Papers by Matej Martinc

7 papers
Leveraging Contextual Embeddings for Detecting Diachronic Semantic Shift (2020.lrec-1)

Copied to clipboard

Challenge: Existing methods for word embeddings have been used to model semantic relations with word embeds.
Approach: They propose a method that leverages contextual embeddings for diachronic semantic shift detection by generating time specific word representations from BERT embedds.
Outcome: The proposed method performs comparable to the current state-of-the-art without time consuming domain adaptation on large corpora.
Embeddings models for Buddhist Sanskrit (2022.lrec-1)

Copied to clipboard

Challenge: Despite extensive scholarly endeavors, much uncertainty still surrounds this body of literature, especially regarding matters of chronology, authorship, compositional history.
Approach: They propose a corpus of Buddhist texts, a general corpus and word similarity and word analogy datasets for embeddings models.
Outcome: The proposed models perform better on semantic similarity and word analogy tasks than on contextual models.
Reusable workflows for gender prediction (L18-1)

Copied to clipboard

Challenge: Existing systems for author profiling (AP) modeling require extensive feature engineering and testing.
Approach: They propose to implement a system for author profiling (AP) modeling that reduces the complexity and time of building a sophisticated model for a number of different AP tasks.
Outcome: The proposed model achieves comparable results to state of the art models for cross-genre gender prediction, but lags when genre of test set is different from genre of train set.
SEKE: Specialised Experts for Keyword Extraction (2025.findings-emnlp)

Copied to clipboard

Challenge: Keyword extraction involves identifying the most descriptive words in a document . supervised keyword extraction is based on the mixture of experts (MoE) technique .
Approach: They propose a supervised keyword extraction approach based on the mixture of experts technique . they use a learnable routing sub-network to direct information to specialised experts .
Outcome: The proposed approach is based on the mixture of experts (MoE) technique . experts attend to each token and integrate it with a bidirectional long-term memory network .
Out of Thin Air: Is Zero-Shot Cross-Lingual Keyword Detection Better Than Unsupervised? (2022.lrec-1)

Copied to clipboard

Challenge: Keyword extraction is the task of retrieving words that are essential to the content of a document.
Approach: They propose to use pretrained multilingual language models for zero-shot cross-lingual keyword extraction on low-resource languages with limited or no available labeled training data.
Outcome: The proposed models outperform state-of-the-art unsupervised methods on low-resource languages with limited or no training data.
Scalable and Interpretable Semantic Change Detection (2021.naacl-main)

Copied to clipboard

Challenge: Several cluster-based methods for word usage change detection are unscalable in terms of memory consumption and computation time.
Approach: They propose a scalable method for word usage-change detection that uses contextual embeddings to aggregate word usages into clusters.
Outcome: The proposed method offers high performance and interpretability while being unscalable.
Effectiveness of Data Augmentation and Pretraining for Improving Neural Headline Generation in Low-Resource Settings (2022.lrec-1)

Copied to clipboard

Challenge: Neural approaches for natural language generation (NLG) have mushroomed due to large textual resources.
Approach: They propose to use a pretrained multilingual encoder-decoder model and a combination of two pretrained language models to train a model in a low-resource setting.
Outcome: The proposed model outperforms the previous model on English and on a small subset of the same data.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations