An Amharic Stemmer: Reducing Words to their Citation Forms (2009)
Atelach Alemu Argaw, Lars Asker
Stemming is an important analysis step in a number of areas such as natural language processing (NLP), information retrieval (IR), machine translation(MT) and text classification. In this paper we...
Methods for Amharic part-of-speech tagging (2009)
Gambäck, Björn, Olsson, Fredrik, Argaw, Atelach Alemu, Asker, Lars
The paper describes a set of experiments involving the application of three state-of- the-art part-of-speech taggers to Ethiopian Amharic, using three different tagsets. The taggers showed worse...
Dictionary-based Amharic-French Information Retrieval (2008)
Atelach Alemu Argaw, Lars Asker, Rickard Cöster, Jussi Karlgren, Magnus Sahlgren
We present four approaches to the Amharic- French bilingual track at CLEF 2005. All experiments use a dictionary based approach to translate the Amharic queries into French Bags-of-words, but while...
Applying Machine Learning to Amharic Text Classification (2008)
Lars Asker, Atelach Alemu Argaw, Björn Gambäck
The goal of this work has been to investigate how well a high-level task like text classification can be carried out on Amharic text. We have also investigated the effect that operations like...
PROTEIN NAMES AND HOW TO FIND THEM KRISTOFER FRANZE'N, GUNNAR ERIKSSON, FREDRIK OLSSON (2008)
1 Introduction Terabytes of scientific data are added weekly to the pot of knowledge within the life sciences. More than 2000 completed references are added daily to MEDLINE 1
Automatic Keyword Extraction Using Domain Knowledge (2008)
Hulth, Anette, Karlgren, Jussi, Jonsson, Anna, Boström, Henrik, Asker, Lars
Documents can be assigned keywords by frequency analysis of the terms found in the document text, which arguably is the primary source of knowledge about the document itself. By including a...
PROTEIN NAMES AND HOW TO FIND THEM (2007)
Kristofer Franzn, Gunnar Eriksson, Fredrik Olsson, Lars Asker, Per Lidn, Joakim Cster
A prerequisite for all higher level information extraction tasks is the identi-cation of unknown names in text. Today, when large corpora can consist of billions of words, it is of utmost importance...
Mikael Huss, Henrik Boström, Lars Asker, Joakim Cöster
During the last decade, the area of bioinformatics has produced an overwhelming amount of data, with the recently published draft of the human genome being the most prominent example. This has...
Mikael Huss, Henrik Bostrm, Lars Asker, Joakim Cster
During the last decade, the area of bioinformatics has produced an overwhelming amount of data, with the recently published draft of the human genome being the most prominent example. This has...
Rule Induction for Classification of Gene Expression Array Data (2007)
Per Liden, Lars Asker, Henrik Boström
Gene expression array technology has rapidly become a standard tool for biologists. Its use within areas such as diagnostics, toxicology, and genetics, calls for good methods for finding patterns and...
Dictionary-based Amharic-French Information Retrieval (2006)
Argaw, Atelach Alemu, Asker, Lars, Cöster, Rickard, Karlgren, Jussi, Sahlgren, Magnus
Dictionary-based Amharic-English information retrieval (2005)
Argaw, Atelach Alemu, Asker, Lars, Cöster, Rickard, Karlgren, Jussi
An Empirical Approach to building an Amharic treebank (2003)
Atelach Alemu, Lars Asker, Gunnar Eriksson
30 million people. In spite of this, it suffers severely from lack of computational linguistic resources. Most work on natural language processing of Amharic to date has consisted of limited...
Natural language processing for Amharic: Overview and suggestions for a way forward (2003)
Atelach Alemu, Atelach Alemu, Lars Asker, Lars Asker, Mesfin Getachew, Mesfin Getachew
Nous donnons une vue d’ensemble des efforts qui ont été faits pour développer des systèmes de traitement de langage naturel pour l'Amharique, la langue officielle de l'Ethiopie. Nous...
Protein names and how to find them (2002)
Franzén, Kristofer, Eriksson, Gunnar, Olsson, Fredrik, Asker, Lars, Lidén, Per, Cöster, Joakim
A prerequisite for all higher level information extraction tasks is the identification of unknown names in text. Today, when large corpora can consist of billions of words, it is of utmost importance...
Exploiting Syntax when Detecting Protein Names in Text (2002)
Eriksson, Gunnar, Franzén, Kristofer, Olsson, Fredrik, Asker, Lars, Lidén, Per
This paper presents work on a method to detect names of proteins in running text. Our system - Yapex - uses a combination of lexical and syntactic knowledge, heuristic filters and a local dynamic...
IDAMAP 2002: Intelligent Data Analysis in Medicine and Pharmacology (2002)
Held During, Peter Lucas, Lars Asker, Silvia Miksch
brought together various theoretical and practical approaches to using data-analysis and machinelearning approaches tackling biomedical and health-care problems. The IDAMAP workshop series is devoted...
Exploiting syntax when detecting protein names in text (2002)
Gunnar Eriksson, Kristofer Franzn, Fredrik Olsson, Lars Asker, Per Lidn
This paper presents work on a method to detect names of proteins in running text. Our system Yapex uses a combination of lexical and syntactic knowledge, heuristic lters and a local dynamic...
Using Heuristics, Syntax and a Local Dynamic Dictionary for Protein Name Tagging (2002)
Gunnar Eriksson, Kristofer Franzn, Fredrik Olsson, Lars Asker, Per Lidn
This paper presents work on a method to detect names of proteins in running text. The detection and categorization of named
Notions of correctness when evaluating protein name taggers (2002)
Fredrik Olsson, Gunnar Eriksson, Kristofer Franzn, Lars Asker, Per Lidn
This paper introduces four dierent notions of correctness to be used when measuring the performance of protein name taggers, each of which reects certain characteristics of the tagger under...
Whereas many applications of natural language processing for molecular biology focus on protein name tagging for the purpose high-level information extraction from large corpuses of scientific text,...
Notions of correctness when evaluating protein name taggers (2002)
Olsson, Fredrik, Franzén, Kristofer, Eriksson, Gunnar, Asker, Lars, Lidén, Per
This paper introduces four different notions of correctness to be used when measuring the performance of protein name taggers, each of which reflects certain characteristics of the tagger under...
Merging Classifiers for Improved Information Retrieval (1999)
Anette Hulth, Lars Asker, Jussi Karlgren
resumed to be (in comparison to the other retrieved documents). The ordering is based on the relevance score - a figure produced by the stream, reflecting the document's accuracy as judged by...
. Divide-and-Conquer (DAC) and Separate-and-Conquer (SAC) are two strategies for rule induction that have been used extensively. When searching for rules DAC is maximally conservative w.r.t....
Lars Asker, Asker Hb, Love Ekenberg, Jane Nyakairu, Linda Widmark, Anders Granlund Sida, ...
This report has been commissioned by the Swedish Ministry for Foreign Affairs and Sida. Authors: Lars Asker Mats Danielson Love Ekenberg Jane Nyakairu Linda Widmark ISBN 91-586-7749-6 The authors has...
. Divide-and-Conquer (DAC) and Separate-and-Conquer (SAC) are two strategies for rule induction that have been used extensively. When searching for rules DAC is maximally conservative w.r.t....
Learning to Recognize Volcanoes on Venus (1998)
Michael C. Burl, Lars Asker, Padhraic Smyth, Usama Fayyad, Pietro Perona, Larry Crumpler
. Dramatic improvements in sensor and image acquisition technology have created a demand for automated tools that can aid in the analysis of large image databases. We describe the development of...
Ensembles as a sequence of classifiers (1997)
An ensemble is a classifier created by combining the predictions of multiple component classifiers. We present a new method for combining classifiers into an ensemble based on a simple estimation of...
Ensembles as a Sequence of Classifiers (1997)
An ensemble is a classifier created by combining the predictions of multiple component classifiers. We present a new method for combining classifiers into an ensemble based on a simple estimation of...
The DeNOx System: Machine Learning for Process Control (1995)
Lars Asker And, Lars Asker, Henrik Bostrom
At Hogdalenverket, waste from Stockholm households is burned to produce heat and power for the Stockholm area. Hogdalenverket has been instructed by the Swedish National Environment Protection Board...
Acquiring a Lexicon by Actively Querying the User (1995)
We present a semi-automatic approach to lexical acquisition which utilizes experiences from earlier systems by the authors and others. The hybrid system combines the subsystems in the following way:...
Building the DeNOx System: Experience from a Real-World Application of Machine Learning (1995)
Hogdalenverket is a combined heating and power station located in Stockholm, Sweden. At Hogdalenverket, waste from Stockholm households is burned to produce heat and power for the Stockholm area....
The DeNOx System: Machine Learning for Process Control (1995)
At Hogdalenverket, waste from Stockholm households is burned to produce heat and power for the Stockholm area. Hogdalenverket has been instructed by the Swedish National Environment Protection Board...
Partial explanations as a basis for learning / (1994)
Thesis (doctoral)--Stockholm University, 1994.
Improving Accuracy of Incorrect Domain Theories (1994)
An approach to improve accuracy of incorrect domain theories is presented that learns concept descriptions from positive and negative examples of the concept. The method uses the available domain...
Committees Of Learning Agents (1993)
Lars Asker, Mats Danielson, Love Ekenberg
This paper describes an application dealing with the handling of unexpected events in a combined heat and power plant in a major populated area in Sweden. The plant has a capacity of 135 MW...
EBL : An Approach to Automatic Lexical Acquisition (1992)
Lars Asker, Bj()r N Gam, Back Cllrister, Sam Uelsson
A method for automatic lexical acquisition is out lined. An existing lexicon that, in addition Io ordi-nary]exical entries, contains prototypical cntrips for various non-exclusive paradigms of...
Feature Engineering and Classifier Selection: A Case Study in Venusian Volcano Detection
As machine learning has graduated from toy problems to "real world" applications, users are finding that "real world" problems require them to perform aspects of problem solving...