There has been a contemporary surge of interest in the application of stochastic models of parsing. The use of tree-adjoining grammar (TAG) in this domain has been relatively limited due in part to the unavailability, until recently, of large-scale corpora hand-annotated with TAG structures. Our goals are to develop inexpensive means of generating such corpora and to demonstrate their applicability to stochastic modeling. We present a method for automatically extracting a linguistically plausible TAG from the Penn Treebank. Furthermore, we also introduce labor-inexpensive methods for inducing higher-level organization of TAGs. Empirically, we perform an evaluation of various automatically extracted TAGs and also demonstrate how our induced higher-level organization of TAGs can be used for smoothing stochastic TAG models.

Anomaly detection can be seen as an unsupervised learning task in which a predictive model created on historical data is used to detect outlying instances in new data. This work addresses possibly promising but relatively uncommon application of anomaly detection to text data. Two English-language and one Polish-language Internet discussion forums devoted to psychoactive substances received from home-grown plants, such as hashish or marijuana, serve as text sources that are both realistic and possibly interesting on their own, due to potential associations with drug-related crime. The utility of two different vector text representations is examined: the simple bag of words representation and a more refined Global Vectors (GloVe) representation, which is an example of the increasingly popular word embedding approach. They are both combined with two unsupervised anomaly detection methods, based on one-class support vector machines (SVM) and based on dissimilarity to k-medoids clusters. The GloVe representation is found definitely more useful for anomaly detection, permitting better detection quality and ameliorating the curse of dimensionality issues with text clustering. The cluster dissimilarity approach combined with this representation outperforms one-class SVM with respect to detection quality and appears a more promising approach to anomaly detection in text data.

Detecting, whether a document contains sufficient new information to be deemed as novel, is of immense significance in this age of data duplication. Existing techniques for document-level novelty detection mostly perform at the lexical level and are unable to address the semantic-level redundancy. These techniques usually rely on handcrafted features extracted from the documents in a rule-based or traditional feature-based machine learning setup. Here, we present an effective approach based on neural attention mechanism to detect document-level novelty without any manual feature engineering. We contend that the simple alignment of texts between the source and target document(s) could identify the state of novelty of a target document. Our deep neural architecture elicits inference knowledge from a large-scale natural language inference dataset, which proves crucial to the novelty detection task. Our approach is effective and outperforms the standard baselines and recent work on document-level novelty detection by a margin of $\sim$ 3% in terms of accuracy.

Two studies on multilingual multimodal image description provide empirical evidence towards two questions at the core of the task: (i) whether target language speakers prefer descriptions generated directly in their native language, as compared to descriptions translated from a different language; (ii) whether images improve human translation of descriptions. These results provide guidance for future work in multimodal natural language processing by first showing that on the whole, translations are not distinguished from native language descriptions, and second delineating and quantifying the information gained from the image during the human translation task.

We discuss the random generation of strings using the grammatical formalism AGFL. This formalism consists of context-free grammars extended with a parameter mechanism, where the parameters range over a finite domain. Our approach consists in static analysis of the combinations of parameter values with which derivations can be constructed. After this analysis, generation of sentences can be performed without backtracking.

Accurate negation identification is one of the most important tasks in the context of sentiment analysis. In order to correctly interpret the sentiment value of a particular expression, we need to identify whether it is in the scope of negation. While much of the work on negation detection has focused on English, we have seen recent developments that provide accurate identification of negation in other languages. In this paper, we provide an overview of negation detection systems and describe an implementation of a Spanish system for negation cue detection and scope identification. We apply this system to the sentiment analysis task, confirming also for Spanish that improvements can be gained from accurate negation detection. The paper contributes an implementation of negation detection for sentiment analysis in Spanish and a detailed error analysis. This is the first work in Spanish in which a machine learning negation processing system is applied to the sentiment analysis task. Existing methods have used negation rules that have not been assessed, perhaps because the first Spanish corpus annotated with negation for sentiment analysis has only recently become available.

Arabic language is strongly structured and considered as one of the most highly inflected and derivational languages. Learning Arabic morphology is a basic step for language learners to develop language skills such as listening, speaking, reading, and writing. Arabic morphology is non-concatenative and provides the ability to attach a large number of affixes to each root or stem that makes combinatorial increment of possible inflected words. As such, Arabic lexical (morphological and phonological) rules may be confusing for second language learners. Our study indicates that research and development endeavors on spelling, and checking of grammatical errors does not provide adequate interpretations to second language learners’ errors. In this paper we address issues related to error diagnosis and feedback for second language learners of Arabic verbs and how they impact the development of a web-based intelligent language tutoring system. The major aim is to develop an Arabic intelligent language tutoring system that solves these issues and helps second language learners to improve their linguistic knowledge. Learners are encouraged to produce input freely in various situations and contexts, and are guided to recognize by themselves the erroneous functions of their misused expressions. Moreover, we proposed a framework that allows for the individualization of the learning process and provides the intelligent feedback that conforms to the learner's expertise for each class of error. Error diagnosis is not possible with current Arabic morphological analyzers. So constraint relaxation and edit distance techniques are successfully employed to provide error-specific diagnosis and adaptive feedback to learners. We demonstrated the capabilities of these techniques in diagnosing errors related to Arabic weak verbs formed using complex morphological rules. As a proof of concept, we have implemented the components that diagnose learner's errors and generate feedback which have been effectively evaluated against test data acquired from real teaching environment. The experimental results were satisfactory, and the performance achieved was 74.34 percent in terms of recall rate.

Textual Entailment is a directional relation between two text fragments. The relation holds whenever the truth of one text fragment, called Hypothesis (H), follows from another text fragment, called Text (T). Up until now, using machine learning approaches for recognizing textual entailment has been hampered by the limited availability of data. We present an approach based on syntactic transformations and machine learning techniques which is designed to fit well with a new type of available data sets that are larger but less complex than data sets used in the past. The transformations are not predefined, but calculated from the data sets, and then used as features in a supervised learning classifier. The method has been evaluated using two data sets: the SICK data set and the EXCITEMENT English data set. While both data sets are of a larger order of magnitude than data sets such as RTE-3, they are also of lower levels of complexity, each in its own way. SICK consists of pairs created by applying a predefined set of syntactic and lexical rules to its T and H pairs, which can be accurately captured by our transformations. The EXCITEMENT English data contains short pieces of text that do not require a high degree of text understanding to be annotated. The resulting AdArte system is simple to understand and implement, but also effective when compared with other existing systems. AdArte has been made freely available with the EXCITEMENT Open Platform, an open source platform for textual inference.

This paper proposes four novel term evaluation metrics to represent documents in the text categorization where class distribution is imbalanced. These metrics are achieved from the revision of the four common term evaluation metrics: chi-square, information gain, odds ratio, and relevance frequency. While the common metrics require a balanced class distribution, our proposed metrics evaluate the document terms under an imbalanced distribution. They calculate the degree of relatedness of terms with respect to minor and major classes by considering their imbalanced distribution. Using these metrics in the document representation makes a better distinction between the documents of the minor and major classes and improves the performance of machine learning algorithms. The proposed metrics are assessed over three popular benchmarks (two subsets of Reuters-21578 and WebKB) by using four classification algorithms: support vector machines, naive Bayes, decision trees, and centroid-based classifiers. Our empirical results indicate that the proposed metrics outperform the common metrics in the imbalanced text categorization.

In this introduction, we present our overview of interactive question answering (IQA). We contextualize IQA in the wider field of question answering, and establish connections to research in Information Retrieval and Dialogue Systems. We highlight the development of QA as a field, and identify challenges in the present research paradigm for which IQA is a potential solution. Finally, we present an overview of papers in this special issue, drawing connections between these and the challenges they address.

We present the architecture and data model for TEXTRACT, a robust, scalable and configurable document analysis framework. TEXTRACT has been engineered as a pipeline architecture, allowing for rapid prototyping and application development by freely mixing reusable, existing, language analysis plugins and custom, new, plugins with customizable functionality. We discuss design issues which arise from requirements of industrial strength efficiency and scalability, and which are further constrained by plugin interactions, both among themselves, and with a common data model comprising an annotation store, document vocabulary and a lexical cache. We exemplify some of these by focusing on a meta-plugin: an interpreter for annotation-based finite state transduction, through which many linguistic filters can be implemented as stand-alone plugins. The framework and component plugins have been extensively deployed in both research and industrial environments, for a broad range of text analysis and mining tasks.

This work presents the development and evaluation of an extended Urdu parser. It further focuses on issues related to this parser and describes the changes made in the Earley algorithm to get accurate and relevant results from the Urdu parser. The parser makes use of a morphologically rich context free grammar extracted from a linguistically-rich Urdu treebank. This grammar with sufficient encoded information is comparable with the state-of-the-art parsing requirements for the morphologically rich Urdu language. The extended parsing model and the linguistically rich extracted-grammar both provide us better evaluation results in Urdu/Hindi parsing domain. The parser gives 87% of f-score, which outperforms the existing parsing work of Urdu/Hindi based on the tree-banking approach.

Thesauri, which list the most salient semantic relations between words, have mostly been compiled manually. Therefore, the inclusion of an entry depends on the subjective decision of the lexicographer. As a consequence, those resources are usually incomplete. In this paper, we propose an unsupervised methodology to automatically discover pairs of semantically related words by highlighting their local environment and evaluating their semantic similarity in local and global semantic spaces. This proposal differs from all other research presented so far as it tries to take the best of two different methodologies, i.e. semantic space models and information extraction models. In particular, it can be applied to extract close semantic relations, it limits the search space to few, highly probable options and it is unsupervised.

Finite-state technology is considered the preferred model for representing the phonology and morphology of natural languages. The attractiveness of this technology for natural language processing stems from four sources: modularity of the design, due to the closure properties of regular languages and relations; the compact representation that is achieved through minimization; efficiency, which is a result of linear recognition time with finite-state devices; and reversibility, resulting from the declarative nature of such devices. However, when wide-coverage morphological grammars are considered, finite-state technology does not scale up well, and the benefits of this technology can be overshadowed by the limitations it imposes as a programming environment for language processing. This paper investigates the strengths and weaknesses of existing technology, focusing on various aspects of large-scale grammar development. Using a real-world case study, we compare a finite-state implementation with an equivalent Java program with respect to ease of development, modularity, maintainability of the code, and space and time efficiency. We identify two main problems, abstraction and incremental development, which are currently not addressed sufficiently well by finite-state technology, and which we believe should be the focus of future research and development.

In advertising, slogans are used to enhance the recall of the advertised product by consumers and to distinguish it from others in the market. Creating effective slogans is a resource-consuming task for humans. In this paper, we describe a novel method for automatically generating slogans, given a target concept (e.g., car) and an adjectival property to express (e.g., elegant) as input. Additionally, a key component in our approach is a novel method for generating nominal metaphors, using a metaphor interpretation model, to allow generating metaphorical slogans. The method for generating slogans extracts skeletons from existing slogans. It then fills a skeleton in with suitable words by utilizing multiple linguistic resources (such as a repository of grammatical relations, and semantic and language models) and genetic algorithms to optimize multiple objectives such as semantic relatedness, language correctness, and usage of rhetorical devices. We evaluate the metaphor and slogan generation methods by running crowdsourced surveys. On a five-point Likert scale, we ask online judges to evaluate whether the generated metaphors, along with three other metaphors generated using different methods, highlight the intended property. The slogan generation method is evaluated by asking crowdsourced judges to rate generated slogans from five perspectives: (1) how well is the slogan related to the topic, (2) how correct is the language of the slogan, (3) how metaphoric is the slogan, (4) how catchy, attractive, and memorable is it, and (5) how good is the slogan overall. Similarly, we evaluate existing expert-made slogans. Based on the evaluations, we analyze the method and provide insights regarding existing slogans. The empirical results indicate that our metaphor generation method is capable of producing apt metaphors. Regarding the slogan generator, the results suggest that the method has successfully produced at least one effective slogan for every evaluated input.

Most existing Natural Language Database Interfaces (NLDB) were designed to be used with database systems that provide very limited facilities for manipulating time-dependent data, and they do not support adequately temporal linguistic mechanisms (verb tenses, temporal adverbials, temporal subordinate clauses, etc.). The database community is becoming increasingly interested in temporal database systems, which are intended to store and manipulate in a principled manner information not only about the present, but also about the past and future. When interfacing to temporal databases, supporting temporal linguistic mechanisms becomes crucial.

We present a framework for constructing Natural Language Interfaces for Temporal Databases (NLTDB), which draws on research in tense and aspect theories, temporal logics and temporal databases. The framework consists of a temporal intermediate representation language, called TOP, an HPSG grammar that maps a wide range of questions involving temporal mechanisms to appropriate TOP expressions, and a provably correct method for translating from TOP to TSQL2, TSQL2 being a recently proposed temporal extension of the SQL database language. This framework was employed to implement a prototype NLTDB.

In this paper, we present results of a project that investigated the application of lexicon based text retrieval techniques to Alternative and Augmentative Communication (AAC). As a practical outcome of this research, a communication aid based on message retrieval by key words was designed, implemented and evaluated. The message retrieval module in the system uses a large semantic lexicon, derived from the WordNet database, for query expansion. Trials have been carried out with the device to evaluate whether the approach is suitable for AAC, and to determine the semantic relations that lead to efficient message retrieval. The first part of this paper describes the background of the project and highlights the retrieval requirements for a communication aid, which differ considerably from the requirements in standard text retrieval. We then present the overall design of the WordKeys communication aid and describe the tasks of its sub-modules. We summarise trials that have been carried out to determine the effect of semantic query expansion on the success of message retrieval. Evaluation results show that information about word frequency can solve problems that occurred in the semantic query expansion because of taxonomies that have too many intermediate steps between closely related words. Finally, a user evaluation with the improved system showed that full text retrieval is an effective approach to message access in a communication aid.

Paraphrase patterns are semantically equivalent patterns, which are useful in both paraphrase recognition and generation. This paper presents a pivot approach for extracting paraphrase patterns from bilingual parallel corpora, whereby the paraphrase patterns in English are extracted using the patterns in another language as pivots. We make use of log-linear models for computing the paraphrase likelihood between pattern pairs and exploit feature functions based on maximum likelihood estimation (MLE), lexical weighting (LW), and monolingual word alignment (MWA). Using the presented method, we extract more than 1 million pairs of paraphrase patterns from about 2 million pairs of bilingual parallel sentences. The precision of the extracted paraphrase patterns is above 78%. Experimental results show that the presented method significantly outperforms a well-known method called discovery of inference rules from text (DIRT). Additionally, the log-linear model with the proposed feature functions are effective. The extracted paraphrase patterns are fully analyzed. Especially, we found that the extracted paraphrase patterns can be classified into five types, which are useful in multiple natural language processing (NLP) applications.

Automatic deception detection is a crucial task that has many applications both in direct physical and in computer-mediated human communication. Our focus is on automatic deception detection in text across cultures. In this context, we view culture through the prism of the individualism/collectivism dimension, and we approximate culture by using country as a proxy. Having as a starting point recent conclusions drawn from the social psychology discipline, we explore if differences in the usage of specific linguistic features of deception across cultures can be confirmed and attributed to cultural norms in respect to the individualism/collectivism divide. In addition, we investigate if a universal feature set for cross-cultural text deception detection tasks exists. We evaluate the predictive power of different feature sets and approaches. We create culture/language-aware classifiers by experimenting with a wide range of n-gram features from several levels of linguistic analysis, namely phonology, morphology and syntax, other linguistic cues like word and phoneme counts, pronouns use, etc., and token embeddings. We conducted our experiments over eleven data sets from five languages (English, Dutch, Russian, Spanish, and Romanian), from six countries (United States of America, Belgium, India, Russia, Mexico, and Romania), and we applied two classification methods, namely logistic regression and fine-tuned BERT models. The results showed that the undertaken task is fairly complex and demanding. Furthermore, there are indications that some linguistic cues of deception have cultural origins and are consistent in the context of diverse domains and data set settings for the same language. This is more evident for the usage of pronouns and the expression of sentiment in deceptive language. The results of this work show that the automatic deception detection across cultures and languages cannot be handled in unified manners and that such approaches should be augmented with knowledge about cultural differences and the domains of interest.