Tim Schlippe

IU International University of Applied Sciences | IU

Sentiment analysis can aid in understanding people's opinions and emotions on social issues. In multilingual communities sentiment analysis systems can be used to quickly identify social challenges in social media posts, enabling government departments to detect and address these issues more precisely and effectively. Recently, large-language model...

Chatbots based on large language models (LLMs) like ChatGPT are available to the wide public. These tools can for instance be used by students to generate essays or whole theses from scratch or by rephrasing an existing text. But how does for instance a teacher know whether a text is written by a student or an AI? In this paper, we investigate perp...

Running machine learning algorithms for image classification locally on small, cheap, and low-power microcontroller units (MCUs) has advantages in terms of bandwidth, inference time, energy, reliability, and privacy for different applications. Therefore, TinyML focuses on deploying neural networks on MCUs with random access memory sizes between 2 K...

Our paper compares the correctness, efficiency, and maintainability of human-generated and AI-generated program code. For that, we analyzed the computational resources of AI- and human-generated program code using metrics such as time and space complexity as well as runtime and memory usage. Additionally, we evaluated the maintainability using metr...

The automated transcription of mathematical formulas represents a complex challenge that is of great importance for digital processing and comprehensibility of mathematical content. Consequently, our goal was to analyze state-of-the-art approaches for the transcription of printed mathematical formulas on images into spoken English text. We focused...

To optimally prepare students for jobs, it is often useful to match the content of the learning material with the needs of the current job market. On the other hand, it can motivate students and give them inspiration for their future careers to see what exciting jobs they can acquire if they learn the learning material. For these reasons, we have e...

Recently, generative AIs like ChatGPT have become available to the wide public. These tools can for instance be used by students to generate essays or whole theses. But how does a teacher know whether a text is written by a student or an AI? In our work, we explore traditional and new features to (1) detect text generated by AI from scratch and (2)...

Text simplification is an essential task in today’s society. It has the potential to help minorities get information, the broad masses have access to higher education, and assist in learning a new language. Through text simplification, we achieve an inclusive world with less language barriers. However, for training automatic artificial intelligence...

This book is a collection of selected research papers presented at the 2023 4th International Conference on Artificial Intelligence in Education Technology (AIET 2023), held in Berlin, Germany, on June 30 - July 2, 2023. AIET establishes a platform for AI in education researchers to present research, exchange innovative ideas, propose new models, a...

Recently, generative AIs like ChatGPT have become available to the wide public. These tools can for instance be used by students to generate essays or whole theses. But how does a teacher know whether a text is written by a student or an AI? In our work, we explore traditional and new features to (1) detect text generated by AI from scratch and (2)...

Empathy is often understood as the ability to share and understand another individual's state of mind or emotion. With the increasing use of chatbots in various domains, e.g., children seeking help with homework, individuals looking for medical advice, and people using the chatbot as a daily source of everyday companionship, the importance of empat...

French is a strategically and economically important language in the regions where the African language Twi is spoken. However, only a very small proportion of Twi speakers in Ghana speak French. The development of a Twi–French parallel corpus and corresponding machine translation applications would provide various advantages, including stimulating...

Sentiment analysis is a helpful task to automatically analyse opinions and emotions on various topics in areas such as AI for Social Good, AI in Education or marketing. While many of the sentiment analysis systems are developed for English, many African languages are classified as low-resource languages due to the lack of digital language resources...

Skills are the common ground between employers, job seekers and educational institutions which can be analyzed with the help of artificial intelligence (AI), specifically natural language processing (NLP) techniques. In this paper we explore a state-of-the-art pipeline that extracts, vectorizes, clusters, and compares skills to provide recommendati...

Massive open online courses and other online study opportunities are providing easier access to education for more and more people around the world. To cope with the large number of exams to be assessed in these courses, AI-driven automatic short answer grading can recommend teaching staff to assign points when evaluating free text answers, leading...

More and more educational institutions are making lecture videos available online. Since 100+ empirical studies document that captioning a video improves comprehension of, attention to, and memory for the video [1], it makes sense to provide those lecture videos with captions. However, studies also show that the words themselves contribute only 7%...

This edited book is a collection of selected research papers presented at the 2022 3rd International Conference on Artificial Intelligence in Education Technology (AIET 2022), held in Wuhan, China, on July 1–3, 2022. AIET establishes a platform for AI in education researchers to present research, exchange innovative ideas, propose new models, as we...

Usually employers, job seekers and educational institutions use AI in isolation from one another. However, skills are the common ground between these three parties which can be analyzed with the help of AI. Employers want to automatically check which of their required skills are covered by applicants’ CVs and know which courses their employees can...

Sentiment analysis has the potential to help analyse people’s opinions and emotions on social issues [1]. We believe that in multilingual communities sentiment analysis systems should be even used to quickly discover what social challenges exist. This would help government departments target those issues more precisely and effectively. Consequently...

Skills are the common ground between employers, job seekers and educational institutions which can be analyzed with the help of natural language processing (NLP) techniques. In this paper we explore a state-of-the-art pipeline that extracts, vectorizes, clusters, and compares skills to provide recommendations for all three parties—thereby bridging...

Multilingual sentiment analysis is a process of detecting and classifying sentiment based on textual information written in multiple languages. There has been tremendous research advancement on high-resourced languages such as English. However, progress on under-resourced languages remains underrepresented with limited opportunities for further dev...

We describe our work on sentiment analysis for Hausa, where we investigated monolingual and cross-lingual approaches to classify student comments in course evaluations. Furthermore, we propose a novel stemming algorithm to improve accuracy. For studies in this area, we collected a corpus of more than 40,000 comments-the Hausa-English Sentiment Anal...

Usually employers, job seekers and educational institutions use AI in isolation from one another. However, skills are the common ground between these three parties which can be analyzed with the help of AI: (1) Employers want to automatically check which of their required skills are covered by appli-cants' CVs and know which courses their employees...

We investigate and compare state-of-the-art deep learning techniques for Automatic Short Answer Grading. Our experiments demonstrate that systems based on the Bidirectional Encoder Representations from Transformers (BERT) [1] performed best for English and German. Our system achieves a Pearson correlation coefficient of 0.73 and a Mean Absolute Err...

Massive open online courses and other online study opportunities are providing easier access to education for more and more people around the world. However, one big challenge is still the language barrier: Most courses are available in English, but only 16% of the world’s population speaks English [1]. The language challenge is especially evident...

While AI is being used more and more to generate images, the generation usually does not resemble a human painting process. However, for applications in the field of art, it is useful to simulate the human painting process—e.g. in relation to location, order, shape, color and contours of the areas being painted in each step. Such applications are f...

Our previous analysis on 26 languages which represent over 2.9 billion speakers and 8 language families demonstrated that cross-lingual automatic short answer grading allows students to write answers in exams in their native language and graders to rely on the scores of the system [1]. With lower deviations than 14% (0.72 points out of 5 points) on...

This paper illustrates a number of locality sensitive hasing (LSH) models for the identification and removal of nearly redundant data in a text dataset. To evaluate the different models, we created a dataset for data deduplication using Wikipedia articles. Area-Under-Curve (AUC) values more than 0.9 were observed for most models, with the best mode...

This paper illustrates locality sensitive hasing (LSH) models for the identification and removal of nearly redundant data in a text dataset. To evaluate the different models, we create an artificial dataset for data deduplication using English Wikipedia articles. Area-Under-Curve (AUC) over 0.9 were observed for most models, with the best model rea...

We present the concept of an intelligent tutoring system which combines web search for learning purposes and state-of-the-art natural language processing techniques. Our concept is described for the case of teaching information literacy, but has the potential to be applied to other courses or for independent acquisition of knowledge through web sea...

Diversification of fonts in video captions based on the voice characteristics, namely loudness, speed and pauses, can affect the viewer receiving the content. This study evaluates a new method, WaveFont, which visualizes the voice characteristics for captions in an intuitive way. The study was specifically designed to test captions, which aims to a...

With voice driven type design (VDTD), we introduce a novel concept to present written information in the digital age. While the shape of a single typographical character has been treated as an unchangeable property until today, we present an innovative method to adjust the shape of each single character according to particular acoustic features in...

With voice driven type design (VDTD), we introduce a novel concept to present written information in the digital age. While the shape of a single typographic character has been treated as an unchangeable property until today, we present an innovative method to adjust the shape of each single character according to particular acoustic features in th...

With voice driven type design (VDTD), we introduce a novel concept to present written in-formation in the digital age. While the shape of a single typographic character has been treated as an unchangeable property until today, we present an innovative method to adjust the shape of each single character according to particular acoustic features in t...

Zero-resource Automatic Speech Recognition (ZR ASR) addresses target languages without given pronunciation dictionary, transcribed speech, and language model. Lexical discovery for ZR ASR aims to extract word-like chunks from speech. Lexical discovery benefits from the availability of written translations in another source language [1, 2, 3]. In th...

In this paper we describe and compare two techniques for the automatic diacritization of Arabic text: First, we treat diacritization as a monotone machine translation problem, proposing and evaluating several translation and language models, including word and character-based models separately and com- bined as well as a model which uses statisti-...

In this paper, we study methods to discover words and extract their pronunciations from audio data for non-written and under- resourced languages. We examine the potential and the challenges of pronunciation extraction from phoneme sequences through cross-lingual word-to-phoneme alignment. In our scenario a human translator produces utterances in t...

In this paper we propose efficient methods which contribute to a rapid and economic semi-automatic pronunciation dictionary development and evaluate them on English, German, Spanish, Vietnamese, Swahili, and Haitian Creole. First we determine optimal strategies for the word selection and the period for the grapheme-to-phoneme model retraining. In a...

We introduce BioKIT, a new Hidden Markov Model based toolkit to preprocess, model and interpret biosignals such as speech, motion, muscle and brain activities. The focus of this toolkit is to enable researchers from various communities to pursue their experiments and integrate real-time biosignal in-terpretation into their applications. BioKIT boos...

In this paper we tackle the task of bootstrapping an Automatic Speech Recognition system without an a priori given language model, a pronunciation dictionary, or transcribed speech data for the target language Slovene – only untranscribed speech and translations to other resource-rich source languages of what was said are avail-able. Therefore, our...

This paper presents investigations of features which can be used to predict Code-Switching speech. For this task, fac-tored language models are applied and implemented into a state-of-the-art decoder. Different possible factors, such as words, part-of-speech tags, Brown word clusters, open class words and open class word clusters are explored. We f...

With the globalization more and more words from other lan-guages come into a language without assimilation to the phonetic system of the new language. To economically build up lexical re-sources with automatic or semi-automatic methods, it is important to detect and treat them separately. Due to the strong increase of Anglicisms, especially from th...

For pronunciation dictionary creation, we propose the com-bination of grapheme-to-phoneme (G2P) converter outputs where low resources are available to train the single convert-ers. Our experiments with German, English, French, and Spanish show that in most cases the phoneme-level combi-nation approaches validated reference pronunciations more than...

We improve the automatic speech recognition of broadcast news using paradigms from Web 2.0 to obtain time- And topicrelevant text data for language modeling. We elaborate an unsupervised text collection and decoding strategy that includes crawling appropriate texts from RSS Feeds, complementing it with texts from Twitter, language model and vocabul...

With the help of written translations in a source language, we cross-lingually segment phoneme sequences in a target language into word units using our new alignment model Model 3P [17]. From this, we deduce phonetic transcriptions of target language words, introduce the vocabulary in terms of word IDs, and extract a pronunciation dictionary. Our a...

In this paper we study the potential as well as the challenges of using the World Wide Web as a seed for the rapid generation of pronunciation dictionaries in new languages. In particular, we describe Wiktionary, a community-driven resource of pronunciations in IPA notation, which is available in many different languages. First, we analyze Wiktiona...

Code-switching is a very common phenomenon in multilingual communities. In this paper, we investigate language modeling for conversational Mandarin-English code-switching (CS) speech recognition. First, we investigate the prediction of code switches based on textual features with focus on Part-of-Speech (POS) tags and trigger words. Second, we prop...

This paper describes the advances in the multilingual text and speech database GlobalPhone, a multilingual database of highquality read speech with corresponding transcriptions and pronunciation dictionaries in 20 languages. GlobalPhone was designed to be uniform across languages with respect to the amount of data, speech quality, the collection sc...

We report on our efforts toward an LVCSR system for the Slavic language Ukrainian. We describe the Ukrainian text and speech database recently collected as a part of our GlobalPhone corpus [1] with our Rapid Language Adaptation Toolkit [2]. The data was complemented by a large collection of text data crawled from various Ukrainian websites. For the...

In [1], we have proposed systems for text normalization based on statistical machine translation (SMT) methods which are constructed with the support of Internet users and evaluated those with French texts. Internet users normalize text displayed in a web interface in an annotation process, thereby providing a parallel corpus of normalized and non-...

This paper presents first steps toward a large vocabulary continuous speech recognition system (LVCSR) for conversational Mandarin-English code-switching (CS) speech. We applied state-of-the-art techniques such as speaker adaptive and discriminative training to build the first baseline system on the SEAME corpus [1] (South East Asia Mandarin-Englis...

We present our new alignment model Model 3P for cross-lingual word-to-phoneme alignment, and show that unsupervised learning of word segmentation is more accurate when information of another language is used. Word segmentation with cross-lingual information is highly relevant to bootstrap pronunciation dictionaries from audio data for Automatic Spe...

In this paper, we present our latest investigations on pronunciation modeling and its impact on ASR. We pro- pose completely automatic methods to detect, remove, and substitute inconsistent or flawed entries in pronunciation dictionaries. The experiments were conducted on different tasks, namely (1) word-pronunciation pairs from the Czech, English,...

We report on our efforts toward an LVCSR system for the African language Hausa. We describe the Hausa text and speech database recently collected as a part of our GlobalPhone corpus [1]. The data was complemented by a large collection of text data crawled from various Hausa websites. We achieve significant improvement by automatically substituting...

In this paper, we evaluate grapheme-to-phoneme (g2p) models among languages and of different quality. We created g2p models for Indo-European languages with word-pronunciation pairs from the GlobalPhone project and from Wiktionary [1]. Then we checked their quality in terms of consistency and complexity as well as their impact on Czech, English, Fr...

This paper presents first steps toward a large vocabulary continuous speech recognition system (LVCSR) for conversational Mandarin-English code-switching (CS) speech. We applied state-of-the-art techniques such as speaker adaptive and discriminative training to build the first baseline system on the SEAME corpus [1] (South East Asia Mandarin-Englis...

This paper describes the speech-to-text systems used to provide automatic transcriptions used in the Quaero 2010 evaluation of Machine Translation from speech. Quaero (www.quaero.org) is a large research and industrial innovation program focusing on technologies for automatic analysis and classification of multimedia and multilingual documents. The...

In this paper, we describe and compare systems for text normalization based on statistical machine translation (SMT) methods which are constructed with the support of internet users. Internet users normalize text displayed in a web interface, thereby providing a parallel corpus of normalized and nonnormalized text. With this corpus, SMT models are...

This paper presents our latest efforts toward LVCSR systems for five Eastern European languages such as Bulgarian, Croatian, Czech, Polish, and Russian using our Rapid Language Adaptation Toolkit (RLAT) [1]. We investigated the possibility of crawling large quantities of text material from the Internet, which is very cheap but also requires text po...

In this paper, we analyze whether dictionaries from the World Wide Web which contain phonetic notations, may support the rapid creation of pronunciation dictionaries within the speech recognition and speech synthesis system building process. As a representative dictionary, we selected Wiktionary [1] since it is at hand in multiple languages and, in...