Skip to content

Latest commit

 

History

History
64 lines (39 loc) · 3.41 KB

ReadingMaterial.md

File metadata and controls

64 lines (39 loc) · 3.41 KB

Reading Material

We provide some basic reading material here. More detailed pointers can also be found in the slides. Feel free to contact us for more references.

Introduction to Language Modelling

Michael Repplinger , Lisa Beinborn , Willem Zuidema:
Vector-space models of words and sentences

Daniel Jurafsky and James H. Martin: Speech and Language Processing (2020)
Chapter 3: N-gram Language Models
Chapter 9: Deep Learning Architectures for Sequence Processing

Neural Language Models

Matthew Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, Luke Zettlemoyer (2018):
Deep Contextualized Word Representations (ELMO)

Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina Toutanova (2019):
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, Illia Polosukhin (2017):
Attention is all you need (Transformer)

Tom B. Brown et al. (2020):
Language Models are Few-Shot Learners (GPT-3)

Illustrated Blog Posts

The original ELMO and Bert papers are hard to read. Jay Alammar provides very good conceptual introductions:

The illustrated Transformer

The illustrated BERT

Coding Tutorials

A very basic LSTM language model in Keras with Dutch training data

Kristina Gulordava: An exmple LSTM language model in pytorch

Chris McCormick: Introductory tutorials to BERT

Alexander Rush: The annotated Transformer

Our Research on Cognitive Plausibility

Samira Abnar, Lisa Beinborn, Rochelle Choenni, Willem Zuidema (Blackbox NLP 2019):
Blackbox Meets Blackbox: Representational Similarity and Stability Analysis of Neural Language Models and Brains

M. Giulianelli, J. Harding, F. Mohnert, D. Hupkes, W. Zuidema (Best Paper Blackbox NLP 2018):
Under the Hood: Using Diagnostic Classifiers to Investigate and Improve how Language Models Track Agreement Information

Hollenstein & Beinborn (ACL 2021):
Relative Importance in Sentence Processing

N. Hollenstein, F. Pirovano, C. Zhang, L. Jäger, L. Beinborn (NAACL 2021):
Multilingual Language Models Predict Human Reading Behavior

Nora Hollenstein, Maria Barrett, Lisa Beinborn (LiNCR 2020):
Towards best practices for leveraging human language processing signals for natural language processing

Lisa Beinborn, Samira Abnar, Rochelle Choenni (2019):
Robust Evaluation of Language–Brain Encoding Experiments