Work in computer vision and natural language processing involving images and text has been experiencing explosive growth over the past decade, with a particular boost coming from the neural network revolution. The present volume brings together five research articles from several different corners of the area: multilingual multimodal image description (Frank et al.), multimodal machine translation (Madhyastha et al., Frank et al.), image caption generation (Madhyastha et al., Tanti et al.), visual scene understanding (Silberer et al.), and multimodal learning of high-level attributes (Sorodoc et al.). In this article, we touch upon all of these topics as we review work involving images and text under the three main headings of image description (Section 2), visually grounded referring expression generation (REG) and comprehension (Section 3), and visual question answering (VQA) (Section 4).

Automatic term extraction has become a priority area of research within corpus processing. Despite the extensive literature in this field, there are still some outstanding issues that should be dealt with during the construction of term extractors, particularly those oriented to support research in terminology and terminography. In this regard, this article describes the design and development of DEXTER, an online workbench for the extraction of simple and complex terms from domain-specific corpora in English, French, Italian and Spanish. In this framework, three issues contribute to placing the most important terms in the foreground. First, unlike the elaborate morphosyntactic patterns proposed by most previous research, shallow lexical filters have been constructed to discard term candidates. Second, a large number of common stopwords are automatically detected by means of a method that relies on the IATE database together with the frequency distribution of the domain-specific corpus and a general corpus. Third, the term-ranking metric, which is grounded on the notions of salience, relevance and cohesion, is guided by the IATE database to display an adequate distribution of terms.

The semantic information of documents needs to be represented because it is the basis for many applications, such as document summarization, web search, and text analysis. Although many studies have explored this problem by enriching document vectors with the relatedness of the words involved, the performance remains far from satisfactory because the physical boundaries of documents hinder the evaluation of the relatedness between words. To address this problem, we propose an effective approach to further infer the implicit relatedness between words via their common related words. To avoid overestimation of the implicit relatedness, we restrict the inference in terms of the marginal probabilities of the words based on the law of total probability. The proposed method measures the relatedness between words, which is confirmed theoretically and experimentally. Thorough evaluation on real datasets illustrates that significant improvement on document clustering has been achieved with the proposed method compared with state-of-the-art methods.

The Journal of Natural Language Engineering (JNLE) has enjoyed another very successful year. The impact factor of the journal has increased for the third consecutive year, with the journal being listed among both Linguistics and Computer Science categories. Against the background of a record number of submissions, JNLE has, since 2016, been offering six 160-page issues per year, which by far exceeds the four 96-page issues offered less than 10 years ago!

This paper reviews the state-of-the-art of one emergent field in computational linguistics—semantic change computation. It summarizes the literature by proposing a framework that identifies five components in the field: diachronic corpus, diachronic word sense characterization, change modelling, evaluation and data visualization. Despite its potentials, the review shows that current studies are mainly focused on testifying hypotheses of semantic change from theoretical linguistics and that several core issues remain to be tackled: the need of diachronic corpora for languages other than English, the comparison and development of approaches to diachronic word sense characterization and change modelling, the need of comprehensive evaluation data and further exploration of data visualization techniques for hypothesis justification.

Our passion to continually improve the journal and, as a result, our contribution to the community drives our quest for highly diversified and up-to-date content. We are launching a new category of papers, i.e., ‘keynote’ or ‘invited’ papers, which will be penned by leading lights in the field.

Major advances have recently been made in merging language and vision representations. Most tasks considered so far have confined themselves to the processing of objects and lexicalised relations amongst objects (content words). We know, however, that humans (even pre-school children) can abstract over raw multimodal data to perform certain types of higher level reasoning, expressed in natural language by function words. A case in point is given by their ability to learn quantifiers, i.e. expressions like few, some and all. From formal semantics and cognitive linguistics, we know that quantifiers are relations over sets which, as a simplification, we can see as proportions. For instance, in most fish are red, most encodes the proportion of fish which are red fish. In this paper, we study how well current neural network strategies model such relations. We propose a task where, given an image and a query expressed by an object–property pair, the system must return a quantifier expressing which proportions of the queried object have the queried property. Our contributions are twofold. First, we show that the best performance on this task involves coupling state-of-the-art attention mechanisms with a network architecture mirroring the logical structure assigned to quantifiers by classic linguistic formalisation. Second, we introduce a new balanced dataset of image scenarios associated with quantification queries, which we hope will foster further research in this area.

The objective, in this article, is to address the issue of the comparability of documents, which are extracted from different sources and written in different languages. These documents are not necessarily translations of each other. This material is referred as multilingual comparable corpora. These language resources are useful for multilingual natural language processing applications, especially for low-resourced language pairs. In this paper, we collect different data in Arabic, English, and French. Two corpora are built by using available hyperlinks for Wikipedia and Euronews. Euronews is an aligned multilingual (Arabic, English, and French) corpus of 34k documents collected from Euronews website. A more challenging issue is to build comparable corpus from two different and independent media having two distinct editorial lines, such as British Broadcasting Corporation (BBC) and Al Jazeera (JSC). To build such corpus, we propose to use the Cross-Lingual Latent Semantic approach. For this purpose, documents have been harvested from BBC and JSC websites for each month of the years 2012 and 2013. The comparability is calculated for each Arabic–English couple of documents of each month. This automatic task is then validated by hand. This led to a multilingual (Arabic–English) aligned corpus of 305 pairs of documents (233k English words and 137k Arabic words). In addition, a study is presented in this paper to analyze the performance of three methods of the literature allowing to measure the comparability of documents on the multilingual reference corpora. A recall at rank 1 of 50.16 per cent is achieved with the Cross-lingual LSI approach for BBC–JSC test corpus, while the dictionary-based method reaches a recall of only 35.41 per cent.

It is a challenging task to discover information from a large amount of data in an open domain.1 In this paper, an event network framework is proposed to address this challenge. It is in fact an empirical construct for exploring open information, composed of three steps: document event detection, event network construction and event network analysis. First, documents are clustered into document events for reducing the impact of noisy and heterogeneous resources. Secondly, linguistic units (e.g., named entities or entity relations) are extracted from each document event and combined into an event network, which enables content-oriented retrieval. Then, in the final step, techniques such as social network or complex network can be applied to analyze the event network for exploring open information. In the implementation section, we provide examples of exploring open information via event network.

We investigate feature selection methods for machine learning approaches in sentiment analysis. More specifically, we use data from the cooking platform Epicurious and attempt to predict ratings for recipes based on user reviews. In machine learning approaches to such tasks, it is a common approach to use word or part-of-speech n-grams. This results in a large set of features, out of which only a small subset may be good indicators for the sentiment. One of the questions we investigate concerns the extension of feature selection methods from a binary classification setting to a multi-class problem. We show that an inherently multi-class approach, multi-class information gain, outperforms ensembles of binary methods. We also investigate how to mitigate the effects of extreme skewing in our data set by making our features more robust and by using review and recipe sampling. We show that over-sampling is the best method for boosting performance on the minority classes, but it also results in a severe drop in overall accuracy of at least 6 per cent points.

As the interest of the Semantic Web and computational linguistics communities in linguistic linked data (LLD) keeps increasing and the number of contributions that dwell on LLD rapidly grows, scholars (and linguists in particular) interested in the development of LLD resources sometimes find it difficult to determine which mechanism is suitable for their needs and which challenges have already been addressed. This review seeks to present the state of the art on the models, ontologies and their extensions to represent language resources as LLD by focusing on the nature of the linguistic content they aim to encode. Four basic groups of models are distinguished in this work: models to represent the main elements of lexical resources (group 1), vocabularies developed as extensions to models in group 1 and ontologies that provide more granularity on specific levels of linguistic analysis (group 2), catalogues of linguistic data categories (group 3) and other models such as corpora models or service-oriented ones (group 4). Contributions encompassed in these four groups are described, highlighting their reuse by the community and the modelling challenges that are still to be faced.

Comparable corpora serve as an important substitute for parallel resources in cases of under-resourced language pairs. Previous work mostly aims to find a better strategy to exploit existing comparable corpora, while ignoring the variety in corpus quality. The quality of comparable corpora affects a lot its usability in practice, a fact that has been justified by several studies. However, researchers have not been able to establish a widely accepted and fully validated framework to measure corpus quality. We will thus investigate in this paper a comprehensive methodology to deal with the quality of comparable corpora. To be exact, we will propose several comparability measures and a quantitative strategy to test those measures. Our experiments show that the proposed comparability measure can capture gold-standard comparability levels very well and is robust to the bilingual dictionary used. Moreover, we will show in the task of bilingual lexicon extraction that the proposed measure correlates well with the performance of the real world application.

Social media are an emerging new paradigm in interdisciplinary research in crisis informatics. They bring many opportunities as well as challenges to all fields of application and research involved in the project of using social media content for an improved disaster management. Using the Central European flooding 2013 as our case study, we optimize and apply methods from the field of natural language processing and unsupervised machine learning to investigate the thematic and temporal structure of German social media communication. By means of topic model analysis, we will investigate which kind of content was shared on social media during the event. On this basis, we will, furthermore, investigate the development of topics over time and apply temporal clustering techniques to automatically identify different characteristic phases of communication. From the results, we, first, want to reveal properties of social media content and show what potential social media have for improving disaster management in Germany. Second, we will be concerned with the methodological issue of finding and adapting natural language processing methods that are suitable for analysing social media data in order to obtain information relevant for disaster management. With respect to the first, application-oriented focal point, our study reveals high potential of social media content in the factual, organizational and psychological dimension of the disaster and during all stages of the disaster management life cycle. Interestingly, there appear to be systematic differences in thematic profile between the different platforms Facebook and Twitter and between different stages of the event. In context of our methodological investigation, we claim that if topic model analysis is combined with appropriate optimization techniques, it shows high applicability for thematic and temporal social media analysis in disaster management.

In the recent years, many benchmark author profiling corpora have been developed for various genres including Twitter, social media, blogs, hotel reviews and e-mail, etc. However, no such standard evaluation resource has been developed for Short Messaging Service (SMS), a popular medium of communication, which is very useful for author profiling. The primary aim of this study is to develop a large multilingual (English and Roman Urdu) benchmark SMS-based author profiling corpus. The proposed corpus contains 810 author profiles, wherein each profile consists of an aggregation of SMS messages as a single document of an author, along with seven demographic traits associated with each author profile: gender, age, native language, native city, qualification, occupation and personality type (introvert/extrovert). The secondary aims of this study include the following: (1) annotating the proposed corpus for code-switching annotations at the lexical level (approximately 0.69 million tokens are manually annotated for code-switching) and (2) applying the stylometry-based method (groups of sixty-four features) and the content-based method (twelve features) for gender identification in order to demonstrate how our proposed corpus can be used for the development and evaluation of various author profiling methods. The results show that the content-based character 5-gram feature outperformed all the other features by obtaining the accuracy score of 0.975 and F1 score of 0.947 for gender identification while using the entire corpus. Furthermore, our proposed corpora (SMS–AP–18 and code-switched SMS–AP–18) are freely and publicly available for research purpose.

Semantic measures are used in handling different issues in several research areas, such as artificial intelligence, natural language processing, knowledge engineering, bioinformatics, and information retrieval. Hierarchical feature-based semantic measures have been proposed to estimate the semantic similarity between two concepts/words depending on the features extracted from a semantic taxonomy (hierarchy) of a given lexical source. The central issue in these measures is the constant weighting assumption that all elements in the semantic representation of the concept possess the same relevance. In this paper, a new weighting-based semantic similarity measure is proposed to address the issues in hierarchical feature-based measures. Four mechanisms are introduced to weigh the degree of relevance of features in the semantic representation of a concept by using topological parameters (edge, depth, descendants, and density) in a semantic taxonomy. With the semantic taxonomy of WordNet, the proposed semantic measure is evaluated for word semantic similarity in four gold-standard datasets. Experimental results show that the proposed measure outperforms hierarchical feature-based semantic measures in all the datasets. Comparison results also imply that the proposed measure is more effective than information-content measures in measuring semantic similarity.

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.

Despite the long history of Natural Language Generation (NLG) research, the potential for influencing real world behaviour through automatically generated texts has not received much attention. In this paper, we present SaferDrive, a behaviour change support system that uses NLG and telematic data in order to create weekly textual feedback for automobile drivers, which is delivered through a smartphone application. Usage-based car insurances use sensors to track driver behaviour. Although the data collected by such insurances could provide detailed feedback about the driving style, they are typically withheld from the driver and used only to calculate insurance premiums. SaferDrive instead provides detailed textual feedback about the driving style, with the intent to help drivers improve their driving habits. We evaluate the system with real drivers and report that the textual feedback generated by our system does have a positive influence on driving habits, especially with regard to speeding.

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.

Just as industrialization matured from mass production to customization and personalization, so has the Web migrated from generic content to public disclosures of one’s most intimately held thoughts, opinions, and beliefs. This relatively new type of data is able to represent finer and more narrowly defined demographic slices. If until now researchers have primarily focused on leveraging personalized content to identify latent information such as gender, nationality, location, or age, this article seeks to establish a structured way of extracting possessions, or items that people own or are entitled to, as a way to ultimately provide insights into people’s behaviors and characteristics. We introduce the new task of ‘possession identification in text’, and release a novel dataset where possessions are marked at different confidence levels. We present experiments and results obtained when seeking to automatically identify and extract possessions from the text.

Neural Network-based approaches have recently produced good performances in Natural language tasks, such as Supertagging. In the supertagging task, a Supertag (Lexical category) is assigned to each word in an input sequence. Combinatory Categorial Grammar Supertagging is a more challenging problem than various sequence-tagging problems, such as part-of-speech (POS) tagging and named entity recognition due to the large number of the lexical categories. Specifically, simple Recurrent Neural Network (RNN) has shown to significantly outperform the previous state-of-the-art feed-forward neural networks. On the other hand, it is well known that Recurrent Networks fail to learn long dependencies. In this paper, we introduce a new neural network architecture based on backward and Bidirectional Long Short-Term Memory (BLSTM) Networks that has the ability to memorize information for long dependencies and benefit from both past and future information. State-of-the-art methods focus on previous information, whereas BLSTM has access to information in both previous and future directions. Our main findings are that bidirectional networks outperform unidirectional ones, and Long Short-Term Memory (LSTM) networks are more precise and successful than both unidirectional and bidirectional standard RNNs. Experiment results reveal the effectiveness of our proposed method on both in-domain and out-of-domain datasets. Experiments show improvements about (1.2 per cent) over standard RNN.