no code implementations • 18 Dec 2023 • Vivi Nastase, Paola Merlo
We explore whether we can compress transformer-based sentence embeddings into a representation that separates different linguistic signals -- in particular, information relevant to subject-verb agreement and verb alternations.
1 code implementation • 15 Dec 2023 • Vivi Nastase, Paola Merlo
Next, we show that various architectures can detect patterns in these two-dimensional reshaped sentence embeddings and successfully learn a model based on smaller amounts of simpler training data, which performs well on more complex test data.
1 code implementation • 20 Jun 2023 • Paola Merlo
In this paper, we provide the formal specification for the task and the generative process of its datasets.
1 code implementation • 22 May 2022 • Paola Merlo, Aixiu An, Maria A. Rodriguez
Current successes of machine learning architectures are based on computationally expensive algorithms and prohibitively large amounts of data.
no code implementations • CONLL 2020 • Maria A. Rodriguez, Paola Merlo
While they do show asymmetry of similarities, their asymmetries do not map those of human association norms.
no code implementations • NAACL 2021 • Haozhou Wang, James Henderson, Paola Merlo
Generative adversarial networks (GANs) have succeeded in inducing cross-lingual word embeddings -- maps of matching words across languages -- without supervision.
Bilingual Lexicon Induction Cross-Lingual Word Embeddings +1
no code implementations • WS 2020 • Paola Merlo
To process the syntactic structures of a language in ways that are compatible with human expectations, we need computational representations of lexical and syntactic properties that form the basis of human knowledge of words and sentences.
no code implementations • CONLL 2019 • Paola Merlo, Maria Andueza Rodriguez
Research on the bilingual lexicon has uncovered fascinating interactions between the lexicons of the native language and of the second language in bilingual speakers.
no code implementations • WS 2019 • Paola Merlo
We extend the work to sentence embeddings and to new languages.
no code implementations • IJCNLP 2019 • Haozhou Wang, James Henderson, Paola Merlo
Distributed representations of words which map each word to a continuous vector have proven useful in capturing important linguistic information not only in a single language but also across different languages.
no code implementations • CONLL 2018 • Paola Merlo, Francesco Ackermann
We present results that show, under exhaustive and precise conditions, that one kind of word embeddings and the similarity spaces they define do not encode the properties of intervention similarity in long-distance dependencies, and that therefore they fail to represent this core linguistic notion.
no code implementations • CONLL 2017 • Christophe Moor, Paola Merlo, James Henderson, Haozhou Wang
This paper describes the University of Geneva{'}s submission to the CoNLL 2017 shared task Multilingual Parsing from Raw Text to Universal Dependencies (listed as the CLCL (Geneva) entry).
no code implementations • WS 2016 • Haozhou Wang, Paola Merlo
Traditional machine translation evaluation metrics such as BLEU and WER have been widely used, but these metrics have poor correlations with human judgements because they badly represent word similarity and impose strict identity matching.
no code implementations • TACL 2016 • Kristina Gulordava, Paola Merlo
We propose a method to evaluate the effects of word order of a language on dependency parsing performance, while controlling for confounding treebank properties.