Foteini Liwicki

Tosin Adewumi, Foteini Liwicki, Marcus Liwicki

We survey SoTA open-domain conversational AI models with the purpose of presenting the prevailing challenges that still exist to spur future research. In addition, we provide statistics on the gender of conversational AI in order to guide the ethics discussion surrounding the issue. Open-domain conversational AI are known to have several challenges, including bland responses and performance degradation when prompted with figurative language, among others. First, we provide some background by discussing some topics of interest in conversational AI. We then discuss the method applied to the two investigations carried out that make up this study. The first investigation involves a search for recent SoTA open-domain conversational AI models while the second involves the search for 100 conversational AI to assess their gender. Results of the survey show that progress has been made with recent SoTA conversational AI, but there are still persistent challenges that need to be solved, and the female gender is more common than the male for conversational AI. One main take-away is that hybrid models of conversational AI offer more advantages than any single architecture. The key contributions of this survey are 1) the identification of prevailing challenges in SoTA open-domain conversational AI, 2) the unusual discussion about open-domain conversational AI for low-resource languages, and 3) the discussion about the ethics surrounding the gender of conversational AI.

Tosin Adewumi, Sana Sabah Sabry, Nosheen Abid et al.

We conduct relatively extensive investigations of automatic hate speech (HS) detection using different state-of-the-art (SoTA) baselines over 11 subtasks of 6 different datasets. Our motivation is to determine which of the recent SoTA models is best for automatic hate speech detection and what advantage methods like data augmentation and ensemble may have on the best model, if any. We carry out 6 cross-task investigations. We achieve new SoTA on two subtasks - macro F1 scores of 91.73% and 53.21% for subtasks A and B of the HASOC 2020 dataset, where previous SoTA are 51.52% and 26.52%, respectively. We achieve near-SoTA on two others - macro F1 scores of 81.66% for subtask A of the OLID 2019 dataset and 82.54% for subtask A of the HASOC 2021 dataset, where SoTA are 82.9% and 83.05%, respectively. We perform error analysis and use two explainable artificial intelligence (XAI) algorithms (IG and SHAP) to reveal how two of the models (Bi-LSTM and T5) make the predictions they do by using examples. Other contributions of this work are 1) the introduction of a simple, novel mechanism for correcting out-of-class (OOC) predictions in T5, 2) a detailed description of the data augmentation methods, 3) the revelation of the poor data annotations in the HASOC 2021 dataset by using several examples and XAI (buttressing the need for better quality control), and 4) the public release of our model checkpoints and codes to foster transparency.

Tosin Adewumi, Foteini Liwicki, Marcus Liwicki

We demonstrate, in this study, that an open-domain conversational system trained on idioms or figurative language generates more fitting responses to prompts containing idioms. Idioms are part of everyday speech in many languages, across many cultures, but they pose a great challenge for many Natural Language Processing (NLP) systems that involve tasks such as Information Retrieval (IR) and Machine Translation (MT), besides conversational AI. We utilize the Potential Idiomatic Expression (PIE)-English idioms corpus for the two tasks that we investigate: classification and conversation generation. We achieve state-of-the-art (SoTA) result of 98% macro F1 score on the classification task by using the SoTA T5 model. We experiment with three instances of the SoTA dialogue model, Dialogue Generative Pre-trained Transformer (DialoGPT), for conversation generation. Their performances are evaluated using the automatic metric perplexity and human evaluation. The results show that the model trained on the idiom corpus generates more fitting responses to prompts containing idioms 71.9% of the time, compared to a similar model not trained on the idioms corpus. We contribute the model checkpoint/demo and code on the HuggingFace hub for public access.

Tosin Adewumi, Lama Alkhaled, Hamam Mokayed et al.

This paper describes the system used by the Machine Learning Group of LTU in subtask 1 of the SemEval-2022 Task 4: Patronizing and Condescending Language (PCL) Detection. Our system consists of finetuning a pretrained Text-to-Text-Transfer Transformer (T5) and innovatively reducing its out-of-class predictions. The main contributions of this paper are 1) the description of the implementation details of the T5 model we used, 2) analysis of the successes & struggles of the model in this task, and 3) ablation studies beyond the official submission to ascertain the relative importance of data split. Our model achieves an F1 score of 0.5452 on the official test set.

Tosin Adewumi, Isabella Södergren, Lama Alkhaled et al.

We investigate five English NLP benchmark datasets (on the superGLUE leaderboard) and two Swedish datasets for bias, along multiple axes. The datasets are the following: Boolean Question (Boolq), CommitmentBank (CB), Winograd Schema Challenge (WSC), Wino-gender diagnostic (AXg), Recognising Textual Entailment (RTE), Swedish CB, and SWEDN. Bias can be harmful and it is known to be common in data, which ML models learn from. In order to mitigate bias in data, it is crucial to be able to estimate it objectively. We use bipol, a novel multi-axes bias metric with explainability, to estimate and explain how much bias exists in these datasets. Multilingual, multi-axes bias evaluation is not very common. Hence, we also contribute a new, large Swedish bias-labelled dataset (of 2 million samples), translated from the English version and train the SotA mT5 model on it. In addition, we contribute new multi-axes lexica for bias detection in Swedish. We make the codes, model, and new dataset publicly available.

Holly Wilson, Scott Wellington, Foteini Simistira Liwicki et al.

Decoding inner speech from the brain signal via hybridisation of fMRI and EEG data is explored to investigate the performance benefits over unimodal models. Two different bimodal fusion approaches are examined: concatenation of probability vectors output from unimodal fMRI and EEG machine learning models, and data fusion with feature engineering. Same task inner speech data are recorded from four participants, and different processing strategies are compared and contrasted to previously-employed hybridisation methods. Data across participants are discovered to encode different underlying structures, which results in varying decoding performances between subject-dependent fusion models. Decoding performance is demonstrated as improved when pursuing bimodal fMRI-EEG fusion strategies, if the data show underlying structure.

Tosin Adewumi, Mofetoluwa Adeyemi, Aremu Anuoluwapo et al.

Dialogue generation is an important NLP task fraught with many challenges. The challenges become more daunting for low-resource African languages. To enable the creation of dialogue agents for African languages, we contribute the first high-quality dialogue datasets for 6 African languages: Swahili, Wolof, Hausa, Nigerian Pidgin English, Kinyarwanda & Yorùbá. These datasets consist of 1,500 turns each, which we translate from a portion of the English multi-domain MultiWOZ dataset. Subsequently, we investigate & analyze the effectiveness of modelling through transfer learning by utilziing state-of-the-art (SoTA) deep monolingual models: DialoGPT and BlenderBot. We compare the models with a simple seq2seq baseline using perplexity. Besides this, we conduct human evaluation of single-turn conversations by using majority votes and measure inter-annotator agreement (IAA). We find that the hypothesis that deep monolingual models learn some abstractions that generalize across languages holds. We observe human-like conversations, to different degrees, in 5 out of the 6 languages. The language with the most transferable properties is the Nigerian Pidgin English, with a human-likeness score of 78.1%, of which 34.4% are unanimous. We freely provide the datasets and host the model checkpoints/demos on the HuggingFace hub for public access.

Foteini Simistira Liwicki, Richa Upadhyay, Prakash Chandra Chhipa et al.

This paper presents a framework to automate the labelling process for gestures in musical performance videos with a 3D Convolutional Neural Network (CNN). While this idea was proposed in a previous study, this paper introduces several novelties: (i) Presents a novel method to overcome the class imbalance challenge and make learning possible for co-existent gestures by batch balancing approach and spatial-temporal representations of gestures. (ii) Performs a detailed study on 7 and 18 categories of gestures generated during the performance (guitar play) of musical pieces that have been video-recorded. (iii) Investigates the possibility to use audio features. (iv) Extends the analysis to multiple videos. The novel methods significantly improve the performance of gesture identification by 12 %, when compared to the previous work (51 % in this study over 39 % in previous work). We successfully validate the proposed methods on 7 super classes (72 %), an ensemble of the 18 gestures/classes, and additional videos (75 %).

Tosin Adewumi, Marcus Liwicki, Foteini Simistira Liwicki et al.

This intervention study investigates the use of counterarguments in writing for critical thinking by students in the context of Generative AI (GenAI). This is especially as risks of cheating and cognitive offloading exist with the use of GenAI. We presented 36 students in a particular university course with 4 carefully selected thesis statements (from a set of popular debates) to write about anyone of them. We used six established rubrics (focus, logic, content, style, correctness and reference) to conduct three human assessments (two student peer-reviews and one experienced teacher) per writeup on a 5-point Likert scale for all the qualified samples (n) of 35 submissions (after disqualifying one for irregularity). Using the same rubrics and guidelines, we also assessed the submissions using six frontier LLMs as judges. Our mixed-method design included qualitative open-ended feedback per assessment and quantitative methods. The results reveal that (1) the students' self-written counterarguments to AI-generated content contains logic, among other things, which is a key component of critical thinking, and (2) GenAI can be successfully used at scale to assess students' written work, based on clear rubrics, and these assessments generally align with human assessments as shown with Gwets AC2 inter-rater reliability values of 0.33 for all the models except one.

Tosin Adewumi, Foteini Simistira Liwicki, Marcus Liwicki et al.

This paper presents an intervention study on the effects of the combined methods of (1) the Socratic method, (2) Chain of Thought (CoT) reasoning, (3) simplified gamification and (4) formative feedback on university students' Maths learning driven by large language models (LLMs). We call our approach Mathematics Explanations through Games by AI LLMs (MEGA). Some students struggle with Maths and as a result avoid Math-related discipline or subjects despite the importance of Maths across many fields, including signal processing. Oftentimes, students' Maths difficulties stem from suboptimal pedagogy. We compared the MEGA method to the traditional step-by-step (CoT) method to ascertain which is better by using a within-group design after randomly assigning questions for the participants, who are university students. Samples (n=60) were randomly drawn from each of the two test sets of the Grade School Math 8K (GSM8K) and Mathematics Aptitude Test of Heuristics (MATH) datasets, based on the error margin of 11%, the confidence level of 90%, and a manageable number of samples for the student evaluators. These samples were used to evaluate two capable LLMs at length (Generative Pretrained Transformer 4o (GPT4o) and Claude 3.5 Sonnet) out of the initial six that were tested for capability. The results showed that students agree in more instances that the MEGA method is experienced as better for learning for both datasets. It is even much better than the CoT (47.5% compared to 26.67%) in the more difficult MATH dataset, indicating that MEGA is better at explaining difficult Maths problems.

Sana Sabah Sabry, Tosin Adewumi, Nosheen Abid et al.

We investigate the performance of a state-of-the art (SoTA) architecture T5 (available on the SuperGLUE) and compare with it 3 other previous SoTA architectures across 5 different tasks from 2 relatively diverse datasets. The datasets are diverse in terms of the number and types of tasks they have. To improve performance, we augment the training data by using an autoregressive model. We achieve near-SoTA results on a couple of the tasks - macro F1 scores of 81.66% for task A of the OLID 2019 dataset and 82.54% for task A of the hate speech and offensive content (HASOC) 2021 dataset, where SoTA are 82.9% and 83.05%, respectively. We perform error analysis and explain why one of the models (Bi-LSTM) makes the predictions it does by using a publicly available algorithm: Integrated Gradient (IG). This is because explainable artificial intelligence (XAI) is essential for earning the trust of users. The main contributions of this work are the implementation method of T5, which is discussed; the data augmentation using a new conversational AI model checkpoint, which brought performance improvements; and the revelation on the shortcomings of HASOC 2021 dataset. It reveals the difficulties of poor data annotation by using a small set of examples where the T5 model made the correct predictions, even when the ground truth of the test set were incorrect (in our opinion). We also provide our model checkpoints on the HuggingFace hub1 to foster transparency.

Tosin Adewumi, Rickard Brännvall, Nosheen Abid et al.

Building open-domain conversational systems (or chatbots) that produce convincing responses is a recognized challenge. Recent state-of-the-art (SoTA) transformer-based models for the generation of natural language dialogue have demonstrated impressive performance in simulating human-like, single-turn conversations in English. This work investigates, by an empirical study, the potential for transfer learning of such models to Swedish language. DialoGPT, an English language pre-trained model, is adapted by training on three different Swedish language conversational datasets obtained from publicly available sources. Perplexity score (an automated intrinsic language model metric) and surveys by human evaluation were used to assess the performances of the fine-tuned models, with results that indicate that the capacity for transfer learning can be exploited with considerable success. Human evaluators asked to score the simulated dialogue judged over 57% of the chatbot responses to be human-like for the model trained on the largest (Swedish) dataset. We provide the demos and model checkpoints of our English and Swedish chatbots on the HuggingFace platform for public use.

Mattias Nilsson, Foteini Liwicki, Fredrik Sandin

Mixed-signal neuromorphic processors with brain-like organization and device physics offer an ultra-low-power alternative to the unsustainable developments of conventional deep learning and computing. However, realizing the potential of such neuromorphic hardware requires efficient use of its heterogeneous, analog neurosynaptic circuitry with neurocomputational methods for sparse, spike-timing-based encoding and processing. Here, we investigate the use of balanced excitatory-inhibitory disynaptic lateral connections as a resource-efficient mechanism for implementing a thalamocortically inspired Spatiotemporal Correlator (STC) neural network without using dedicated delay mechanisms. We present hardware-in-the-loop experiments with a DYNAP-SE neuromorphic processor, in which receptive fields of heterogeneous coincidence-detection neurons in an STC network with four lateral afferent connections per column were mapped by random input-sampling. Furthermore, we demonstrate how such a neuron was tuned to detect a particular spatiotemporal feature by discrete address-reprogramming of the analog synaptic circuits. The energy dissipation of the disynaptic connections is one order of magnitude lower per lateral connection (0.65 nJ vs 9.6 nJ per spike) than in the former delay-based hardware implementation of the STC.

Tosin P. Adewumi, Roshanak Vadoodi, Aparajita Tripathy et al.

We present a fairly large, Potential Idiomatic Expression (PIE) dataset for Natural Language Processing (NLP) in English. The challenges with NLP systems with regards to tasks such as Machine Translation (MT), word sense disambiguation (WSD) and information retrieval make it imperative to have a labelled idioms dataset with classes such as it is in this work. To the best of the authors' knowledge, this is the first idioms corpus with classes of idioms beyond the literal and the general idioms classification. In particular, the following classes are labelled in the dataset: metaphor, simile, euphemism, parallelism, personification, oxymoron, paradox, hyperbole, irony and literal. We obtain an overall inter-annotator agreement (IAA) score, between two independent annotators, of 88.89%. Many past efforts have been limited in the corpus size and classes of samples but this dataset contains over 20,100 samples with almost 1,200 cases of idioms (with their meanings) from 10 classes (or senses). The corpus may also be extended by researchers to meet specific needs. The corpus has part of speech (PoS) tagging from the NLTK library. Classification experiments performed on the corpus to obtain a baseline and comparison among three common models, including the BERT model, give good results. We also make publicly available the corpus and the relevant codes for working with it for NLP tasks.

Tosin P. Adewumi, Foteini Liwicki, Marcus Liwicki

The major contributions of this work include the empirical establishment of a better performance for Yoruba embeddings from undiacritized (normalized) dataset and provision of new analogy sets for evaluation. The Yoruba language, being a tonal language, utilizes diacritics (tonal marks) in written form. We show that this affects embedding performance by creating embeddings from exactly the same Wikipedia dataset but with the second one normalized to be undiacritized. We further compare average intrinsic performance with two other work (using analogy test set & WordSim) and we obtain the best performance in WordSim and corresponding Spearman correlation.

Tosin P. Adewumi, Foteini Liwicki, Marcus Liwicki

In this work, we show that the difference in performance of embeddings from differently sourced data for a given language can be due to other factors besides data size. Natural language processing (NLP) tasks usually perform better with embeddings from bigger corpora. However, broadness of covered domain and noise can play important roles. We evaluate embeddings based on two Swedish corpora: The Gigaword and Wikipedia, in analogy (intrinsic) tests and discover that the embeddings from the Wikipedia corpus generally outperform those from the Gigaword corpus, which is a bigger corpus. Downstream tests will be required to have a definite evaluation.

Tosin P. Adewumi, Foteini Liwicki, Marcus Liwicki

In this paper, our main contributions are that embeddings from relatively smaller corpora can outperform ones from larger corpora and we make the new Swedish analogy test set publicly available. To achieve a good network performance in natural language processing (NLP) downstream tasks, several factors play important roles: dataset size, the right hyper-parameters, and well-trained embeddings. We show that, with the right set of hyper-parameters, good network performance can be reached even on smaller datasets. We evaluate the embeddings at both the intrinsic and extrinsic levels. The embeddings are deployed with the Transformer in named entity recognition (NER) task and significance tests conducted. This is done for both Swedish and English. We obtain better performance in both languages on the downstream task with smaller training data, compared to recently released, Common Crawl versions; and character n-grams appear useful for Swedish, a morphologically rich language.

Tosin P. Adewumi, Foteini Liwicki, Marcus Liwicki

Word2Vec is a prominent model for natural language processing (NLP) tasks. Similar inspiration is found in distributed embeddings for new state-of-the-art (SotA) deep neural networks. However, wrong combination of hyper-parameters can produce poor quality vectors. The objective of this work is to empirically show optimal combination of hyper-parameters exists and evaluate various combinations. We compare them with the released, pre-trained original word2vec model. Both intrinsic and extrinsic (downstream) evaluations, including named entity recognition (NER) and sentiment analysis (SA) were carried out. The downstream tasks reveal that the best model is usually task-specific, high analogy scores don't necessarily correlate positively with F1 scores and the same applies to focus on data alone. Increasing vector dimension size after a point leads to poor quality or performance. If ethical considerations to save time, energy and the environment are made, then reasonably smaller corpora may do just as well or even better in some cases. Besides, using a small corpus, we obtain better human-assigned WordSim scores, corresponding Spearman correlation and better downstream performances (with significance tests) compared to the original model, trained on 100 billion-word corpus.

Rajkumar Saini, Derek Dobson, Jon Morrey et al.

We propose a Historical Document Reading Challenge on Large Chinese Structured Family Records, in short ICDAR2019 HDRC CHINESE. The objective of the proposed competition is to recognize and analyze the layout, and finally detect and recognize the textlines and characters of the large historical document collection containing more than 20 000 pages kindly provided by FamilySearch.