Search Results for author: Vivi Nastase

Found 26 papers, 2 papers with code

Are there identifiable structural parts in the sentence embedding whole?

no code implementations24 Jun 2024 Vivi Nastase, Paola Merlo

Sentence embeddings from transformer models encode in a fixed length vector much linguistic information.

Disentangling continuous and discrete linguistic signals in transformer-based sentence embeddings

no code implementations18 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.

Sentence Sentence Embeddings +1

Grammatical information in BERT sentence embeddings as two-dimensional arrays

1 code implementation15 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.

Few-Shot Learning Sentence +1

Semantic Relations and Deep Learning

no code implementations11 Sep 2020 Vivi Nastase, Stan Szpakowicz

The second edition of "Semantic Relations Between Nominals" by Vivi Nastase, Stan Szpakowicz, Preslav Nakov and Diarmuid \'O S\'eaghdha has been published in April 2021 by Morgan & Claypool (www. morganclaypoolpublishers. com/catalog_Orig/product_info. php? products_id=1627).

Relation Classification

Towards Extracting Medical Family History from Natural Language Interactions: A New Dataset and Baselines

no code implementations IJCNLP 2019 Mahmoud Azab, Stephane Dadian, Vivi Nastase, Larry An, Rada Mihalcea

We introduce a new dataset consisting of natural language interactions annotated with medical family histories, obtained during interactions with a genetic counselor and through crowdsourcing, following a questionnaire created by experts in the domain.

Relation Extraction

Anglicized Words and Misspelled Cognates in Native Language Identification

no code implementations WS 2019 Ilia Markov, Vivi Nastase, Carlo Strapparava

In this paper, we present experiments that estimate the impact of specific lexical choices of people writing in a second language (L2).

Native Language Identification

The Role of Emotions in Native Language Identification

no code implementations WS 2018 Ilia Markov, Vivi Nastase, Carlo Strapparava, Grigori Sidorov

We explore the hypothesis that emotion is one of the dimensions of language that surfaces from the native language into a second language.

Deception Detection Native Language Identification +1

Induction of a Large-Scale Knowledge Graph from the Regesta Imperii

no code implementations COLING 2018 Juri Opitz, Leo Born, Vivi Nastase

We induce and visualize a Knowledge Graph over the Regesta Imperii (RI), an important large-scale resource for medieval history research.

Punctuation as Native Language Interference

no code implementations COLING 2018 Ilia Markov, Vivi Nastase, Carlo Strapparava

In this paper, we describe experiments designed to explore and evaluate the impact of punctuation marks on the task of native language identification.

Classification Cross-corpus +3

Word Etymology as Native Language Interference

no code implementations EMNLP 2017 Vivi Nastase, Carlo Strapparava

We present experiments that show the influence of native language on lexical choice when producing text in another language {--} in this particular case English.

Analysis of the Impact of Negative Sampling on Link Prediction in Knowledge Graphs

1 code implementation22 Aug 2017 Bhushan Kotnis, Vivi Nastase

We note a marked difference in the impact of these sampling methods on the two datasets, with the "traditional" corrupting positives method leading to best results on WN18, while embedding based methods benefiting the task on FB15k.

Knowledge Graph Embeddings Knowledge Graphs +1

Learning Knowledge Graph Embeddings with Type Regularizer

no code implementations28 Jun 2017 Bhushan Kotnis, Vivi Nastase

Learning relations based on evidence from knowledge bases relies on processing the available relation instances.

Knowledge Graph Embeddings Vocal Bursts Type Prediction

Coarse-grained Cross-lingual Alignment of Comparable Texts with Topic Models and Encyclopedic Knowledge

no code implementations28 Nov 2014 Vivi Nastase, Angela Fahrni

We present a method for coarse-grained cross-lingual alignment of comparable texts: segments consisting of contiguous paragraphs that discuss the same theme (e. g. history, economy) are aligned based on induced multilingual topics.

Topic Models

Concept-based Selectional Preferences and Distributional Representations from Wikipedia Articles

no code implementations LREC 2012 Alex Judea, Vivi Nastase, Michael Strube

This paper describes the derivation of distributional semantic representations for open class words relative to a concept inventory, and of concepts relative to open class words through grammatical relations extracted from Wikipedia articles.

Semantic Role Labeling Topic Models +1

Cannot find the paper you are looking for? You can Submit a new open access paper.