• Publications
  • Influence
Colorless green recurrent networks dream hierarchically
tl;dr
We test whether RNNs trained with a generic language modeling objective in four languages can predict long-distance number agreement in various constructions. Expand
  • 182
  • 36
  • Open Access
A distributional similarity approach to the detection of semantic change in the Google Books Ngram corpus.
tl;dr
This paper presents a novel approach for automatic detection of semantic change of words based on distributional similarity models. Expand
  • 129
  • 9
  • Open Access
How to represent a word and predict it, too: improving tied architectures for language modelling
tl;dr
We propose a minimal modification to tied language modelling architectures to address this issue: we add a linear transformation between the hidden layer and the word embedding prediction, partially decouple the two. Expand
  • 8
  • 2
  • Open Access
Diachronic Trends in Word Order Freedom and Dependency Length in Dependency-Annotated Corpora of Latin and Ancient Greek
tl;dr
In this study on Latin and Ancient Greek, two wellknown and well-documented free-order languages, we propose syntactic correlates of word order freedom both in the noun phrase and at the sentence level. Expand
  • 20
  • 1
  • Open Access
Putting words in context: LSTM language models and lexical ambiguity
tl;dr
We investigate how an LSTM language model deals with lexical ambiguity in English, designing a method to probe its hidden representations for lexical and contextual information about words. Expand
  • 10
  • 1
  • Open Access
Towards Incremental Learning of Word Embeddings Using Context Informativeness
tl;dr
In this paper, we investigate the task of learning word embeddings from very sparse data in an incremental, cognitively-plausible way. Expand
  • 3
  • 1
  • Open Access
Structural and lexical factors in adjective placement in complex noun phrases across Romance languages
tl;dr
We show that differences in the prenominal and postnominal placement of adjectives in the noun phrase across five main Romance languages is not only subject to heaviness effects, as previously reported, but also to subtler structural interactions among dependencies that are better explained as effects of the principle of dependency length minimisation. Expand
  • 8
  • 1
  • Open Access
Probing for Referential Information in Language Models
tl;dr
We analyze two state of the art models with LSTM and Transformer architectures, respectively, using probe tasks on a coreference annotated corpus. Expand
  • 3
  • 1
  • Open Access
Dependency length minimisation effects in short spans: a large-scale analysis of adjective placement in complex noun phrases
tl;dr
We show that minimisation does occur in short spans, but also that it is a complex effect: it is not only the length of the dependency that is at stake, and also the effect of the surrounding dependencies. Expand
  • 19
  • Open Access
Multi-lingual Dependency Parsing Evaluation: a Large-scale Analysis of Word Order Properties using Artificial Data
tl;dr
We propose a method to evaluate the effects of word order of a language on dependency parsing performance, while controlling for confounding treebank properties. Expand
  • 15
  • Open Access