Search Results - "Sahlgren, Magnus"

The Singleton Fallacy: Why Current Critiques of Language Models Miss the Point by Sahlgren, Magnus, Carlsson, Fredrik

“…This paper discusses the current critique against neural network-based Natural Language Understanding solutions known as language models . We argue that much…”
Get full text

GDTM: Graph-based Dynamic Topic Models by Ghoorchian, Kambiz, Sahlgren, Magnus

“…Dynamic Topic Modeling (DTM) is the ultimate solution for extracting topics from short texts generated in Online Social Networks (OSNs) like Twitter. It…”
Get full text

Encoding Sequential Information in Semantic Space Models: Comparing Holographic Reduced Representation and Random Permutation by Jones, Michael N., Kanerva, Pentti, Sahlgren, Magnus, Recchia, Gabriel

“…Circular convolution and random permutation have each been proposed as neurally plausible binding operators capable of encoding sequential information in…”
Get full text

A Distributional Semantic Online Lexicon for Linguistic Explorations of Societies by Dahlberg, Stefan, Axelsson, Sofia, Gyllensten, Amaru Cuba, Sahlgren, Magnus, Ekgren, Ariel, Holmberg, Sören, Schwarz, Jonas Andersson

“…Linguistic Explorations of Societies (LES) is an interdisciplinary research project with scholars from the fields of political science, computer science, and…”
Get full text

Effect of self-managed lifestyle treatment on glycemic control in patients with type 2 diabetes by Dwibedi, Chinmay, Mellergård, Emelia, Gyllensten, Amaru Cuba, Nilsson, Kristoffer, Axelsson, Annika S., Bäckman, Malin, Sahlgren, Magnus, Friend, Stephen H., Persson, Sofie, Franzén, Stefan, Abrahamsson, Birgitta, Carlsson, Katarina Steen, Rosengren, Anders H.

“…The lack of effective, scalable solutions for lifestyle treatment is a global clinical problem, causing severe morbidity and mortality. We developed a method…”
Get full text

A comparative evaluation and analysis of three generations of Distributional Semantic Models by Lenci, Alessandro, Sahlgren, Magnus, Jeuniaux, Patrick, Cuba Gyllensten, Amaru, Miliani, Martina

“…Distributional semantics has deeply changed in the last decades. First, predict models stole the thunder from traditional count ones, and more recently both of…”
Get full text

Random indexing of multidimensional data by Sandin, Fredrik, Emruli, Blerim, Sahlgren, Magnus

“…Random indexing (RI) is a lightweight dimension reduction method, which is used, for example, to approximate vector semantic relationships in online natural…”
Get full text

Random indexing of multi-dimensional data by Sandin, Fredrik, Emruli, Blerim, Sahlgren, Magnus

“…Random indexing (RI) is a lightweight dimension reduction method, which is used for example to approximate vector-semantic relationships in online natural…”
Get full text

Visual analysis of online social media to open up the investigation of stance phenomena by Kucher, Kostiantyn, Schamp-Bjerede, Teri, Kerren, Andreas, Paradis, Carita, Sahlgren, Magnus

“…Online social media are a perfect text source for stance analysis. Stance in human communication is concerned with speaker attitudes, beliefs, feelings and…”
Get full text

Visual Analysis of Relationships between Heterogeneous Networks and Texts: An Application on the IEEE VIS Publication Dataset by Zimmer, Björn, Sahlgren, Magnus, Kerren, Andreas

“…The visual exploration of large and complex network structures remains a challenge for many application fields. Moreover, a growing number of real-world…”
Get full text

Learning machines in Internet-delivered psychological treatment by Boman, Magnus, Ben Abdesslem, Fehmi, Forsell, Erik, Gillblad, Daniel, Görnerup, Olof, Isacsson, Nils, Sahlgren, Magnus, Kaldo, Viktor

“…A learning machine, in the form of a gating network that governs a finite number of different machine learning methods, is described at the conceptual level…”
Get full text

We Need to Talk About Data: The Importance of Data Readiness in Natural Language Processing by Olsson, Fredrik, Sahlgren, Magnus

“…In this paper, we identify the state of data as being an important reason for failure in applied Natural Language Processing (NLP) projects. We argue that…”
Get full text

The Singleton Fallacy: Why Current Critiques of Language Models Miss the Point by Sahlgren, Magnus, Carlsson, Fredrik

“…This paper discusses the current critique against neural network-based Natural Language Understanding (NLU) solutions known as language models. We argue that…”
Get full text

Why Not Simply Translate? A First Swedish Evaluation Benchmark for Semantic Similarity by Isbister, Tim, Sahlgren, Magnus

“…This paper presents the first Swedish evaluation benchmark for textual semantic similarity. The benchmark is compiled by simply running the English STS-B…”
Get full text

Data Readiness for Natural Language Processing by Olsson, Fredrik, Sahlgren, Magnus

“…This document concerns data readiness in the context of machine learning and Natural Language Processing. It describes how an organization may proceed to…”
Get full text

SWEb: A Large Web Dataset for the Scandinavian Languages by Norlund, Tobias, Isbister, Tim, Gyllensten, Amaru Cuba, Santos, Paul Dos, Petrelli, Danila, Ekgren, Ariel, Sahlgren, Magnus

“…This paper presents the hitherto largest pretraining dataset for the Scandinavian languages: the Scandinavian WEb (SWEb), comprising over one trillion tokens…”
Get full text

Should we Stop Training More Monolingual Models, and Simply Use Machine Translation Instead? by Isbister, Tim, Carlsson, Fredrik, Sahlgren, Magnus

“…Most work in NLP makes the assumption that it is desirable to develop solutions in the native language in question. There is consequently a strong trend…”
Get full text

Measuring Issue Ownership using Word Embeddings by Gyllensten, Amaru Cuba, Sahlgren, Magnus

“…Sentiment and topic analysis are common methods used for social media monitoring. Essentially, these methods answers questions such as, "what is being talked…”
Get full text

Cross-lingual Transfer of Monolingual Models by Gogoulou, Evangelia, Ekgren, Ariel, Isbister, Tim, Sahlgren, Magnus

“…Recent studies in zero-shot cross-lingual learning using multilingual models have falsified the previous hypothesis that shared vocabulary and joint…”
Get full text

The Effects of Data Size and Frequency Range on Distributional Semantic Models by Sahlgren, Magnus, Lenci, Alessandro

“…This paper investigates the effects of data size and frequency range on distributional semantic models. We compare the performance of a number of…”
Get full text