Warning: This paper is based on hate speech detection and may contain examples of abusive/ offensive phrases.

Cyberbullying, online harassment, etc., via offensive comments are pervasive across different social media platforms like ™Twitter, ™Facebook, ™YouTube, etc. Hateful comments must be detected and eradicated to prevent harassment and violence on social media. In the Natural Language Processing (NLP) domain, the most prevalent task is comment classification, which is challenging, and language models based on transformers are at the forefront of this advancement. This paper intends to analyze the performance of language models based on transformers like BERT, ALBERT, RoBERTa, and DistilBERT on the Indian hate speech datasets over binary classification. Here, we utilize the existing datasets, i.e., HASOC (Hindi and Marathi) and HS-Bangla. So, we evaluate several multilingual language models like MuRIL-BERT, XLM-RoBERTa, etc., few monolingual language models like RoBERTa-Hindi, Maha-BERT (Marathi), Bangla-BERT (Bangla), Assamese-BERT (Assamese), etc., and perform cross-lingual experiment also. For further analyses, we perform multilingual, monolingual, and cross-lingual experiments on our Hate Speech Assamese (HS-Assamese) (Indo-Aryan language family) and Hate Speech Bodo (HS-Bodo) (Sino-Tibetan language family) dataset (HS dataset version 2) also and achieved a promising result. The motivation of the cross-lingual experiment is to encourage researchers to learn about the power of the transformer. Note that no pre-trained language models are currently available for Bodo or any other Sino-Tibetan languages.

Disorder named entity recognition (DNER) is a fundamental task of biomedical natural language processing, which has attracted plenty of attention. This task consists in extracting named entities of disorders such as diseases, symptoms, and pathological functions from unstructured text. The European Clinical Case Corpus (E3C) is a freely available multilingual corpus (English, French, Italian, Spanish, and Basque) of semantically annotated clinical case texts. The entities of type disorder in the clinical cases are annotated at both mention and concept level. At mention -level, the annotation identifies the entity text spans, for example, abdominal pain. At concept level, the entity text spans are associated with their concept identifiers in Unified Medical Language System, for example, C0000737. This corpus can be exploited as a benchmark for training and assessing information extraction systems. Within the context of the present work, multiple experiments have been conducted in order to test the appropriateness of the mention-level annotation of the E3C corpus for training DNER models. In these experiments, traditional machine learning models like conditional random fields and more recent multilingual pre-trained models based on deep learning were compared with standard baselines. With regard to the multilingual pre-trained models, they were fine-tuned (i) on each language of the corpus to test per-language performance, (ii) on all languages to test multilingual learning, and (iii) on all languages except the target language to test cross-lingual transfer learning. Results show the appropriateness of the E3C corpus for training a system capable of mining disorder entities from clinical case texts. Researchers can use these results as the baselines for this corpus to compare their own models. The implemented models have been made available through the European Language Grid platform for quick and easy access.

Linguistic synesthesia as a productive figurative language usage has received little attention in the field of Natural Language Processing (NLP). Although linguistic synesthesia is similar to metaphor concerning involving conceptual mappings and showing great usefulness in the NLP tasks such as sentiment analysis and stance detection, the well-studied methods of metaphor detection cannot be applied to the detection of linguistic synesthesia directly. This study incorporates comprehensive linguistic features (i.e., character and radical information, word segmentation information, and part-of-speech tagging) into a neural model to detect linguistic synesthetic usages in a sentence automatically. In particular, we employ a span-based boundary detection model to extract sensory words. In addition, a joint model is proposed to detect the original and synesthetic modalities of the sensory words collectively. Based on the experiments, our model is shown to achieve state-of-the-art results on the dataset for linguistic synesthesia detection. The results prove that leveraging culturally enriched linguistic features and joint learning are effective in linguistic synesthesia detection. Furthermore, as the proposed model leverages non-language-specific linguistic features, the model would be applied to the detection of linguistic synesthesia in other languages.

Although Korean language education is experiencing rapid growth in recent years and several studies have investigated automated writing evaluation (AWE) systems, AWE for Korean L2 writing still remains unexplored. Therefore, this study aims to develop and validate a state-of-the-art neural model AWE system which can be widely used for Korean language teaching and learning. Based on a Korean learner corpus, the proposed AWE is developed using natural language processing techniques such as part-of-speech tagging, syntactic parsing, and statistical language modeling to engineer linguistic features and a pre-trained neural language model. This study attempted to determine how neural network models use different linguistic features to improve AWE performance. Experimental results of the proposed AWE tool showed that the neural AWE system achieves high reliability for unseen test data from the corpus, which implies metrics used in the AWE system can help differentiate different proficiency levels and predict holistic scores. Furthermore, the results confirmed that the proposed linguistic features–syntactic complexity, quantitative complexity, and fluency–offer benefits that complement neural automated writing evaluation.

This paper presents a scheme that allows one to relax the all-or-none nature of two-level constraints in two-level morphology in a controlled manner, so that word forms with violations of some of the two-level constraints can be analyzed and ranked. The problem has been motivated by a recent phenomenon in Turkish with imported words that violate a fundamental assumption of Turkish that pronunciation and orthography have almost a one-to-one correspondence, and by a problem in Basque words with differing amounts of competence errors. We present the formulation of our proposal, and provide details of implementations for both problems using the XRCE Finite State Toolkit.

An important problem in knowledge discovery from text is the automatic extraction of semantic relations. This paper addresses the automatic classification of the semantic relations expressed by English genitives. A learning model is introduced based on the statistical analysis of the distribution of genitives' semantic relations in a corpus. The semantic and contextual features of the genitive's noun phrase constituents play a key role in the identification of the semantic relation. The algorithm was trained and tested on a corpus of approximately 20,000 sentences and achieved an f-measure of 79.80 per cent for of-genitives, far better than the 40.60 per cent obtained using a Decision Trees algorithm, the 50.55 per cent obtained using a Naive Bayes algorithm, or the 72.13 per cent obtained using a Support Vector Machines algorithm on the same corpus using the same features. The results were similar for s-genitives: 78.45 per cent using Semantic Scattering, 47.00 per cent using Decision Trees, 43.70 per cent using Naive Bayes, and 70.32 per cent using a Support Vector Machines algorithm. The results demonstrate the importance of word sense disambiguation and semantic generalization/specialization for this task. They also demonstrate that different patterns (in our case the two types of genitive constructions) encode different semantic information and should be treated differently in the sense that different models should be built for different patterns.

Sarcasm detection research in the Bengali language so far can be considered to be narrow due to the unavailability of resources. In this paper, we introduce a large-scale self-annotated Bengali corpus for sarcasm detection research problem in the Bengali language named ‘Ben-Sarc’ containing 25,636 comments, manually collected from different public Facebook pages and evaluated by external evaluators. Then we present a complete strategy to utilize different models of traditional machine learning, deep learning, and transfer learning to detect sarcasm from text using the Ben-Sarc corpus. Finally, we demonstrate a comparison between the performance of traditional machine learning, deep learning, and transfer learning models on our Ben-Sarc corpus. Transfer learning using Indic-Transformers Bengali Bidirectional Encoder Representations from Transformers as a pre-trained source model has achieved the highest accuracy of 75.05%. The second-highest accuracy is obtained by the long short-term memory model with 72.48% and Multinomial Naive Bayes is acquired the third highest with 72.36% accuracy for deep learning and machine learning, respectively. The Ben-Sarc corpus is made publicly available in the hope of advancing the Bengali Natural Language Processing Community. The Ben-Sarc is available at https://github.com/sanzanalora/Ben-Sarc.

A competitive and cost-effective public procurement (PP) process is essential for the effective use of public resources. In this work, we explore whether descriptions of procurement calls can be used to predict their outcomes. In particular, we focus on predicting four well-known economic metrics: (i) the number of offers, (ii) whether only a single offer is received, (iii) whether a foreign firm is awarded the contract, and (iv) whether the contract price exceeds the expected price. We extract the European Union’s multilingual PP notices, covering 22 different languages. We investigate fine-tuning multilingual transformer models and propose two approaches: (1) multilayer perceptron (MLP) models with transformer embeddings for each business sector in which the training data are filtered based on the procurement category and (2) a k-nearest neighbor (KNN)-based approach fine-tuned using triplet networks. The fine-tuned MBERT model outperforms all other models in predicting calls with a single offer and foreign contract awards, whereas our MLP-based filtering approach yields state-of-the-art results in predicting contracts in which the contract price exceeds the expected price. Furthermore, our KNN-based approach outperforms all the baselines in all tasks and our other proposed models in predicting the number of offers. Moreover, we investigate cross-lingual and multilingual training for our tasks and observe that multilingual training improves prediction accuracy in all our tasks. Overall, our experiments suggest that notice descriptions play an important role in the outcomes of PP calls.

There are well-meaning efforts to address ethics that will likely make the world a better place, but care needs to be taken to avoid repeating mistakes of the past. In particular, ACL has recently introduced a new process where there are special reviews of some papers for ethics. We would be more comfortable with the new ethics process if there were more checks and balances, due process and transparency. Otherwise, there is a risk that the process could intimidate authors in ways that are not that dissimilar from the ways that academics were intimidated during the Cold War on both sides of the Iron Curtain.

Recent years have seen a growing number of publications that analyse Natural Language Understanding (NLU) datasets for superficial cues, whether they undermine the complexity of the tasks underlying those datasets and how they impact those models that are optimised and evaluated on this data. This structured survey provides an overview of the evolving research area by categorising reported weaknesses in models and datasets and the methods proposed to reveal and alleviate those weaknesses for the English language. We summarise and discuss the findings and conclude with a set of recommendations for possible future research directions. We hope that it will be a useful resource for researchers who propose new datasets to assess the suitability and quality of their data to evaluate various phenomena of interest, as well as those who propose novel NLU approaches, to further understand the implications of their improvements with respect to their model’s acquired capabilities.

Inside parsing is a best parse parsing method based on the Inside algorithm that is often used in estimating probabilistic parameters of stochastic context free grammars. It gives a best parse in O(N3G3) time where N is the input size and G is the grammar size. Earley algorithm can be made to return best parses with the same complexity in N.

By way of experiments, we show that Inside parsing can be more efficient than Earley parsing with sufficiently large grammar and sufficiently short input sentences. For instance, Inside parsing is better with sentences of 16 or less words for a grammar containing 429 states. In practice, parsing can be made efficient by employing the two methods selectively.

The redundancy of Inside algorithm can be reduced by the topdown filtering using the chart produced by Earley algorithm, which is useful in training the probabilistic parameters of a grammar. Extensive experiments on Penn Tree corpus show that the efficiency of Inside computation can be improved by up to 55%.

Convolutional sequence to sequence (CNN seq2seq) models have met success in abstractive summarization. However, their outputs often contain repetitive word sequences and logical inconsistencies, limiting the practicality of their application. In this paper, we find the reasons behind the repetition problem in CNN-based abstractive summarization through observing the attention map between the summaries with repetition and their corresponding source documents and mitigate the repetition problem. We propose to reduce the repetition in summaries by attention filter mechanism (ATTF) and sentence-level backtracking decoder (SBD), which dynamically redistributes attention over the input sequence as the output sentences are generated. The ATTF can record previously attended locations in the source document directly and prevent the decoder from attending to these locations. The SBD prevents the decoder from generating similar sentences more than once via backtracking at test. The proposed model outperforms the baselines in terms of ROUGE score, repeatedness, and readability. The results show that this approach generates high-quality summaries with minimal repetition and makes the reading experience better.

In this study, we investigate using unsupervised generative learning methods for subjectivity detection across different domains. We create an initial training set using simple lexicon information and then evaluate two iterative learning methods with a base naive Bayes classifier to learn from unannotated data. The first method is self-training, which adds instances with high confidence into the training set in each iteration. The second is a calibrated EM (expectation-maximization) method where we calibrate the posterior probabilities from EM such that the class distribution is similar to that in the real data. We evaluate both approaches on three different domains: movie data, news resource, and meeting dialogues, and we found that in some cases the unsupervised learning methods can achieve performance close to the fully supervised setup. We perform a thorough analysis to examine factors, such as self-labeling accuracy of the initial training set in unsupervised learning, the accuracy of the added examples in self-training, and the size of the initial training set in different methods. Our experiments and analysis show inherent differences across domains and impacting factors explaining the model behaviors.

Problems in the area of text and document processing can often be described as text rewriting tasks: given an input text, produce a new text by applying some fixed set of rewriting rules. In its simplest form, a rewriting rule is given by a pair of strings, representing a source string (the “original”) and its substitute. By a rewriting dictionary, we mean a finite list of such pairs; dictionary-based text rewriting means to replace in an input text occurrences of originals by their substitutes. We present an efficient method for constructing, given a rewriting dictionary D, a subsequential transducer that accepts any text t as input and outputs the intended rewriting result under the so-called “leftmost-longest match” replacement with skips, t'. The time needed to compute the transducer is linear in the size of the input dictionary. Given the transducer, any text t of length |t| is rewritten in a deterministic manner in time O(|t|+|t'|), where t' denotes the resulting output text. Hence the resulting rewriting mechanism is very efficient. As a second advantage, using standard tools, the transducer can be directly composed with other transducers to efficiently solve more complex rewriting tasks in a single processing step.

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.

Determining whether two terms have an ancestor relation (e.g. Toyota Camry and car) or a sibling relation (e.g. Toyota and Honda) is an essential component of textual inference in Natural Language Processing applications such as Question Answering, Summarization, and Textual Entailment. Significant work has been done on developing knowledge sources that could support these tasks, but these resources usually suffer from low coverage, noise, and are inflexible when dealing with ambiguous and general terms that may not appear in any stationary resource, making their use as general purpose background knowledge resources difficult. In this paper, rather than building a hierarchical structure of concepts and relations, we describe an algorithmic approach that, given two terms, determines the taxonomic relation between them using a machine learning-based approach that makes use of existing resources. Moreover, we develop a global constraint-based inference process that leverages an existing knowledge base to enforce relational constraints among terms and thus improves the classifier predictions. Our experimental evaluation shows that our approach significantly outperforms other systems built upon the existing well-known knowledge sources.

One of the key issues in spoken-language translation is how to deal with unrestricted expressions in spontaneous utterances. We have developed a paraphraser for use as part of a translation system, and in this paper we describe the implementation of a Chinese paraphraser for a Chinese-Japanese spoken-language translation system. When an input sentence cannot be translated by the transfer engine, the paraphraser automatically transforms the sentence into alternative expressions until one of these alternatives can be translated by the transfer engine. Two primary issues must be dealt with in paraphrasing: how to determine new expressions, and how to retain the meaning of the input sentence. We use a pattern-based approach in which the meaning is retained to the greatest possible extent without deep parsing. The paraphrase patterns are acquired from a paraphrase corpus and human experience. The paraphrase instances are automatically extracted and then generalized into paraphrase patterns. A total of 1719 paraphrase patterns obtained using this method and an implemented paraphraser were used in a paraphrasing experiment. The results showed that the implemented paraphraser generated 1.7 paraphrases on average for each test sentence and achieved an accuracy of 88%.

Extraction keyphrase systems traditionally use classification algorithms and do not consider the fact that part of the keyphrases may not be found in the text, reducing the accuracy of such algorithms a priori. In this work, we propose to improve the accuracy of these systems with inferential mechanisms that use a knowledge representation model, including symbolic models of knowledge bases and distributional semantics, to expand the set of keyphrase candidates to be submitted to the classification algorithm with terms that are not in the text (not-in-text terms). The basic assumption we have is that not-in-text terms have a semantic relationship with terms that are in the text. To represent this relationship, we have defined two new features to be represented as input to the classification algorithms. The first feature refers to the power of discrimination of the inferred not-in-text terms. The intuition behind this is that good candidates for a keyphrase are those that are deduced from various textual terms in a specific document and that are not often deduced in other documents. The other feature represents the descriptive strength of a not-in-text candidate. We argue that not-in-text keyphrases must have a strong semantic relationship with the text and that the power of this semantic relationship can be measured in a similar way as popular metrics like TFxIDF. The method proposed in this work was compared with state-of-the-art systems using five corpora and the results show that it has significantly improved automatic keyphrase extraction, dealing with the limitation of extracting keyphrases absent from the text.