Hi! I’m a computational linguist = a researcher who answers (intriguing and fascinating) questions about language using computational models and tools.

I’m currently a postdoc on Gemma Boleda’s ERC project at the University Pompeu Fabra, Barcelona. The goal of the project is to develop and analyse neural network models for semantic reference. I’m particularly interested in modeling reference and word learning in child language acquisition.

Before that, I obtained my PhD at the University of Geneva working with Paola Merlo. You can download my thesis “Word order variation and dependency length minimisation : a cross-linguistic computational approach” here.

Publications

Computational Quantitative Syntax: The Case of Universal 18.

Accepted for the upcoming volume for LSRL 47

Kristina Gulordava, Paola Merlo

How to represent a word and predict it, too: Improving tied architectures for language modelling.

EMNLP 2018 (short) pdf / bib

Kristina Gulordava, Laura Aina, Gemma Boleda

Colorless Green Recurrent Networks Dream Hierarchically.

NAACL 2018 pdf / bib / code / slides

Kristina Gulordava, Piotr Bojanowski, Edouard Grave, Tal Linzen, Marco Baroni

Multi-lingual Dependency Parsing Evaluation: a Large-scale Analysis of Word Order Properties using Artificial Data.

TACL 2016 pdf / bib

Kristina Gulordava, Paola Merlo

Discontinuous Verb Phrases in Parsing and Machine Translation of English and German.

LREC 2016 pdf / bib

Sharid Loáiciga, Kristina Gulordava

Dependency length minimisation effects in short spans: a large-scale analysis of adjective placement in complex noun phrases.

ACL 2015 (short) pdf / bib

Kristina Gulordava, Paola Merlo, Benoit Crabbé

Structural and lexical factors in adjective placement in complex noun phrases across Romance languages.

CONLL 2015 pdf / bib

Kristina Gulordava, Paola Merlo

Diachronic Trends in Word Order Freedom and Dependency Length in Dependency-Annotated Corpora of Latin and Ancient Greek.

International Conference on Dependency Linguistics 2015 pdf / bib

Kristina Gulordava, Paola Merlo

A distributional similarity approach to the detection of semantic change in the Google Books Ngram corpus.

Proceedings of the GEMS 2011 Workshop pdf / bib

Kristina Gulordava, Marco Baroni

Abstracts & Presentations

Do RNN language models induce referential information? An analysis of article prediction.

Learning Language in Humans and Machines 2018 poster

Kristina Gulordava, Gemma Boleda

Incremental Generative Model of Sentence Linearization and Word Order Variation.

CMCL Workshop at EACL 2017 poster

Kristina Gulordava, Frank Keller

Lexico-semantic factors in the variation of adjective placement in complex noun phrases in Italian.

DSALT Workshop 2016 abstract

Kristina Gulordava

A large-scale corpus-based study of NP-internal word order variation for several languages.

8th Days of Swiss Linguistics 2014 abstract

Kristina Gulordava, Paola Merlo