Language-dependent Resources Research Articles

An Unsupervised Normalization Algorithm for Noisy Text: A Case Study for Information Retrieval and Stance Detection

A large fraction of textual data available today contains various types of “noise,” such as OCR noise in digitized documents, noise due to informal writing style of users on microblogging sites, and so on. To enable tasks such as search/retrieval and classification over all the available data, we need robust algorithms for text normalization, i.e., for cleaning different kinds of noise in the text. There have been several efforts towards cleaning or normalizing noisy text; however, many of the existing text normalization methods are supervised and require language-dependent resources or large amounts of training data that is difficult to obtain. We propose an unsupervised algorithm for text normalization that does not need any training data/human intervention. The proposed algorithm is applicable to text over different languages and can handle both machine-generated and human-generated noise. Experiments over several standard datasets show that text normalization through the proposed algorithm enables better retrieval and stance detection, as compared to that using several baseline text normalization methods.

Co-occurrence graph-based context adaptation: a new unsupervised approach to word sense disambiguation

Abstract Word sense disambiguation (WSD) is the task of selecting correct sense for an ambiguous word in its context. Since WSD is one of the most challenging tasks in various text processing systems, improving its accuracy can be very beneficial. In this article, we propose a new unsupervised method based on co-occurrence graph created by monolingual corpus without any dependency on the structure and properties of the language itself. In the proposed method, the context of an ambiguous word is represented as a sub-graph extracted from a large word co-occurrence graph built based on a corpus. Most of the words are connected in this graph. To clarify the exact sense of an ambiguous word, its senses and relations are added to the context graph, and various similarity functions are employed based on the senses and context graph. In the disambiguation process, we select senses with highest similarity to the context graph. As opposite to other WSD methods, the proposed method does not use any language-dependent resources (e.g. WordNet) and it just uses a monolingual corpus. Therefore, the proposed method can be employed for other languages. Moreover, by increasing the size of corpus, it is possible to enhance the accuracy of WSD. Experimental results on English and Persian datasets show that the proposed method is competitive with existing supervised and unsupervised WSD approaches.

Estudio de la influencia de incorporar conocimiento léxico-semántico a la técnica de Análisis de Componentes Principales para la generación de resúmenes multilingües

The objective of automatic text summarization is to reduce the dimension of a text keeping the relevant information. In this paper we analyse and apply the language-independent Principal Component Analysis technique for generating extractive single-document multilingual summaries. This technique will be studied to evaluate its performance with and without adding lexical-semantic knowledge through language-dependent resources and tools. Experiments were conducted using two different corpora: newswire and Wikipedia articles in three languages (English, German and Spanish) to validate the use of this technique in several scenarios. The proposed approaches show very competitive results compared to multilingual available systems, indicating that, although there is still room for improvement with respect to the technique and the type of knowledge to be taken into consideration, this has great potential for being applied in other contexts and for other languages.

Detection of sentence boundaries and abbreviations in clinical narratives.

BackgroundIn Western languages the period character is highly ambiguous, due to its double role as sentence delimiter and abbreviation marker. This is particularly relevant in clinical free-texts characterized by numerous anomalies in spelling, punctuation, vocabulary and with a high frequency of short forms.MethodsThe problem is addressed by two binary classifiers for abbreviation and sentence detection. A support vector machine exploiting a linear kernel is trained on different combinations of feature sets for each classification task. Feature relevance ranking is applied to investigate which features are important for the particular task. The methods are applied to German language texts from a medical record system, authored by specialized physicians.ResultsTwo collections of 3,024 text snippets were annotated regarding the role of period characters for training and testing. Cohen's kappa resulted in 0.98. For abbreviation and sentence boundary detection we can report an unweighted micro-averaged F-measure using a 10-fold cross validation of 0.97 for the training set. For test set based evaluation we obtained an unweighted micro-averaged F-measure of 0.95 for abbreviation detection and 0.94 for sentence delineation. Language-dependent resources and rules were found to have less impact on abbreviation detection than on sentence delineation.ConclusionsSentence detection is an important task, which should be performed at the beginning of a text processing pipeline. For the text genre under scrutiny we showed that support vector machines exploiting a linear kernel produce state of the art results for sentence boundary detection. The results are comparable with other sentence boundary detection methods applied to English clinical texts. We identified abbreviation detection as a supportive task for sentence delineation.

Time for More Languages

Most of the research on temporal tagging so far is done for processing English text documents. There are hardly any multilingual temporal taggers supporting more than two languages. Recently, the temporal tagger HeidelTime has been made publicly available, supporting the integration of new languages by developing language-dependent resources without modifying the source code. In this article, we describe our work on developing such resources for two Asian and two Romance languages: Arabic, Vietnamese, Spanish, and Italian. While temporal tagging of the two Romance languages has been addressed before, there has been almost no research on Arabic and Vietnamese temporal tagging so far. Furthermore, we analyze language-dependent challenges for temporal tagging and explain the strategies we followed to address them. Our evaluation results on publicly available and newly annotated corpora demonstrate the high quality of our new resources for the four languages, which we make publicly available to the research community.

A multiobjective simulated annealing approach for classifier ensemble: Named entity recognition in Indian languages as case studies

In this paper, we propose a simulated annealing (SA) based multiobjective optimization (MOO) approach for classifier ensemble. Several different versions of the objective functions are exploited. We hypothesize that the reliability of prediction of each classifier differs among the various output classes. Thus, in an ensemble system, it is necessary to find out the appropriate weight of vote for each output class in each classifier. Diverse classification methods such as Maximum Entropy (ME), Conditional Random Field (CRF) and Support Vector Machine (SVM) are used to build different models depending upon the various representations of the available features. One most important characteristics of our system is that the features are selected and developed mostly without using any deep domain knowledge and/or language dependent resources. The proposed technique is evaluated for Named Entity Recognition (NER) in three resource-poor Indian languages, namely Bengali, Hindi and Telugu. Evaluation results yield the recall, precision and F-measure values of 93.95%, 95.15% and 94.55%, respectively for Bengali, 93.35%, 92.25% and 92.80%, respectively for Hindi and 84.02%, 96.56% and 89.85%, respectively for Telugu. Experiments also suggest that the classifier ensemble identified by the proposed MOO based approach optimizing the F-measure values of named entity (NE) boundary detection outperforms all the individual models, two conventional baseline models and three other MOO based ensembles.

Time and space-efficient architecture for a corpus-based text-to-speech synthesis system

This paper proposes a time and space-efficient architecture for a text-to-speech synthesis system (TTS). The proposed architecture can be efficiently used in those applications with unlimited domain, requiring multilingual or polyglot functionality. The integration of a queuing mechanism, heterogeneous graphs and finite-state machines gives a powerful, reliable and easily maintainable architecture for the TTS system. Flexible and language-independent framework efficiently integrates all those algorithms used within the scope of the TTS system. Heterogeneous relation graphs are used for linguistic information representation and feature construction. Finite-state machines are used for time and space-efficient representation of language resources, for time and space-efficient lookup processes, and the separation of language-dependent resources from a language-independent TTS engine. Its queuing mechanism consists of several dequeue data structures and is responsible for the activation of all those TTS engine modules having to process the input text. In the proposed architecture, all modules use the same data structure for gathering linguistic information about input text. All input and output formats are compatible, the structure is modular and interchangeable, it is easily maintainable and object oriented. The proposed architecture was successfully used when implementing the Slovenian PLATTOS corpus-based TTS system, as presented in this paper.

Towards multilingual interoperability in automatic speech recognition

This communication addresses multilingual aspects in speech recognition and tries to link them to the concept of interoperability. After a tentative definition of multilingual interoperability, the speech recognition components are discussed with a view towards separating language-specific from language-independent elements. An overview gives examples of previous multilingual speech recognition research and developments across different speaking styles (read, prepared and conversational). The problem of adaptation across languages is addressed. In particular there exist language-independent and cross-language acoustic modeling techniques to port recognition systems from one language to another without language-specific acoustic data. However these data remain valuable for acoustic model adaptation. At this time pronunciation dictionaries and text material appear to be the most crucial language-dependent resources. In our opinion fast porting, enabled by the existence of these language-dependent resources, is a step towards multilingual interoperability. On-going efforts to produce multilingual pronunciation dictionaries and to collect multilingual text corpora including speech transcripts, should be extended to the largest possible number of languages. These efforts could be shared with initiatives aiming at the support of minority languages.