A large collection of texts may be reached through the Internet and this provides a powerful platform from which common-sense knowledge may be gathered. This paper presents a system that contains a core knowledge base structured around WordNet, a lexical database, capable of extracting contextual information from a given input text. Such context information is then used to retrieve other texts from the Internet that relate to that context. When processed by the system, these new texts bring more information that represents an enhanced domain context for the initial text. This is an incremental method for text processing that acquires domain knowledge from other texts. The paper describes the system architecture, its core knowledge base and inference engine, and the acquisition of new knowledge from corpora.

Synchronous tree substitution grammars (stsg) are a (formal) tree transformation model that is used in the area of syntax-based machine translation. A competitor that is at least as expressive as stsg is proposed and compared to stsg. The competitor is the extended multi bottom-up tree transducer (mbot), which is the bottom-up analogue with the additional feature that states have non-unary ranks. Unweighted mbot have already been investigated with respect to their basic properties, but the particular properties of the constructions that are required in the machine translation task are largely unknown. stsg and mbot are compared with respect to binarization, regular restriction, and application. Particular attention is paid to the complexity of the constructions.

Capturing word meaning is one of the challenges of natural language processing (NLP). Formal models of meaning, such as networks of words or concepts, are knowledge repositories used in a variety of applications. To be effectively used, these networks have to be large or, at least, adapted to specific domains. Learning word meaning from texts is then an active area of research. Lexico-syntactic pattern methods are one of the possible solutions. Yet, these models do not use structural properties of target semantic relations, e.g. transitivity, during learning. In this paper, we propose a novel lexico-syntactic pattern probabilistic method for learning taxonomies that explicitly models transitivity and naturally exploits vector space model techniques for reducing space dimensions. We define two probabilistic models: the direct probabilistic model and the induced probabilistic model. The first is directly estimated on observations over text collections. The second uses transitivity on the direct probabilistic model to induce probabilities of derived events. Within our probabilistic model, we also propose a novel way of using singular value decomposition as unsupervised method for feature selection in estimating direct probabilities. We empirically show that the induced probabilistic taxonomy learning model outperforms state-of-the-art probabilistic models and our unsupervised feature selection method improves performance.

In this study, we investigate the process of generating single-sentence representations for the purpose of Dialogue Act (DA) classification, including several aspects of text pre-processing and input representation which are often overlooked or underreported within the literature, for example, the number of words to keep in the vocabulary or input sequences. We assess each of these with respect to two DA-labelled corpora, using a range of supervised models, which represent those most frequently applied to the task. Additionally, we compare context-free word embedding models with that of transfer learning via pre-trained language models, including several based on the transformer architecture, such as Bidirectional Encoder Representations from Transformers (BERT) and XLNET, which have thus far not been widely explored for the DA classification task. Our findings indicate that these text pre-processing considerations do have a statistically significant effect on classification accuracy. Notably, we found that viable input sequence lengths, and vocabulary sizes, can be much smaller than is typically used in DA classification experiments, yielding no significant improvements beyond certain thresholds. We also show that in some cases the contextual sentence representations generated by language models do not reliably outperform supervised methods. Though BERT, and its derivative models, do represent a significant improvement over supervised approaches, and much of the previous work on DA classification.

The occurrence of code-switching in online communication, when a writer switches among multiple languages, presents a challenge for natural language processing tools, since they are designed for texts written in a single language. To answer the challenge, this paper presents detailed research on ways to detect code-switching in Arabic text automatically. We compare the prediction by partial matching (PPM) compression-based classifier, implemented in Tawa, and a traditional machine learning classifier sequential minimal optimization (SMO), implemented in Waikato Environment for Knowledge Analysis, working specifically on Arabic text taken from Facebook. Three experiments were conducted in order to: (1) detect code-switching among the Egyptian dialect and English; (2) detect code-switching among the Egyptian dialect, the Saudi dialect, and English; and (3) detect code-switching among the Egyptian dialect, the Saudi dialect, Modern Standard Arabic (MSA), and English. Our experiments showed that PPM achieved a higher accuracy rate than SMO with 99.8% versus 97.5% in the first experiment and 97.8% versus 80.7% in the second. In the third experiment, PPM achieved a lower accuracy rate than SMO with 53.2% versus 60.2%. Code-switching between Egyptian Arabic and English text is easiest to detect because Arabic and English are generally written in different character sets. It is more difficult to distinguish between Arabic dialects and MSA as these use the same character set, and most users of Arabic, especially Saudis and Egyptians, frequently mix MSA with their dialects. We also note that the MSA corpus used for training the MSA model may not represent MSA Facebook text well, being built from news websites. This paper also describes in detail the new Arabic corpora created for this research and our experiments.

The alignment of WordNet and Wikipedia has received wide attention from researchers of computational linguistics, who are building a new lexical knowledge source or enriching the semantic information of WordNet entities. The main challenge of this alignment is how to handle the synonymy and ambiguity issues in the contents of two units from different sources. Therefore, this paper introduces mapping method that links an Arabic WordNet synset to its corresponding article in Wikipedia. This method uses monolingual and bilingual features to overcome the lack of semantic information in Arabic WordNet. For evaluating this method, an Arabic mapping data set, which contains 1,291 synset–article pairs, is compiled. The experimental analysis shows that the proposed method achieves promising results and outperforms the state-of-the-art methods that depend only on monolingual features. The mapped method has also been used to increase the coverage of Arabic WordNet by inserting new synsets from Wikipedia.

We investigate the problem of complex answers in question answering. Complex answers consist of several simple answers. We describe the online question answering system SHAPAQA, and using data from this system we show that the problem of complex answers is quite common. We define nine types of complex questions, and suggest two approaches, based on answer frequencies, that allow question answering systems to tackle the problem.

Arabic prosody is the science that studies the music of Arabic poetry, which is mainly meter and rhyme. The identification of meters for Arabic verses or poems is a complicated task. This task requires a certain level of expertise to identify the meter to which a verse belongs. In this paper, we present BASRAH1, a system that automatically identifies the meter of Arabic poetry by using the numerical prosody method. The numerical prosody method depends on verse coding, which is derived from the general concept of Al-Khalil's feet by using two primary units (cord = 2) and (peg = 3). On testing both old and modern Arabic verses and poems, BASRAH has proved to be an efficient tool to help inexperienced users to determine the meter of Arabic verses and poems.

Many research topics in natural language processing (NLP), such as explanation generation, dialog modeling, or machine translation, require evaluation that goes beyond standard metrics like accuracy or F1 score toward a more human-centered approach. Therefore, understanding how to design user studies becomes increasingly important. However, few comprehensive resources exist on planning, conducting, and evaluating user studies for NLP, making it hard to get started for researchers without prior experience in the field of human evaluation. In this paper, we summarize the most important aspects of user studies and their design and evaluation, providing direct links to NLP tasks and NLP-specific challenges where appropriate. We (i) outline general study design, ethical considerations, and factors to consider for crowdsourcing, (ii) discuss the particularities of user studies in NLP, and provide starting points to select questionnaires, experimental designs, and evaluation methods that are tailored to the specific NLP tasks. Additionally, we offer examples with accompanying statistical evaluation code, to bridge the gap between theoretical guidelines and practical applications.

We propose a language-independent word normalisation method and exemplify it on modernising historical Slovene words. Our method relies on character-level statistical machine translation (CSMT) and uses only shallow knowledge. We present relevant data on historical Slovene, consisting of two (partially) manually annotated corpora and the lexicons derived from these corpora, containing historical word–modern word pairs. The two lexicons are disjoint, with one serving as the training set containing 40,000 entries, and the other as a test set with 20,000 entries. The data spans the years 1750–1900, and the lexicons are split into fifty-year slices, with all the experiments carried out separately on the three time periods. We perform two sets of experiments. In the first one – a supervised setting – we build a CSMT system using the lexicon of word pairs as training data. In the second one – an unsupervised setting – we simulate a scenario in which word pairs are not available. We propose a two-step method where we first extract a noisy list of word pairs by matching historical words with cognate modern words, and then train a CSMT system on these pairs. In both sets of experiments, we also optionally make use of a lexicon of modern words to filter the modernisation hypotheses. While we show that both methods produce significantly better results than the baselines, their accuracy and which method works best strongly correlates with the age of the texts, meaning that the choice of the best method will depend on the properties of the historical language which is to be modernised. As an extrinsic evaluation, we also compare the quality of part-of-speech tagging and lemmatisation directly on historical text and on its modernised words. We show that, depending on the age of the text, annotation on modernised words also produces significantly better results than annotation on the original text.

This paper addresses the feasibility of cross-lingual parsing with Universal Dependencies (UD) between Romance languages, analyzing its performance when compared to the use of manually annotated resources of the target languages. Several experiments take into account factors such as the lexical distance between the source and target varieties, the impact of delexicalization, the combination of different source treebanks or the adaptation of resources to the target language, among others. The results of these evaluations show that the direct application of a parser from one Romance language to another reaches similar labeled attachment score (LAS) values to those obtained with a manual annotation of about 3,000 tokens in the target language, and unlabeled attachment score (UAS) results equivalent to the use of around 7,000 tokens, depending on the case. These numbers can noticeably increase by performing a focused selection of the source treebanks. Furthermore, the removal of the words in the training corpus (delexicalization) is not useful in most cases of cross-lingual parsing of Romance languages. The lessons learned with the performed experiments were used to build a new UD treebank for Galician, with 1,000 sentences manually corrected after an automatic cross-lingual annotation. Several evaluations in this new resource show that a cross-lingual parser built with the best combination and adaptation of the source treebanks performs better (77 percent LAS and 82 percent UAS) than using more than 16,000 (for LAS results) and more than 20,000 (UAS) manually labeled tokens of Galician.

Generic software architectures aim to support re-use of components, focusing of research and development effort, and evaluation and comparison of approaches. In the field of natural language processing, generic frameworks for understanding have been successfully deployed to meet all of these aims, but nothing comparable yet exists for generation. The nature of the task itself, and the current methodologies available to research it, seem to make it more difficult to reach the necessary level of consensus to support generic proposals. Recent work has made progress towards establishing a generic framework for generation at the functional level, but left open the issue of actual implementation. In this paper, we discuss the requirements for such an implementation layer for generation systems, drawing on two initial attempts to implement it. We argue that it is possible and useful to distinguish “functional architecture” from “implementation architecture” for generation systems.

Named Entity Recognition is a basic task in Information Extraction that aims at identifying entities of interest within full text documents. The patterns used to recognize entities can be rule based, as in the popular JAPE system. However, hand-crafting effective patterns is often difficult, and yet there is little research devoted to methods capable of learning human-readable patterns, possibly with arbitrary sets of features. In this paper, we present a semi-automatic method to generate both regular expressions and a subset of the JAPE language. It does not need a corpus annotated beforehand. Instead, it employs active learning and combines clustering with an algorithm that finds alignments between symbols present in the entities discovered during the learning process. The method currently supports a fixed set of character features and an arbitrary set of token features, but it can incorporate other kinds of features as well. Through several experiments with an English corpus, we show the ability of the method to generate effective patterns at a low annotation cost, and how it can successfully help in the annotation of brand new corpora.

Finding translations for technical terms is an important problem in machine translation. In particular, in highly specialized domains such as biology or medicine, it is difficult to find bilingual experts to annotate sufficient cross-lingual texts in order to train machine translation systems. Moreover, new terms are constantly being generated in the biomedical community, which makes it difficult to keep the translation dictionaries up to date for all language pairs of interest. Given a biomedical term in one language (source language), we propose a method for detecting its translations in a different language (target language). Specifically, we train a binary classifier to determine whether two biomedical terms written in two languages are translations. Training such a classifier is often complicated due to the lack of common features between the source and target languages. We propose several feature space concatenation methods to successfully overcome this problem. Moreover, we study the effectiveness of contextual and character n-gram features for detecting term translations. Experiments conducted using a standard dataset for biomedical term translation show that the proposed method outperforms several competitive baseline methods in terms of mean average precision and top-k translation accuracy.

We present the RAGS (Reference Architecture for Generation Systems) framework, a specification of an abstract Natural Language Generation (NLG) system architecture to support sharing, re-use, comparison and evaluation of NLG technologies. We argue that the evidence from a survey of actual NLG systems calls for a different emphasis in a reference proposal from that seen in similar initiatives in information extraction and multimedia interfaces. We introduce the framework itself, in particular the two-level data model that allows us to support the complex data requirements of NLG systems in a flexible and coherent fashion, and describe our efforts to validate the framework through a range of implementations.

The paper presents experiments on part-of-speech and full morphological tagging of the Slavic minority language Rusyn. The proposed approach relies on transfer learning and uses only annotated resources from related Slavic languages, namely Russian, Ukrainian, Slovak, Polish, and Czech. It does not require any annotated Rusyn training data, nor parallel data or bilingual dictionaries involving Rusyn. Compared to earlier work, we improve tagging performance by using a neural network tagger and larger training data from the neighboring Slavic languages. We experiment with various data preprocessing and sampling strategies and evaluate the impact of multitask learning strategies and of pretrained word embeddings. Overall, while genre discrepancies between training and test data have a negative impact, we improve full morphological tagging by 9% absolute micro-averaged F1 as compared to previous research.

Humans proficiently interpret the true sense of an ambiguous word by establishing association among words in a sentence. The complete sense of text is also based on implicit information, which is not explicitly mentioned. The absence of this implicit information is a significant problem for a computer program that attempts to determine the correct sense of ambiguous words. In this paper, we propose a novel method to uncover the implicit information that links the words of a sentence. We reveal this implicit information using a graph, which is then used to disambiguate the ambiguous word. The experiments show that the proposed algorithm interprets the correct sense for both homonyms and polysemous words. Our proposed algorithm has performed better than the approaches presented in the SemEval-2013 task for word sense disambiguation and has shown an accuracy of 79.6 percent, which is 2.5 percent better than the best unsupervised approach in SemEval-2007.

Paraphrase corpora are an essential but scarce resource in Natural Language Processing. In this paper, we present the Wikipedia-based Relational Paraphrase Acquisition (WRPA) method, which extracts relational paraphrases from Wikipedia, and the derived WRPA paraphrase corpus. The WRPA corpus currently covers person-related and authorship relations in English and Spanish, respectively, suggesting that, given adequate Wikipedia coverage, our method is independent of the language and the relation addressed. WRPA extracts entity pairs from structured information in Wikipedia applying distant learning and, based on the distributional hypothesis, uses them as anchor points for candidate paraphrase extraction from the free text in the body of Wikipedia articles. Focussing on relational paraphrasing and taking advantage of Wikipedia-structured information allows for an automatic and consistent evaluation of the results. The WRPA corpus characteristics distinguish it from other types of corpora that rely on string similarity or transformation operations. WRPA relies on distributional similarity and is the result of the free use of language outside any reformulation framework. Validation results show a high precision for the corpus.

This paper proposes a robust text classification and correspondence analysis approach to identification of similar languages. In particular, we propose to use the readily available information of clauses and word length distribution to model similar languages. The modeling and classification are based on the hypothesis that languages are self-adaptive complex systems and hence can be classified by dynamic features describing the system, especially in terms of distributional relations of constituents of a system. For similar languages whose grammatical differences are often subtle, classification based on dynamic system features should be more effective. To test this hypothesis, we considered both regional and genre varieties of Mandarin Chinese for classification. The data are extracted from two comparable balanced corpora to minimize possible confounding factors. The two corpora are the Sinica Corpus from Taiwan and the Lancaster Corpus of Mandarin Chinese from Mainland China, and the two genres are reportage and review. Our text classification and correspondence analysis results show that the linguistically felicitous two-level constituency model combining power functions between word and clauses effectively classifies the two varieties of Chinese for both genres. In addition, we found that genres do have compounding effect on classification of regional varieties. In particular, reportage in two varieties is more likely to be classified than review, corroborating the complex system view of language variations. That is, language variations and changes typically do not take place evenly across the board for the complete language system. This further enhances our hypothesis that dynamic complex system features, such as the power functions captured by the Menzerath–Altmann law, provide effective models in classifications of similar languages.

Recently, most part-of-speech tagging approaches, such as rule-based, probabilistic and neural network approaches, have shown very promising results. In this paper, we are particularly interested in probabilistic approaches, which usually require lots of training data to get reliable probabilities. We alleviate such a restriction of probabilistic approaches by introducing a fuzzy network model to provide a method for estimating more reliable parameters of a model under a small amount of training data. Experiments with the Brown corpus show that the performance of the fuzzy network model is much better than that of the hidden Markov model under a limited amount of training data.