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.

In the past few years, high-quality automated text-to-speech synthesis has effectively become a commodity, with easy access to cloud-based APIs provided by a number of major players. At the same time, developments in deep learning have broadened the scope of voice synthesis functionalities that can be delivered, leading to a growth in the range of commercially viable use cases. We take a look at the technology features and use cases that have attracted attention and investment in the past few years, identifying the major players and recent start-ups in the space.

We propose a novel approach for sentence boundary detection in text datasets in which boundaries are not evident (e.g., sentence fragments). Although detecting sentence boundaries without punctuation marks has rarely been explored in written text, current real-world textual data suffer from widespread lack of proper start/stop signaling. Herein, we annotate a dataset with linguistic information, such as parts of speech and named entity labels, to boost the sentence boundary detection task. Via experiments, we obtained F1 scores up to 98.07% using the proposed multitask neural model, including a score of 89.41% for sentences completely lacking punctuation marks. We also present an ablation study and provide a detailed analysis to demonstrate the effectiveness of the proposed multitask learning method.

Word embeddings have become important building blocks that are used profoundly in natural language processing (NLP). Despite their several advantages, word embeddings can unintentionally accommodate some gender- and ethnicity-based biases that are present within the corpora they are trained on. Therefore, ethical concerns have been raised since word embeddings are extensively used in several high-level algorithms. Studying such biases and debiasing them have recently become an important research endeavor. Various studies have been conducted to measure the extent of bias that word embeddings capture and to eradicate them. Concurrently, as another subfield that has started to gain traction recently, the applications of NLP in the field of law have started to increase and develop rapidly. As law has a direct and utmost effect on people’s lives, the issues of bias for NLP applications in legal domain are certainly important. However, to the best of our knowledge, bias issues have not yet been studied in the context of legal corpora. In this article, we approach the gender bias problem from the scope of legal text processing domain. Word embedding models that are trained on corpora composed by legal documents and legislation from different countries have been utilized to measure and eliminate gender bias in legal documents. Several methods have been employed to reveal the degree of gender bias and observe its variations over countries. Moreover, a debiasing method has been used to neutralize unwanted bias. The preservation of semantic coherence of the debiased vector space has also been demonstrated by using high-level tasks. Finally, overall results and their implications have been discussed in the scope of NLP in legal domain.

Arabic presents many challenges for automatic processing. Although several research studies have addressed some issues, electronic resources for processing Arabic remain relatively rare or not widely available. In this paper, we propose a Tree-adjoining grammar with a syntax-semantic interface. It is applied to the modern standard Arabic, but it can be easily adapted to other languages. This grammar named “ArabTAG V2.0” (Arabic Tree Adjoining Grammar) is semi-automatically generated by means of an abstract representation called meta-grammar. To ensure its development, ArabTAG V2.0 benefits from a grammar testing environment that uses a corpus of phenomena. Further experiments were performed to check the coverage of this grammar as well as the syntax-semantic analysis. The results showed that ArabTAG V2.0 can cover the majority of syntactical structures and different linguistic phenomena with a precision rate of 88.76%. Moreover, we were able to semantically analyze sentences and build their semantic representations with a precision rate of about 95.63%.

Named entities (NEs) are among the most relevant type of information that can be used to properly index digital documents and thus easily retrieve them. It has long been observed that NEs are key to accessing the contents of digital library portals as they are contained in most user queries. However, most digitized documents are indexed through their optical character recognition (OCRed) version which include numerous errors. Although OCR engines have considerably improved over the last few years, OCR errors still considerably impact document access. Previous works were conducted to evaluate the impact of OCR errors on named entity recognition (NER) and named entity linking (NEL) techniques separately. In this article, we experimented with a variety of OCRed documents with different levels and types of OCR noise to assess in depth the impact of OCR on named entity processing. We provide a deep analysis of OCR errors that impact the performance of NER and NEL. We then present the resulting exhaustive study and subsequent recommendations on the adequate documents, the OCR quality levels, and the post-OCR correction strategies required to perform reliable NER and NEL.

We present novel methods for detecting lexical entailment in a fully rule-based and explainable fashion, by automatic construction of semantic graphs, in any language for which a crowd-sourced dictionary with sufficient coverage and a dependency parser of sufficient accuracy are available. We experiment and evaluate on both the Semeval-2020 lexical entailment task (Glavaš et al. (2020). Proceedings of the Fourteenth Workshop on Semantic Evaluation, pp. 24–35) and the SherLIiC lexical inference dataset of typed predicates (Schmitt and Schütze (2019). Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 902–914). Combined with top-performing systems, our method achieves improvements over the previous state-of-the-art on both benchmarks. As a standalone system, it offers a fully interpretable model of lexical entailment that makes detailed error analysis possible, uncovering future directions for improving both the semantic parsing method and the inference process on semantic graphs. We release all components of our system as open source software.

This paper presents MHeTRep, a multilingual medical terminology and the methodology followed for its compilation. The multilingual terminology is organised into one vocabulary for each language. All the terms in the collection are semantically tagged with a tagset corresponding to the top categories of Snomed-CT ontology. When possible, the individual terms are linked to their equivalent in the other languages. Even though many NLP resources and tools claim to be domain independent, their application to specific tasks can be restricted to specific domains, otherwise their performance degrades notably. As the accuracy of NLP resources drops heavily when applied in environments different from which they were built, a tuning to the new environment is needed. Usually, having a domain terminology facilitates and accelerates the adaptation of general domain NLP applications to a new domain. This is particularly important in medicine, a domain living moments of great expansion. The proposed method takes Snomed-CT as starting point. From this point and using 13 multilingual resources, covering the most relevant medical concepts such as drugs, anatomy, clinical findings and procedures, we built a large resource covering seven languages totalling more than two million semantically tagged terms. The resulting collection has been intensively evaluated in several ways for the involved languages and domain categories. Our hypothesis is that MHeTRep can be used advantageously over the original resources for a number of NLP use cases and likely extended to other languages.

Deep learning approaches are superior in natural language processing due to their ability to extract informative features and patterns from languages. The two most successful neural architectures are LSTM and transformers, used in large pretrained language models such as BERT. While cross-lingual approaches are on the rise, most current natural language processing techniques are designed and applied to English, and less-resourced languages are lagging behind. In morphologically rich languages, information is conveyed through morphology, for example, through affixes modifying stems of words. The existing neural approaches do not explicitly use the information on word morphology. We analyse the effect of adding morphological features to LSTM and BERT models. As a testbed, we use three tasks available in many less-resourced languages: named entity recognition (NER), dependency parsing (DP) and comment filtering (CF). We construct baselines involving LSTM and BERT models, which we adjust by adding additional input in the form of part of speech (POS) tags and universal features. We compare the models across several languages from different language families. Our results suggest that adding morphological features has mixed effects depending on the quality of features and the task. The features improve the performance of LSTM-based models on the NER and DP tasks, while they do not benefit the performance on the CF task. For BERT-based models, the added morphological features only improve the performance on DP when they are of high quality (i.e., manually checked) while not showing any practical improvement when they are predicted. Even for high-quality features, the improvements are less pronounced in language-specific BERT variants compared to massively multilingual BERT models. As in NER and CF datasets manually checked features are not available, we only experiment with predicted features and find that they do not cause any practical improvement in performance.

In training deep learning networks, the optimizer and related learning rate are often used without much thought or with minimal tuning, even though it is crucial in ensuring a fast convergence to a good quality minimum of the loss function that can also generalize well on the test dataset. Drawing inspiration from the successful application of cyclical learning rate policy to computer vision tasks, we explore how cyclical learning rate can be applied to train transformer-based neural networks for neural machine translation. From our carefully designed experiments, we show that the choice of optimizers and the associated cyclical learning rate policy can have a significant impact on the performance. In addition, we establish guidelines when applying cyclical learning rates to neural machine translation tasks.

Many papers are chasing state-of-the-art (SOTA) numbers, and more will do so in the future. SOTA-chasing comes with many costs. SOTA-chasing squeezes out more promising opportunities such as coopetition and interdisciplinary collaboration. In addition, there is a risk that too much SOTA-chasing could lead to claims of superhuman performance, unrealistic expectations, and the next AI winter. Two root causes for SOTA-chasing will be discussed: (1) lack of leadership and (2) iffy reviewing processes. SOTA-chasing may be similar to the replication crisis in the scientific literature. The replication crisis is yet another example, like evaluation, of over-confidence in accepted practices and the scientific method, even when such practices lead to absurd consequences.

Many fundamental tasks in natural language processing (NLP) such as part-of-speech tagging, text chunking, and named-entity recognition can be formulated as sequence labeling problems. Although neural sequence labeling models have shown excellent results on standard test sets, they are very brittle when presented with misspelled texts. In this paper, we introduce an adversarial training framework that enhances the robustness against typographical adversarial examples. We evaluate the robustness of sequence labeling models with an adversarial evaluation scheme that includes typographical adversarial examples. We generate two types of adversarial examples without access (black-box) or with full access (white-box) to the target model’s parameters. We conducted a series of extensive experiments on three languages (English, Thai, and German) across three sequence labeling tasks. Experiments show that the proposed adversarial training framework provides better resistance against adversarial examples on all tasks. We found that we can further improve the model’s robustness on the chunking task by including a triplet loss constraint.

Text usually suffers from typos which can negatively affect various Information Retrieval and Natural Language Processing tasks. Although there is a wide variety of choices for tackling this issue in the English language, this is not the case for other languages. For the Greek language, most of the existing phonetic algorithms provide rather insufficient support. For this reason, in this paper, we introduce an algorithm for phonetic matching designed for the Greek language: we start from the original Soundex and we redesign and extend it for accommodating the Greek language’s phonetic rules, ending up to a family of algorithms, that we call ${\tt Soundex}_{GR}$. Then, we report various experimental results showcasing how the algorithm behaves in different scenarios, and we provide comparative results for various parameters of the algorithm for revealing the trade-off between precision and recall in datasets with different kinds of errors. We also provide comparative results with matching using stemming, full phonemic transcription, and edit distance, that demonstrate that ${\tt Soundex}_{GR}$ performs better (indicatively, it achieves F-Score over 95% in collections of similar-sounded words). The simplicity, efficiency, and effectiveness of the proposed algorithm make it applicable and adaptable to a wide range of tasks.

Previouswork in slogan generation focused on utilising slogan skeletons mined from existing slogans. While some generated slogans can be catchy, they are often not coherent with the company’s focus or style across their marketing communications because the skeletons are mined from other companies’ slogans. We propose a sequence-to-sequence (seq2seq) Transformer model to generate slogans from a brief company description. A naïve seq2seq model fine-tuned for slogan generation is prone to introducing false information. We use company name delexicalisation and entity masking to alleviate this problem and improve the generated slogans’ quality and truthfulness. Furthermore, we apply conditional training based on the first words’ part-of-speech tag to generate syntactically diverse slogans. Our best model achieved a ROUGE-1/-2/-L $\mathrm{F}_1$ score of 35.58/18.47/33.32. Besides, automatic and human evaluations indicate that our method generates significantly more factual, diverse and catchy slogans than strong long short-term memory and Transformer seq2seq baselines.

Large-scale transformer-based language models (LMs) demonstrate impressive capabilities in open-text generation. However, controlling the generated text’s properties such as the topic, style, and sentiment is challenging and often requires significant changes to the model architecture or retraining and fine-tuning the model on new supervised data. This paper presents a novel approach for topical language generation (TLG) by combining a pre-trained LM with topic modeling information. We cast the problem using Bayesian probability formulation with topic probabilities as a prior, LM probabilities as the likelihood, and TLG probability as the posterior. In learning the model, we derive the topic probability distribution from the user-provided document’s natural structure. Furthermore, we extend our model by introducing new parameters and functions to influence the quantity of the topical features presented in the generated text. This feature would allow us to easily control the topical properties of the generated text. Our experimental results demonstrate that our model outperforms the state-of-the-art results on coherency, diversity, and fluency while being faster in decoding.