Summarizing content contributed by individuals can be challenging, because people make different lexical choices even when describing the same events. However, there remains a significant need to summarize such content. Examples include the student responses to post-class reflective questions, product reviews, and news articles published by different news agencies related to the same events. High lexical diversity of these documents hinders the system’s ability to effectively identify salient content and reduce summary redundancy. In this paper, we overcome this issue by introducing an integer linear programming-based summarization framework. It incorporates a low-rank approximation to the sentence-word cooccurrence matrix to intrinsically group semantically similar lexical items. We conduct extensive experiments on datasets of student responses, product reviews, and news documents. Our approach compares favorably to a number of extractive baselines as well as a neural abstractive summarization system. The paper finally sheds light on when and why the proposed framework is effective at summarizing content with high lexical variety.

This work focuses on the rapid development of linguistic annotation tools for low-resource languages (languages that have no labeled training data). We experiment with several cross-lingual annotation projection methods using recurrent neural networks (RNN) models. The distinctive feature of our approach is that our multilingual word representation requires only a parallel corpus between source and target languages. More precisely, our approach has the following characteristics: (a) it does not use word alignment information, (b) it does not assume any knowledge about target languages (one requirement is that the two languages (source and target) are not too syntactically divergent), which makes it applicable to a wide range of low-resource languages, (c) it provides authentic multilingual taggers (one tagger for N languages). We investigate both uni and bidirectional RNN models and propose a method to include external information (for instance, low-level information from part-of-speech tags) in the RNN to train higher level taggers (for instance, Super Sense taggers). We demonstrate the validity and genericity of our model by using parallel corpora (obtained by manual or automatic translation). Our experiments are conducted to induce cross-lingual part-of-speech and Super Sense taggers. We also use our approach in a weakly supervised context, and it shows an excellent potential for very low-resource settings (less than 1k training utterances).

It seems like there’s yet another cloud-based text analytics Application Programming Interface (API) on the market every few weeks. If you’re interested in building an application using these kinds of services, how do you decide which API to go for? In the previous Industry Watch post, we looked at the text analytics APIs from the behemoths in the cloud software world: Amazon, Google, IBM and Microsoft. In this post, we survey sixteen APIs offered by smaller players in the market.

This work proposes a sequential tagger for named entity recognition in morphologically rich languages. Several schemes for representing the morphological analysis of a word in the context of named entity recognition are examined. Word representations are formed by concatenating word and character embeddings with the morphological embeddings based on these schemes. The impact of these representations is measured by training and evaluating a sequential tagger composed of a conditional random field layer on top of a bidirectional long short-term memory layer. Experiments with Turkish, Czech, Hungarian, Finnish and Spanish produce the state-of-the-art results for all these languages, indicating that the representation of morphological information improves performance.

The extraction of templates such as ‘regard X as Y’ from a set of related phrases requires the identification of their internal structures. This paper presents an unsupervised approach for extracting templates on-the-fly from only tagged text by using a novel relaxed variant of the Sequence Binary Decision Diagram (SeqBDD). A SeqBDD can compress a set of sequences into a graphical structure equivalent to a minimal deterministic finite state automata, but more compact and better suited to the task of template extraction. The main contribution of this paper is a relaxed form of the SeqBDD construction algorithm that enables it to form general representations from a small amount of data. The process of compression of shared structures in the text during Relaxed SeqBDD construction, naturally induces the templates we wish to extract. Experiments show that the method is capable of high-quality extraction on tasks based on verb+preposition templates from corpora and phrasal templates from short messages from social media.

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.

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.

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.

It is amazing that I have written for more than a year on Emerging Trends without mentioning China’s investments in Artificial Intelligence (AI). Now that I have moved to Baidu, I would like to take this opportunity to share some of my personal observations with what’s happening in China over the past 25 years. The top universities in China have always been very good, but they are better today than they were 25 years ago, and they are on a trajectory to become the biggest and the best in the world. China is investing big time in what we do, both in the private sector and the public sector. Kai-Fu Lee is bullish on his investments in AI and China. There is a bold government plan for AI with specific milestones for parity with the West in 2020, major breakthroughs by 2025 and the envy of the world by 2030.

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.

When a recurrent neural network (RNN) language model is used for caption generation, the image information can be fed to the neural network either by directly incorporating it in the RNN – conditioning the language model by ‘injecting’ image features – or in a layer following the RNN – conditioning the language model by ‘merging’ image features. While both options are attested in the literature, there is as yet no systematic comparison between the two. In this paper, we empirically show that it is not especially detrimental to performance whether one architecture is used or another. The merge architecture does have practical advantages, as conditioning by merging allows the RNN’s hidden state vector to shrink in size by up to four times. Our results suggest that the visual and linguistic modalities for caption generation need not be jointly encoded by the RNN as that yields large, memory-intensive models with few tangible advantages in performance; rather, the multimodal integration should be delayed to a subsequent stage.

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).

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.