Sabine Ploux

Gabriel Bounias, Sabine Ploux

This work examines the semantic geometry underlying NLP models. We compare supervised vector embeddings, such as CamemBERT, with lexical co-occurrence graphs that encode semantic relations more directly. While transformer-based embeddings achieve strong performance, their induced geometries often display unsatisfactory distributions. In contrast, graph-based models reveal a clearer and more human-readable organization of meaning. We have implemented a methodology that allows us to perform a comparative analysis either based on the structure of the graphs or based on the topology of the embeddings induced by these two approaches. The results of the comparison -- applied to the French "Great National Debate" corpus a collection of citizen contributions to the public debate -- show a similar local topology but a very different overall structure and topology. Theses findings suggest complementary perspectives between deep supervised models and graph-based models, considering a new pathway to guide neural architectures toward more stable and interpretable convergence with graphs structures.

Sabine Ploux, Viviane Déprez

In this article we present a multivariate model for determining the different syntactic, semantic, and form (surface-structure) processes underlying the comprehension of simple phrases. This model is applied to EEG signals recorded during a reading task. The results show a hierarchical precedence of the neurolinguistic processes : form, then syntactic and lastly semantic processes. We also found (a) that verbs are at the heart of phrase syntax processing, (b) an interaction between syntactic movement within the phrase, and semantic processes derived from a person-centered reference frame. Eigenvectors of the multivariate model provide electrode-times profiles that separate the distinctive linguistic processes and/or highlight their interaction. The accordance of these findings with different linguistic theories are discussed.

Jean-François Delpech, Sabine Ploux

We show how random vectors and random projection can be implemented in the usual vector space model to construct a Euclidean semantic space from a French synonym dictionary. We evaluate theoretically the resulting noise and show the experimental distribution of the similarities of terms in a neighborhood according to the choice of parameters. We also show that the Schmidt orthogonalization process is applicable and can be used to separate homonyms with distinct semantic meanings. Neighboring terms are easily arranged into semantically significant clusters which are well suited to the generation of realistic lists of synonyms and to such applications as word selection for automatic text generation. This process, applicable to any language, can easily be extended to collocations, is extremely fast and can be updated in real time, whenever new synonyms are proposed.

Rui Wang, Hai Zhao, Sabine Ploux et al.

Most of the existing methods for bilingual word embedding only consider shallow context or simple co-occurrence information. In this paper, we propose a latent bilingual sense unit (Bilingual Sense Clique, BSC), which is derived from a maximum complete sub-graph of pointwise mutual information based graph over bilingual corpus. In this way, we treat source and target words equally and a separated bilingual projection processing that have to be used in most existing works is not necessary any more. Several dimension reduction methods are evaluated to summarize the BSC-word relationship. The proposed method is evaluated on bilingual lexicon translation tasks and empirical results show that bilingual sense embedding methods outperform existing bilingual word embedding methods.