Keyphrases are the most important phrases of documents that make them suitable for improving natural language processing tasks, including information retrieval, document classification, document visualization, summarization and categorization. Here, we propose a supervised framework augmented by novel extra-textual information derived primarily from Wikipedia. Wikipedia is utilized in such an advantageous way that – unlike most other methods relying on Wikipedia – a full textual index of all the Wikipedia articles is not required by our approach, as we only exploit the category hierarchy and a list of multiword expressions derived from Wikipedia. This approach is not only less resource intensive, but also produces comparable or superior results compared to previous similar works. Our thorough evaluations also suggest that the proposed framework performs consistently well on multiple datasets, being competitive or even outperforming the results obtained by other state-of-the-art methods. Besides introducing features that incorporate extra-textual information, we also experimented with a novel way of representing features that are derived from the POS tagging of the keyphrase candidates.

This paper evaluates four of the most commonly used, freely available, state-of-the-art parsers on a standard benchmark as well as with respect to a set of data relevant for measuring text cohesion, as one example of a learning technology application that requires fast and accurate syntactic parsing. We outline advantages and disadvantages of existing technologies and make recommendations. Our performance report uses traditional measures based on a gold standard as well as novel dimensions for parsing evaluation. To our knowledge, this is the first attempt to evaluate parsers across genres and grade levels for the implementation in learning technology using both gold standard and directed evaluation methods.

Evaluating interactive question answering (QA) systems with real users can be challenging because traditional evaluation measures based on the relevance of items returned are difficult to employ since relevance judgments can be unstable in multi-user evaluations. The work reported in this paper evaluates, in distinguishing among a set of interactive QA systems, the effectiveness of three questionnaires: a Cognitive Workload Questionnaire (NASA TLX), and Task and System Questionnaires customized to a specific interactive QA application. These Questionnaires were evaluated with four systems, seven analysts, and eight scenarios during a 2-week workshop. Overall, results demonstrate that all three Questionnaires are effective at distinguishing among systems, with the Task Questionnaire being the most sensitive. Results also provide initial support for the validity and reliability of the Questionnaires.

The answer determines the success of a Question-Answering (QA) system. In redundancy-based QA systems, a common approach is to extract the candidate answers from the information sources and select the most frequent answers as the final answers. However, this strategy has some pitfalls. For instance, if a system is not able to detect equivalences between the candidate answers, their frequencies might be erroneously calculated. Moreover, the user who posed the question should also be taken into account when answering: different persons require different (correct) answers. This can involve the use of suitable vocabulary and/or information details. In these situations, the generation of a response can be a more suitable strategy, instead of the extraction and direct retrieval of the answer from the information sources. The present survey targets the state of the art in the answering task in QA under three different lines of research. First, we present several works that focus on relating candidate answers. Then, we recover the concept of cooperative answer – a correct, useful, and non-misleading answer – and we bring up attempts to address cooperative answering. Finally, we investigate the research community endeavors on response generation. We will also present our perspective on each of these three topics throughout this paper.

This article evaluates the efficiency of the LiLFeS abstract machine by performing parsing tasks with the LinGO English resource grammar. The instruction set of the abstract machine is optimized for efficient processing of definite clause programs and typed feature structures. LiLFeS also supports various tools required for efficient parsing (e.g. efficient copying, a built-in CFG parser) and the constructions of standard Prolog (e.g. cut, assertions, negation as failure). Several parsers and large-scale grammars, including the LinGO grammar, have been implemented in or ported to LiLFeS. Precise empirical results with the LinGO grammar are provided to allow comparison with other systems. The experimental results demonstrate the efficiency of the LiLFeS abstract machine.

Moderators often face a double challenge regarding reducing offensive and harmful content in social media. Despite the need to prevent the free circulation of such content, strict censorship on social media cannot be implemented due to a tricky dilemma – preserving free speech on the Internet while limiting them and how not to overreact. Existing systems do not essentially exploit the correlatedness of hate-offensive content and aggressive posts; instead, they attend to the tasks individually. As a result, the need for cost-effective, sophisticated multi-task systems to effectively detect aggressive and offensive content on social media is highly critical in recent times. This work presents a novel multifaceted transformer-based framework to identify aggressive and hate posts on social media. Through an end-to-end transformer-based multi-task network, our proposed approach addresses the following array of tasks: (a) aggression identification, (b) misogynistic aggression identification, (c) identifying hate-offensive and non-hate-offensive content, (d) identifying hate, profane, and offensive posts, (e) type of offense. We further investigate the role of emotion in improving the system’s overall performance by learning the task of emotion detection jointly with the other tasks. We evaluate our approach on two popular benchmark datasets of aggression and hate speech, covering four languages, and compare the system performance with various state-of-the-art methods. Results indicate that our multi-task system performs significantly well for all the tasks across multiple languages, outperforming several benchmark methods. Moreover, the secondary task of emotion detection substantially improves the system performance for all the tasks, indicating strong correlatedness among the tasks of aggression, hate, and emotion, thus opening avenues for future research.

If you’re in the market for an off-the-shelf text analytics API, you have a lot of options. You can choose to go with a major player in the software world, for whom each AI-related service is just another entry in their vast catalogues of tools, or you can go for a smaller provider that focusses on text analytics as their core business. In this first of two related posts, we look at what the most prominent software giants have to offer today.

Nowadays, there is an increasing amount of digital data. In the case of the Web, daily, a vast collection of data is generated, whose contents are heterogeneous. A significant portion of this data is available in a natural language format. Open Information Extraction (Open IE) enables the extraction of facts from large quantities of texts written in natural language. In this work, we propose an Open IE method to extract facts from texts written in Portuguese. We developed two new rules that generalize the inference by transitivity and by symmetry. Consequently, this approach increases the number of implicit facts in a sentence. Our novel symmetric inference approach is based on a list of symmetric features. Our results confirmed that our method outstands close works both in precision and number of valid extractions. Considering the number of minimal facts, our approach is equivalent to the most relevant methods in the literature.

Building natural language spoken dialogue systems requires large amounts of human transcribed and labeled speech utterances to reach useful operational service performances. Furthermore, the design of such complex systems consists of several manual steps. The User Experience (UE) expert analyzes and defines by hand the system core functionalities: the system semantic scope (call-types) and the dialogue manager strategy that will drive the human–machine interaction. This approach is extensive and error-prone since it involves several nontrivial design decisions that can be evaluated only after the actual system deployment. Moreover, scalability is compromised by time, costs, and the high level of UE know-how needed to reach a consistent design. We propose a novel approach for bootstrapping spoken dialogue systems based on the reuse of existing transcribed and labeled data, common reusable dialogue templates, generic language and understanding models, and a consistent design process. We demonstrate that our approach reduces design and development time while providing an effective system without any application-specific data.

We address the problem of unsupervised and semi-supervised SMS (Short Message Service) text message SPAM detection. We develop a content-based Bayesian classification approach which is a modest extension of the technique discussed by Resnik and Hardisty in 2010. The approach assumes that the bodies of the SMS messages arise from a probabilistic generative model and estimates the model parameters by Gibbs sampling using an unlabeled, or partially labeled, SMS training message corpus. The approach classifies new SMS messages as SPAM or HAM (non-SPAM) by zero-thresholding their logit estimates. We tested the approach on a publicly available SMS corpora collected from the UK. Used in semi-supervised fashion, the approach clearly outperformed a competing algorithm, Semi-Boost. Used in unsupervised fashion, the approach outperformed a fully supervised classifier, an SVM (Support Vector Machine), when the number of training messages used by the SVM was small and performed comparably otherwise. We believe the approach works well and is a useful tool for SMS SPAM detection.

Anti-Asian speech during the COVID-19 pandemic has been a serious problem with severe consequences. A hate speech wave swept social media platforms. The timely detection of Anti-Asian COVID-19-related hate speech is of utmost importance, not only to allow the application of preventive mechanisms but also to anticipate and possibly prevent other similar discriminatory situations. In this paper, we address the problem of detecting Anti-Asian COVID-19-related hate speech from social media data. Previous approaches that tackled this problem used a transformer-based model, BERT/RoBERTa, trained on the homologous annotated dataset and achieved good performance on this task. However, this requires extensive and annotated datasets with a strong connection to the topic. Both goals are difficult to meet without employing reliable, vast, and costly resources. In this paper, we propose a robust semi-supervised model, SSL-GAN-RoBERTa, that learns from a limited heterogeneous dataset and whose performance is further enhanced by using vast amounts of unlabeled data from another related domain. Compared with the RoBERTa baseline model, the experimental results show that the model has substantial performance gains in terms of Accuracy and Macro-F1 score in different scenarios that use data from different domains. Our proposed model achieves state-of-the-art performance results while efficiently using unlabeled data, showing promising applicability to other complex classification tasks where large amounts of labeled examples are difficult to obtain.

This article presents an HPSG parser using a technique called CFG filtering. The parser predicts possible parse trees using a CFG generated automatically from a given HPSG-based grammar. Parsing costs are reduced because unification is applied only to the predicted parse trees. In other words, parsing is speeded up because the parser avoids unnecessary unification by eliminating impossible parse trees. We show the method for generating a CFG from an HPSG-based grammar and outline a parsing scheme using the CFG. The effectiveness of the parsing scheme is shown through experimental results obtained by using several HPSG-based grammars, including the LinGO grammar.

Word-level language identification is an essential prerequisite for extracting useful information from code-mixed social media content. Previous studies in word-level language identification show two important observations. First, the local context is an important indicator of the language of a word when a word is valid in multiple languages. Second, considering the word in isolation from its context leads to more effective language classification when a word is borrowed or embedded into sentences of other languages. In this paper, we propose a framework for language identification that makes use of a dynamic switching mechanism for effective language classification of both words that are borrowed or embedded from other languages as well as words that are valid in multiple languages. For a given input, the proposed switching mechanism makes a dynamic decision to bias its prediction either towards the prediction obtained by the contextual information or that obtained by the word in isolation. In contrast to existing studies that rely upon large amounts of annotated data for robust performance in a multilingual environment, the proposed approach uses minimal annotated resources and no external resources, making it easily extendible to newer languages. Evaluation over a corpus of transliterated Facebook comments shows that the proposed approach outperforms its baseline counterparts: classification based on the contextual information, classification based on the word in isolation, as well as an ensemble of the two classifiers.

We describe and evaluate a text-to-pictograph translation system that is used in an online platform for Augmentative and Alternative Communication, which is intended for people who are not able to read and write, but who still want to communicate with the outside world. The system is set up to translate from Dutch into Sclera and Beta, two publicly available pictograph sets consisting of several thousands of pictographs each. We have linked large amounts of these pictographs to synsets or combinations of synsets of Cornetto, a lexical-semantic database for Dutch similar to WordNet. In the translation system, the Dutch input text undergoes shallow linguistic analysis and the synsets of the content words are looked up. The system looks for the nearest pictographs in the lexical-semantic database and displays the message into pictographs. We evaluated the system and results showed a large improvement over the baseline system which consisted of straightforward string-matching between the input text and the filenames of the pictographs.

Our system provides a clear improvement in the communication possibilities of illiterate people. Nevertheless there is room for further improvement.

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.

Vastly improved speech recognition, backed by a more slowly improving ability to make sense of the recognized speech, has brought state-of-the-art NLP into our homes in the form of smart speakers and other devices that listen. There’s no doubt these devices can be incredibly useful, but they also may also support incursions into our privacy. We look at where we are today, consider what might be coming, and express just a tad of caution.

This paper presents a novel neural architecture capable of outperforming state-of-the-art systems on the task of language variety classification. The architecture is a hybrid that combines character-based convolutional neural network (CNN) features with weighted bag-of-n-grams (BON) features and is therefore capable of leveraging both character-level and document/corpus-level information. We tested the system on the Discriminating between Similar Languages (DSL) language variety benchmark data set from the VarDial 2017 DSL shared task, which contains data from six different language groups, as well as on two smaller data sets (the Arabic Dialect Identification (ADI) Corpus and the German Dialect Identification (GDI) Corpus, from the VarDial 2016 ADI and VarDial 2018 GDI shared tasks, respectively). We managed to outperform the winning system in the DSL shared task by a margin of about 0.4 percentage points and the winning system in the ADI shared task by a margin of about 0.2 percentage points in terms of weighted F1 score without conducting any language group-specific parameter tweaking. An ablation study suggests that weighted BON features contribute more to the overall performance of the system than the CNN-based features, which partially explains the uncompetitiveness of deep learning approaches in the past VarDial DSL shared tasks. Finally, we have implemented our system in a workflow, available in the ClowdFlows platform, in order to make it easily available also to the non-programming members of the research community.

Translations are generally assumed to share universal features that distinguish them from texts that are originally written in the same language. Thus, we can argue that these translations constitute their own variety of a language, often called translationese. However, translations are also influenced by their source languages and thus show different characteristics depending on the source language. Consequently, we argue that these variants constitute different “dialects” of translations into the same target language. Studies using machine learning techniques on Indo-European languages have investigated the universal characteristics of translationese and how translations from various source languages differ. However, for typologically very different languages such as Chinese, there are only few corpus studies that tap into the intricate relation between translations and the originals, as well as into the relations among translations themselves. In this contribution, we investigate the following questions: (1) What are the characteristics of Chinese translationese, both in general and with respect to different source languages? (2) Can we find differences not only at the lexical but also on the syntactic level? and (3) Based on the characteristics found in the previous questions, which of the proposed laws and universals can we corroborate based on our evidence from Chinese? We use machine learning to operationalize determining the importance of different characteristics and comparing their importance for our Chinese dataset with characteristics previously reported in studies on English. In addition, our methodology allows us to add syntactic features, which have rarely been used to study translations into Chinese. Our results show that Chinese translations as a whole can be reliably distinguished from non-translations, even based on only five features. More interestingly, typological traces from the source languages can often be found in their translations, therefore creating what we call dialects of translationese. For instance, translations from two Altaic languages exhibit more noun repetition and less frequent use of pronouns. Additionally, some characteristics that are not discriminative for English work well for Chinese, possibly because the distance between Chinese and the source languages is greater than that in English studies.

Ten years ago, Microsoft Word's grammar checker was really the only game in town. The software world, and the world of natural language processing, have changed a lot in that time, so what does the grammar checker marketplace have to offer today?

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.