Miloslav Konopík

SWSNL: Semantic Web Search Using Natural Language

As modern search engines are approaching the ability to deal with queries expressed in natural language, full support of natural language interfaces seems to be the next step in the development of future systems. The vision is that of users being able to tell a computer what they would like to find, using any number of sentences and as many details as requested. In this article we describe our effort to move towards this future using currently available technology. The Semantic Web framework was chosen as the best means to achieve this goal. We present our approach to building a complete Semantic Web Search Using Natural Language (SWSNL) system. We cover the complete process which includes preprocessing, semantic analysis, semantic interpretation, and executing a SPARQL query to retrieve the results. We perform an end-to-end evaluation on a domain dealing with accommodation options. The domain data come from an existing accommodation portal and we use a corpus of queries obtained by a Facebook campaign. In our paper we work with written texts in the Czech language. In addition to that, the Natural Language Understanding (NLU) module is evaluated on another domain (public transportation) and language (English). We expect that our findings will be valuable for the research community as they are strongly related to issues found in real-world scenarios. We struggled with inconsistencies in the actual Web data, with the performance of the Semantic Web engines on a decently sized knowledge base, and others.

CRF-Based Czech Named Entity Recognizer and Consolidation of Czech NER Research

In this paper, we present our effort to consolidate and push further the named entity recognition (NER) research for the Czech language. The research in Czech is based upon a non-standard basis. Some systems are constructed to provide hierarchical outputs whereas the rests give flat entities. Direct comparison among these system is therefore impossible. Our first goal is to tackle this issue. We build our own NER system based upon conditional random fields (CRF) model. It is constructed to output either flat or hierarchical named entities thus enabling an evaluation with all the known systems for Czech language. We show a 3.5 – 11% absolute performance increase when compared to previously published results. As a last step we put our system in the context of the research for other languages. We show results for English, Spanish and Dutch corpora. We can conclude that our system provides solid results when compared to the foreign state of the art.

Latent semantics in Named Entity Recognition

Language independent Named Entity Recognition system.Novel features based on latent semantics.Experiments on multiple languages - English, Spanish, Dutch, Czech.State-of-the-art results. In this paper, we propose new features for Named Entity Recognition (NER) based on latent semantics. Furthermore, we explore the effect of unsupervised morphological information on these methods and on the NER system in general. The newly created NER system is fully language-independent thanks to the unsupervised nature of the proposed features. We evaluate the system on English, Spanish, Dutch and Czech corpora and study the difference between weakly and highly inflectional languages. Our system achieves the same or even better results than state-of-the-art language dependent systems. The proposed features proved to be very useful and are the main reason of our promising results.

HPS: High precision stemmer

Abstract Research into unsupervised ways of stemming has resulted, in the past few years, in the development of methods that are reliable and perform well. Our approach further shifts the boundaries of the state of the art by providing more accurate stemming results. The idea of the approach consists in building a stemmer in two stages. In the first stage, a stemming algorithm based upon clustering, which exploits the lexical and semantic information of words, is used to prepare large-scale training data for the second-stage algorithm. The second-stage algorithm uses a maximum entropy classifier. The stemming-specific features help the classifier decide when and how to stem a particular word. In our research, we have pursued the goal of creating a multi-purpose stemming tool. Its design opens up possibilities of solving non-traditional tasks such as approximating lemmas or improving language modeling. However, we still aim at very good results in the traditional task of information retrieval. The conducted tests reveal exceptional performance in all the above mentioned tasks. Our stemming method is compared with three state-of-the-art statistical algorithms and one rule-based algorithm. We used corpora in the Czech, Slovak, Polish, Hungarian, Spanish and English languages. In the tests, our algorithm excels in stemming previously unseen words (the words that are not present in the training set). Moreover, it was discovered that our approach demands very little text data for training when compared with competing unsupervised algorithms.

Semantic spaces for improving language modeling

Language models are crucial for many tasks in NLP (Natural Language Processing) and n-grams are the best way to build them. Huge effort is being invested in improving n-gram language models. By introducing external information (morphology, syntax, partitioning into documents, etc.) into the models a significant improvement can be achieved. The models can however be improved with no external information and smoothing is an excellent example of such an improvement. In this article we show another way of improving the models that also requires no external information. We examine patterns that can be found in large corpora by building semantic spaces (HAL, COALS, BEAGLE and others described in this article). These semantic spaces have never been tested in language modeling before. Our method uses semantic spaces and clustering to build classes for a class-based language model. The class-based model is then coupled with a standard n-gram model to create a very effective language model. Our experiments show that our models reduce the perplexity and improve the accuracy of n-gram language models with no external information added. Training of our models is fully unsupervised. Our models are very effective for inflectional languages, which are particularly hard to model. We show results for five different semantic spaces with different settings and different number of classes. The perplexity tests are accompanied with machine translation tests that prove the ability of proposed models to improve performance of a real-world application.

Active Tags for Semantic Analysis

We propose a new method for semantic analysis. The method is based on handwritten context-free grammars enriched with semantic tags. Associating the rules of a context-free grammar with semantic tags is beneficial; however, after parsing the tags are spread across the parse tree and it is usually hard to extract the complete semantic information from it. Thus, we developed an easy-to-use and yet very powerful mechanism for tag propagation. The mechanism allows the semantic information to be easily extracted from the parse tree. The propagation mechanism is based on an idea to add propagation instruction to the semantic tags. The tags with such instructions are called active tagsin this article. Using the proposed method we developed a useful tool for semantic parsing that we offer for free on our internet pages.

Maximum entropy named entity recognition for Czech language

Named Entity Recognition (NER) is an important preprocessing tool for many Natural Language Processing tasks like Information Retrieval, Question Answering or Machine Translation. This paper is focused on NER for Czech language. The proposed NER is based on knowledge and experiences acquired on other languages and adapted for Czech. Our recognizer outperforms the previously introduced recognizers for Czech. The article is also focused on the use of semantic spaces for NER. Although no significant improvement was yet achieved in this way, we believe that the research is worth of sharing.

Morphological based language models for inflectional languages

This paper shows a method to improve the language modeling for inflectional languages such as the Czech and Slovak language. Methods are based upon the principle of class-based language models, where word classes are derived from morphological information. Our experiments show that the linear interpolation with the class-based language models outperforms the stand-alone word N-gram language model about 10–30%.

Named Entity Recognition for Highly Inflectional Languages: Effects of Various Lemmatization and Stemming Approaches

In this paper, we study the effects of various lemmatization and stemming approaches on the named entity recognition (NER) task for Czech, a highly inflectional language. Lemmatizers are seen as a necessary component for Czech NER systems and they were used in all published papers about Czech NER so far. Thus, it has an utmost importance to explore their benefits, limits and differences between simple and complex methods. Our experiments are evaluated on the standard Czech Named Entity Corpus 1.1 as well as the newly created 2.0 version.

Segment Representations in Named Entity Recognition

In this paper we study the effects of various segment representations in the named entity recognition NER task. The segment representation is responsible for mapping multi-word entities into classes used in the chosen machine learning approach. Usually, the choice of a segment representation in the NER system is arbitrary without proper tests. Some authors presented comparisons of different segment representations such as BIO, BIEO, BILOU and usually compared only two segment representations. Our goal is to show, that the segment representation problem is more complex and that the proper selection of the best approach is not straightforward. We provide experiments with a wide set of segment representations. All the representations are tested using two popular machine learning algorithms: Conditional Random Fields and Maximum Entropy. Furthermore, the tests are done on four languages, namely English, Spanish, Dutch and Czech.