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.