounds and the detailed annotation schemas, and gain some experience in annotating the real-life data, both manually and automatically.

To get BN, one should finish at least 60% of the homework successfully. To get AP, one should also pass a written exam.

コースに移動する

Python I

  • 教官: David Arps
  • 教官: Jan Kels
  • 教官: Yulia Zinova

Formal Languages and Automata Theory

  • 教官: Yulia Zinova

Advanced Constituency Parsing

  • 教官: Laura Kallmeyer
  • 教官: Simon Petitjean

Advanced Constituency Parsing

Aufbauseminar (Laura Kallmeyer)
Module im BA CL integrativ: CL3, CL5, CL6
Dienstag 10.30-12.00, Raum 23.21.U1.72 und Donnerstag 10.30-12.00, Raum 23.21.04.22.

Erste Sitzung: Dienstag 10.10.2023. Letzte Sitzung: 01.02.2024.

Summary

In this seminar, we look into a variety of approaches to parsing that extend standard constituency parsers in different ways:
1. We will discuss approaches that are based on grammar formalisms that are able to generate structures that are beyond context-free grammars. Examples are LCFRS and TAG.
2. Related to this, we will discuss approaches that are able to describe discontinous constituents. These can be grammar-based (LCFRS) or transition based parsers with appropriate transitions such as gap or swap.
3. The course will also cover aspects of incremental, cognitively plausible approaches to constituency parsing.
4. Finally, if there is time, we will also have a look at unsupervised approaches to parsing, i.e., approaches that do not assume labeled training data (in contrast to 1.-3. above).

The course is based on material from the “Parsing beyond CFG” course in 2021/22 and has an extensive overlap with it. This means that student who took that course cannot take the present one in addition.


コースに移動する
あなたは現在ゲストアクセスを利用しています (ログイン)
データ保持概要
ポリシー
Impressum
Powered by Moodle
©Theme Trema