Search Results - "Ushio, Asahi"

Projection-Based Regularized Dual Averaging for Stochastic Optimization by Ushio, Asahi, Yukawa, Masahiro

“…We propose a novel stochastic-optimization framework based on the regularized dual averaging (RDA) method. The proposed approach differs from the previous…”
Get full text

Volatility forecasts using stochastic volatility models with nonlinear leverage effects by McAlinn, Kenichiro, Ushio, Asahi, Nakatsuma, Teruo

“…The leverage effect—the correlation between an asset's return and its volatility—has played a key role in forecasting and understanding volatility and risk…”
Get full text

Projection-based dual averaging for stochastic sparse optimization by Ushio, Asahi, Yukawa, Masahiro

“…We present a variant of the regularized dual averaging (RDA) algorithm for stochastic sparse optimization. Our approach differs from the previous studies of…”
Get full text

T-NER: An All-Round Python Library for Transformer-based Named Entity Recognition by Ushio, Asahi, Camacho-Collados, Jose

“…Language model (LM) pretraining has led to consistent improvements in many NLP downstream tasks, including named entity recognition (NER). In this paper, we…”
Get full text

Distilling Relation Embeddings from Pre-trained Language Models by Ushio, Asahi, Camacho-Collados, Jose, Schockaert, Steven

“…Pre-trained language models have been found to capture a surprisingly rich amount of lexical knowledge, ranging from commonsense properties of everyday…”
Get full text

Back to the Basics: A Quantitative Analysis of Statistical and Graph-Based Term Weighting Schemes for Keyword Extraction by Ushio, Asahi, Liberatore, Federico, Camacho-Collados, Jose

“…Term weighting schemes are widely used in Natural Language Processing and Information Retrieval. In particular, term weighting is the basis for keyword…”
Get full text

A Systematic Analysis on the Temporal Generalization of Language Models in Social Media by Ushio, Asahi, Camacho-Collados, Jose

“…In machine learning, temporal shifts occur when there are differences between training and test splits in terms of time. For streaming data such as news or…”
Get full text

RelBERT: Embedding Relations with Language Models by Ushio, Asahi, Camacho-Collados, Jose, Schockaert, Steven

“…Many applications need access to background knowledge about how different concepts and entities are related. Although Knowledge Graphs (KG) and Large Language…”
Get full text

An Efficient Multilingual Language Model Compression through Vocabulary Trimming by Ushio, Asahi, Zhou, Yi, Camacho-Collados, Jose

“…Multilingual language model (LM) have become a powerful tool in NLP especially for non-English languages. Nevertheless, model parameters of multilingual LMs…”
Get full text

A RelEntLess Benchmark for Modelling Graded Relations between Named Entities by Ushio, Asahi, Collados, Jose Camacho, Schockaert, Steven

“…Relations such as "is influenced by", "is known for" or "is a competitor of" are inherently graded: we can rank entity pairs based on how well they satisfy…”
Get full text

Multilingual Topic Classification in X: Dataset and Analysis by Antypas, Dimosthenis, Ushio, Asahi, Barbieri, Francesco, Camacho-Collados, Jose

“…In the dynamic realm of social media, diverse topics are discussed daily, transcending linguistic boundaries. However, the complexities of understanding and…”
Get full text

A Practical Toolkit for Multilingual Question and Answer Generation by Ushio, Asahi, Alva-Manchego, Fernando, Camacho-Collados, Jose

“…Generating questions along with associated answers from a text has applications in several domains, such as creating reading comprehension tests for students,…”
Get full text

An Empirical Comparison of LM-based Question and Answer Generation Methods by Ushio, Asahi, Alva-Manchego, Fernando, Camacho-Collados, Jose

“…Question and answer generation (QAG) consists of generating a set of question-answer pairs given a context (e.g. a paragraph). This task has a variety of…”
Get full text

Generative Language Models for Paragraph-Level Question Generation by Ushio, Asahi, Alva-Manchego, Fernando, Camacho-Collados, Jose

“…Powerful generative models have led to recent progress in question generation (QG). However, it is difficult to measure advances in QG research since there are…”
Get full text

BERT is to NLP what AlexNet is to CV: Can Pre-Trained Language Models Identify Analogies? by Ushio, Asahi, Espinosa-Anke, Luis, Schockaert, Steven, Camacho-Collados, Jose

“…Analogies play a central role in human commonsense reasoning. The ability to recognize analogies such as "eye is to seeing what ear is to hearing", sometimes…”
Get full text

SuperTweetEval: A Challenging, Unified and Heterogeneous Benchmark for Social Media NLP Research by Antypas, Dimosthenis, Ushio, Asahi, Barbieri, Francesco, Neves, Leonardo, Rezaee, Kiamehr, Espinosa-Anke, Luis, Pei, Jiaxin, Camacho-Collados, Jose

“…Despite its relevance, the maturity of NLP for social media pales in comparison with general-purpose models, metrics and benchmarks. This fragmented landscape…”
Get full text

Named Entity Recognition in Twitter: A Dataset and Analysis on Short-Term Temporal Shifts by Ushio, Asahi, Neves, Leonardo, Silva, Vitor, Barbieri, Francesco, Camacho-Collados, Jose

“…Recent progress in language model pre-training has led to important improvements in Named Entity Recognition (NER). Nonetheless, this progress has been mainly…”
Get full text

Twitter Topic Classification by Antypas, Dimosthenis, Ushio, Asahi, Camacho-Collados, Jose, Neves, Leonardo, Silva, Vítor, Barbieri, Francesco

“…Social media platforms host discussions about a wide variety of topics that arise everyday. Making sense of all the content and organising it into categories…”
Get full text

Latent Space Cartography: Generalised Metric-Inspired Measures and Measure-Based Transformations for Generative Models by Frenzel, Max F, Teleaga, Bogdan, Ushio, Asahi

“…Deep generative models are universal tools for learning data distributions on high dimensional data spaces via a mapping to lower dimensional latent spaces. We…”
Get full text

Guiding Generative Language Models for Data Augmentation in Few-Shot Text Classification by Edwards, Aleksandra, Ushio, Asahi, Camacho-Collados, Jose, de Ribaupierre, Hélène, Preece, Alun

“…Data augmentation techniques are widely used for enhancing the performance of machine learning models by tackling class imbalance issues and data sparsity…”
Get full text