@inProceedings{ahlberg-etal-2015-case-217988, title = {A case study on supervised classification of Swedish pseudo-coordination}, abstract = {We present a case study on supervised classification of Swedish pseudo-coordination (SPC). The classification is attempted on the type-level with data collected from two data sets: a blog corpus and a fiction corpus. Two small experiments were designed to evaluate the feasability of this task. The first experiment explored a classifier’s ability to discriminate pseudo-coordinations from ordinary verb coordinations, given a small labeled data set created during the experiment. The second experiment evaluated how well the classifier performed at detecting and ranking SPCs in a set of unlabeled verb coordinations, to investigate if it could be used as a semi-automatic discovery procedure to find new SPCs.}, booktitle = {Proceedings of the 20th Nordic Conference of Computational Linguistics, NODALIDA 2015, May 11-13, 2015, Vilnius, Lithuania}, author = {Ahlberg, Malin and Andersson, Peter and Forsberg, Markus and Tahmasebi, Nina}, year = {2015}, publisher = {Linköping University Electronic Press}, address = {Linköpings universitet}, ISBN = {978-91-7519-098-3}, } @inProceedings{johansson-2013-training-173587, title = {Training Parsers on Incompatible Treebanks}, abstract = {We consider the problem of training a statistical parser in the situation when there are multiple treebanks available, and these treebanks are annotated according to different linguistic conventions. To address this problem, we present two simple adaptation methods: the first method is based on the idea of using a shared feature representation when parsing multiple treebanks, and the second method on guided parsing where the output of one parser provides features for a second one. To evaluate and analyze the adaptation methods, we train parsers on treebank pairs in four languages: German, Swedish, Italian, and English. We see significant improvements for all eight treebanks when training on the full training sets. However, the clearest benefits are seen when we consider smaller training sets. Our experiments were carried out with unlabeled dependency parsers, but the methods can easily be generalized to other feature-based parsers.}, booktitle = {Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies}, author = {Johansson, Richard}, year = {2013}, pages = {127--137}, } @inProceedings{borin-etal-2013-mining-188846, title = {Mining semantics for culturomics: towards a knowledge-based approach}, abstract = {The massive amounts of text data made available through the Google Books digitization project have inspired a new field of big-data textual research. Named culturomics, this field has attracted the attention of a growing number of scholars over recent years. However, initial studies based on these data have been criticized for not referring to relevant work in linguistics and language technology. This paper provides some ideas, thoughts and first steps towards a new culturomics initiative, based this time on Swedish data, which pursues a more knowledge-based approach than previous work in this emerging field. The amount of new Swedish text produced daily and older texts being digitized in cultural heritage projects grows at an accelerating rate. These volumes of text being available in digital form have grown far beyond the capacity of human readers, leaving automated semantic processing of the texts as the only realistic option for accessing and using the information contained in them. The aim of our recently initiated research program is to advance the state of the art in language technology resources and methods for semantic processing of Big Swedish text and focus on the theoretical and methodological advancement of the state of the art in extracting and correlating information from large volumes of Swedish text using a combination of knowledge-based and statistical methods.}, booktitle = {2013 ACM International Workshop on Mining Unstructured Big Data Using Natural Language Processing, UnstructureNLP 2013, Held at 22nd ACM International Conference on Information and Knowledge Management, CIKM 2013; San Francisco, CA; United States; 28 October 2013 through 28 October 2013}, author = {Borin, Lars and Dubhashi, Devdatt and Forsberg, Markus and Johansson, Richard and Kokkinakis, Dimitrios and Nugues, Pierre}, year = {2013}, ISBN = {978-1-4503-2415-1}, pages = {3--10}, } @inProceedings{kokkinakis-etal-2014-vocation-209808, title = {Vocation Identification in Swedish Fiction. }, abstract = {This paper presents a system for automatic annotation of vocational signals in 19th century Swedish prose fiction. Besides vocation identification, the system assigns gender (male, female, unknown) to the vocation words. Since gender is a prominent attribute of first names, we apply a named-entity recognizer (NER) that uses first name gazetteers where each name has been pre-assigned gender, which aids gender assignment to vocations with unknown gender if appropriate context is available. We also use a statistical modelling method, conditional random fields (CRF), for learning gender-assigned vocations in combination with the results of the NER and other pattern matching techniques. The purpose of this work is to develop and apply tools to literature as means to expand our understanding of history in the area of literature-based gender studies, e.g. investigate how women enter literature, which functions do they assume and their working patterns. Vocation identification can be used as one such indicator for achieving some these goals.}, booktitle = {Proceedings of the Fifth Swedish Language Technology Conference (SLTC)}, author = {Kokkinakis, Dimitrios and Ighe, Ann and Malm, Mats}, year = {2014}, pages = {3}, } @inProceedings{kokkinakis-etal-2014-semantics-209802, title = {Semantics in Storytelling in Swedish Fiction}, abstract = {In this paper, we aim to define foundations and research questions for future large scale exploration of various types of semantic relationships in literature, namely Swedish prose fiction. More specifically, we are interested to get an in-depth understanding of storytelling in Swedish fiction by analyzing and mining the narrative discourse in a small sample of such data, focusing on interpersonal relationships and answering various questions such as how to recognize and assess gender patterns. Our intention is to apply our findings into a much larger scale in the near future in order to obtain useful insights about the social relations, structures, behavior and everyday life of characters found in literary works, thus enhancing the use of prose fiction as a source for research within the humanities and social sciences. Our work is inspired by the notions of distant reading and macroanalysis, a relatively new and often contested paradigm of literary research. In order to achieve our goal we strive for a combination of natural language processing techniques and simple visualizations that allow the user to rapidly focus on key areas of interest and provide the ability to discover latent semantic patterns and structures. }, booktitle = {Proceedings of the Digital Access to textual Cultural Heritage (DATeCH).}, author = {Kokkinakis, Dimitrios and Malm, Mats and Bergenmar, Jenny and Ighe, Ann}, year = {2014}, ISBN = {978-1-4503-2588-2}, pages = {6}, } @article{johansson-2014-automatic-201874, title = {Automatic Expansion of the Swedish FrameNet Lexicon}, abstract = {We evaluate several lexicon-based and corpus-based methods to automatically induce new lexical units for the Swedish FrameNet, and we see that the best-performing setup uses a combination of both types of methods. A particular challenge for Swedish is the absence of a lexical resource such as WordNet; however, we show that the semantic network SALDO, which is organized according to lexicographical principles quite different from those of WordNet, is very useful for our purposes.}, journal = {Constructions and Frames}, author = {Johansson, Richard}, year = {2014}, volume = {6}, number = {1}, pages = {92--113}, } @article{borin-johansson-2014-kulturomik-192931, title = {Kulturomik: Att spana efter språkliga och kulturella förändringar i digitala textarkiv}, journal = {Historia i en digital värld}, author = {Borin, Lars and Johansson, Richard}, year = {2014}, } @inProceedings{ahlberg-etal-2014-semi-198791, title = {Semi-supervised learning of morphological paradigms and lexicons}, abstract = {We present a semi-supervised approach to the problem of paradigm induction from inflection tables. Our system extracts generalizations from inflection tables, representing the resulting paradigms in an abstract form. The process is intended to be language-independent, and to provide human-readable generalizations of paradigms. The tools we provide can be used by linguists for the rapid creation of lexical resources. We evaluate the system through an inflection table reconstruction task using Wiktionary data for German, Spanish, and Finnish. With no additional corpus information available, the evaluation yields per word form accuracy scores on inflecting unseen base forms in different lan guages ranging from 87.81% (German nouns) to 99.52% (Spanish verbs); with additional unlabeled tex t corpora available for training the scores range from 91.81% (German nouns) to 99.58% (Spanish verbs). We separately evaluate the system in a simulated task of Swedish lexicon creation, and show that on the basis of a small number of inflection tables, the system can accurately collect from a list of noun forms a lexicon with inflection information ranging from 100.0% correct (collect 100 words), to 96.4% correct (collect 1000 words).}, booktitle = {Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, Gothenburg, Sweden 26–30 April 2014 }, author = {Ahlberg, Malin and Forsberg, Markus and Hulden, Mans}, year = {2014}, ISBN = {978-1-937284-78-7}, pages = {569--578}, } @article{tahmasebi-etal-2015-visions-212969, title = {Visions and open challenges for a knowledge-based culturomics}, abstract = {The concept of culturomics was born out of the availability of massive amounts of textual data and the interest to make sense of cultural and language phenomena over time. Thus far however, culturomics has only made use of, and shown the great potential of, statistical methods. In this paper, we present a vision for a knowledge-based culturomics that complements traditional culturomics. We discuss the possibilities and challenges of combining knowledge-based methods with statistical methods and address major challenges that arise due to the nature of the data; diversity of sources, changes in language over time as well as temporal dynamics of information in general. We address all layers needed for knowledge-based culturomics, from natural language processing and relations to summaries and opinions.}, journal = {International Journal on Digital Libraries}, author = {Tahmasebi, Nina and Borin, Lars and Capannini, Gabriele and Dubhashi, Devdatt and Exner, Peter and Forsberg, Markus and Gossen, Gerhard and Johansson, Fredrik and Johansson, Richard and Kågebäck, Mikael and Mogren, Olof and Nugues, Pierre and Risse, Thomas}, year = {2015}, volume = {15}, number = {2-4}, pages = {169--187}, } @inProceedings{kageback-etal-2015-neural-217864, title = {Neural context embeddings for automatic discovery of word senses}, abstract = {Word sense induction (WSI) is the problem of automatically building an inventory of senses for a set of target words using only a text corpus. We introduce a new method for embedding word instances and their context, for use in WSI. The method, Instance-context embedding (ICE), leverages neural word embeddings, and the correlation statistics they capture, to compute high quality embeddings of word contexts. In WSI, these context embeddings are clustered to find the word senses present in the text. ICE is based on a novel method for combining word embeddings using continuous Skip-gram, based on both se- mantic and a temporal aspects of context words. ICE is evaluated both in a new system, and in an extension to a previous system for WSI. In both cases, we surpass previous state-of-the-art, on the WSI task of SemEval-2013, which highlights the generality of ICE. Our proposed system achieves a 33% relative improvement.}, booktitle = {Proceedings of the 1st Workshop on Vector Space Modeling for Natural Language Processing. Denver, United States}, author = {Kågebäck, Mikael and Johansson, Fredrik and Johansson, Richard and Dubhashi, Devdatt}, year = {2015}, pages = {25--32}, } @inProceedings{johansson-nietopina-2015-embedding-217863, title = {Embedding a Semantic Network in a Word Space}, abstract = {We present a framework for using continuous- space vector representations of word meaning to derive new vectors representing the meaning of senses listed in a semantic network. It is a post-processing approach that can be applied to several types of word vector representations. It uses two ideas: first, that vectors for polysemous words can be decomposed into a convex combination of sense vectors; secondly, that the vector for a sense is kept similar to those of its neighbors in the network.This leads to a constrained optimization problem, and we present an approximation for the case when the distance function is the squared Euclidean. We applied this algorithm on a Swedish semantic network, and we evaluate the quality of the resulting sense representations extrinsically by showing that they give large improvements when used in a classifier that creates lexical units for FrameNet frames. }, booktitle = {Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Denver, United States, May 31 – June 5, 2015}, author = {Johansson, Richard and Nieto Piña, Luis}, year = {2015}, ISBN = {978-1-941643-49-5}, pages = {1428--1433}, } @inProceedings{johansson-nietopina-2015-combining-216865, title = {Combining Relational and Distributional Knowledge for Word Sense Disambiguation}, abstract = {We present a new approach to word sense disambiguation derived from recent ideas in distributional semantics. The input to the algorithm is a large unlabeled corpus and a graph describing how senses are related; no sense-annotated corpus is needed. The fundamental idea is to embed meaning representations of senses in the same continuous-valued vector space as the representations of words. In this way, the knowledge encoded in the lexical resource is combined with the infor- mation derived by the distributional methods. Once this step has been carried out, the sense representations can be plugged back into e.g. the skip-gram model, which allows us to compute scores for the different possible senses of a word in a given context. We evaluated the new word sense disambiguation system on two Swedish test sets annotated with senses defined by the SALDO lexical resource. In both evaluations, our system soundly outperformed random and first-sense baselines. Its accuracy was slightly above that of a well- known graph-based system, while being computationally much more efficient,}, booktitle = {Proceedings of the 20th Nordic Conference of Computational Linguistics, May 12-13, Vilnius, Lithuania. Linköping Electronic Conference Proceedings 109, Linköping University Electronic Press..}, author = {Johansson, Richard and Nieto Piña, Luis}, year = {2015}, ISBN = {978-91-7519-098-3}, pages = {69--78}, } @inProceedings{johansson-nietopina-2015-combining-216865, title = {Combining Relational and Distributional Knowledge for Word Sense Disambiguation}, abstract = {We present a new approach to word sense disambiguation derived from recent ideas in distributional semantics. The input to the algorithm is a large unlabeled corpus and a graph describing how senses are related; no sense-annotated corpus is needed. The fundamental idea is to embed meaning representations of senses in the same continuous-valued vector space as the representations of words. In this way, the knowledge encoded in the lexical resource is combined with the infor- mation derived by the distributional methods. Once this step has been carried out, the sense representations can be plugged back into e.g. the skip-gram model, which allows us to compute scores for the different possible senses of a word in a given context. We evaluated the new word sense disambiguation system on two Swedish test sets annotated with senses defined by the SALDO lexical resource. In both evaluations, our system soundly outperformed random and first-sense baselines. Its accuracy was slightly above that of a well- known graph-based system, while being computationally much more efficient,}, booktitle = {Proceedings of the 20th Nordic Conference of Computational Linguistics, May 12-13, Vilnius, Lithuania. Linköping Electronic Conference Proceedings 109, Linköping University Electronic Press..}, author = {Johansson, Richard and Nieto Piña, Luis}, year = {2015}, ISBN = {978-91-7519-098-3}, pages = {69--78}, } @inProceedings{borin-etal-2015-here-217351, title = {Here be dragons? The perils and promises of inter-resource lexical-semantic mapping}, abstract = {Lexical-semantic knowledges sources are a stock item in the language technologist’s toolbox, having proved their practical worth in many and diverse natural language processing (NLP) applications. In linguistics, lexical semantics comes in many flavors, but in the NLP world, wordnets reign more or less supreme. There has been some promising work utilizing Roget-style thesauruses instead, but wider experimentation is hampered by the limited availability of such resources. The work presented here is a first step in the direction of creating a freely available Roget-style lexical resource for modern Swedish. Here, we explore methods for automatic disambiguation of interresource mappings with the longer-term goal of utilizing similar techniques for automatic enrichment of lexical-semantic resources.}, booktitle = {Linköping Electronic Conference Proceedings. Semantic resources and semantic annotation for Natural Language Processing and the Digital Humanities. Workshop at NODALIDA , May 11, 13-18 2015, Vilnius}, author = {Borin, Lars and Nieto Piña, Luis and Johansson, Richard}, year = {2015}, volume = {112}, ISBN = {978-91-7519-049-5}, pages = {1--11}, } @inProceedings{ahlberg-etal-2015-paradigm-217987, title = {Paradigm classification in supervised learning of morphology}, abstract = {Supervised morphological paradigm learning by identifying and aligning the longest common subsequence found in inflection tables has recently been proposed as a simple yet competitive way to induce morphological patterns. We combine this non-probabilistic strategy of inflection table generalization with a discriminative classifier to permit the reconstruction of complete inflection tables of unseen words. Our system learns morphological paradigms from labeled examples of inflection patterns (inflection tables) and then produces inflection tables from unseen lemmas or base forms. We evaluate the approach on datasets covering 11 different languages and show that this approach results in consistently higher accuracies vis-a-vis other methods on the same task, thus indicating that the general method is a viable approach to quickly creating high-accuracy morphological resources.}, booktitle = {Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies}, author = {Ahlberg, Malin and Forsberg, Markus and Huldén, Måns}, year = {2015}, } @inProceedings{nusko-etal-2016-building-238135, title = {Building a Sentiment Lexicon for Swedish}, abstract = {In this paper we will present our ongoing project to build and evaluate a sentiment lexicon for Swedish. Our main resource is SALDO, a lexical resource of modern Swedish developed at Språkbanken, University of Gothenburg. Using a semi-supervised approach, we expand a manually chosen set of six core words using parent-child relations based on the semantic network structure of SALDO. At its current stage the lexicon consists of 175 seeds, 633 children, and 1319 grandchildren.}, booktitle = {Linköping Electronic Conference Proceedings}, author = {Nusko, Bianka and Tahmasebi, Nina and Mogren, Olof}, year = {2016}, volume = {126}, number = {006}, ISBN = {978-91-7685-733-5}, pages = {32----37}, } @inProceedings{johansson-etal-2016-multi-233140, title = {A Multi-domain Corpus of Swedish Word Sense Annotation}, abstract = {We describe the word sense annotation layer in Eukalyptus, a freely available five-domain corpus of contemporary Swedish with several annotation layers. The annotation uses the SALDO lexicon to define the sense inventory, and allows word sense annotation of compound segments and multiword units. We give an overview of the new annotation tool developed for this project, and finally present an analysis of the inter-annotator agreement between two annotators. }, booktitle = {10th edition of the Language Resources and Evaluation Conference, 23-28 May 2016, Portorož (Slovenia)}, author = {Johansson, Richard and Adesam, Yvonne and Bouma, Gerlof and Hedberg, Karin}, year = {2016}, publisher = {European Language Resources Association}, ISBN = {978-2-9517408-9-1}, } @inProceedings{kageback-etal-2014-extractive-210878, title = {Extractive Summarization using Continuous Vector Space Models}, abstract = {Automatic summarization can help users extract the most important pieces of information from the vast amount of text digitized into electronic form everyday. Central to automatic summarization is the notion of similarity between sentences in text. In this paper we propose the use of continuous vector representations for semantically aware representations of sentences as a basis for measuring similarity. We evaluate different compositions for sentence representation on a standard dataset using the ROUGE evaluation measures. Our experiments show that the evaluated methods improve the performance of a state-of-the-art summarization framework and strongly indicate the benefits of continuous word vector representations for automatic summarization.}, booktitle = {Proceedings of the 2nd Workshop on Continuous Vector Space Models and their Compositionality (CVSC) EACL, April 26-30, 2014 Gothenburg, Sweden}, author = {Kågebäck, Mikael and Mogren, Olof and Tahmasebi, Nina and Dubhashi, Devdatt}, year = {2014}, ISBN = {978-1-937284-94-7}, pages = {31--39}, }