Zobrazeno 1 - 10
of 41
pro vyhledávání: '"Rönnqvist, Samuel"'
Autor:
Rönnqvist, Samuel, Myntti, Amanda, Kyröläinen, Aki-Juhani, Pyysalo, Sampo, Laippala, Veronika, Ginter, Filip
In recent years, several methods have been proposed for explaining individual predictions of deep learning models, yet there has been little study of how to aggregate these predictions to explain how such models view classes as a whole in text classi
Externí odkaz:
http://arxiv.org/abs/2108.13653
Autor:
Repo, Liina, Skantsi, Valtteri, Rönnqvist, Samuel, Hellström, Saara, Oinonen, Miika, Salmela, Anna, Biber, Douglas, Egbert, Jesse, Pyysalo, Sampo, Laippala, Veronika
We explore cross-lingual transfer of register classification for web documents. Registers, that is, text varieties such as blogs or news are one of the primary predictors of linguistic variation and thus affect the automatic processing of language. W
Externí odkaz:
http://arxiv.org/abs/2102.07396
In this paper, we present the first publicly available part-of-speech and morphologically tagged corpus for the Albanian language, as well as a neural morphological tagger and lemmatizer trained on it. There is currently a lack of available NLP resou
Externí odkaz:
http://arxiv.org/abs/1912.00991
Publikováno v:
In proceedings of the First NLPL Workshop on Deep Learning for Natural Language Processing (2019)
The multilingual BERT model is trained on 104 languages and meant to serve as a universal language model and tool for encoding sentences. We explore how well the model performs on several languages across several tasks: a diagnostic classification pr
Externí odkaz:
http://arxiv.org/abs/1910.03806
News articles such as sports game reports are often thought to closely follow the underlying game statistics, but in practice they contain a notable amount of background knowledge, interpretation, insight into the game, and quotes that are not presen
Externí odkaz:
http://arxiv.org/abs/1910.01863
We introduce an attention-based Bi-LSTM for Chinese implicit discourse relations and demonstrate that modeling argument pairs as a joint sequence can outperform word order-agnostic approaches. Our model benefits from a partial sampling scheme and is
Externí odkaz:
http://arxiv.org/abs/1704.08092
Autor:
Rönnqvist, Samuel, Sarlin, Peter
Publikováno v:
Neurocomputing, 264, 2017
While many models are purposed for detecting the occurrence of significant events in financial systems, the task of providing qualitative detail on the developments is not usually as well automated. We present a deep learning approach for detecting r
Externí odkaz:
http://arxiv.org/abs/1603.05670
Autor:
Rönnqvist, Samuel, Sarlin, Peter
News is a pertinent source of information on financial risks and stress factors, which nevertheless is challenging to harness due to the sparse and unstructured nature of natural text. We propose an approach based on distributional semantics and deep
Externí odkaz:
http://arxiv.org/abs/1507.07870
Autor:
Rönnqvist, Samuel
As we continue to collect and store textual data in a multitude of domains, we are regularly confronted with material whose largely unknown thematic structure we want to uncover. With unsupervised, exploratory analysis, no prior knowledge about the c
Externí odkaz:
http://arxiv.org/abs/1507.04798
Probabilistic topic modeling is a popular and powerful family of tools for uncovering thematic structure in large sets of unstructured text documents. While much attention has been directed towards the modeling algorithms and their various extensions
Externí odkaz:
http://arxiv.org/abs/1409.5623