Tootfinder

Last week, we continued our #ISE2025 lecture on distributional semantics with the introduction of neural language models (NLMs) and compared them to traditional statistical n-gram models.
Benefits of NLMs:
- Capturing Long-Range Dependencies
- Computational and Statistical Tractability
- Improved Generalisation
- Higher Accuracy
@…

This https://arxiv.org/abs/2405.07671 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csFL_…

Constructing a BPE Tokenization DFA
Many natural language processing systems operate over tokenizations of text to address the open-vocabulary problem. In this paper, we give and analyze an algorithm for the efficient construction of deterministic finite automata (DFA) designed to operate directly on tokenizations produced by the popular byte pair encoding (BPE) technique. This makes it possible to apply many existing techniques and algorithms to the tokenized case, such as pattern matching, equivalence checking of tokenization d…

So this guy threw Natural Language Processing at the Voynich Manuscript and concluded that it probably is written in some kind of language and is not just total gibberish. Cool bit of ML research! https://github.com/brianmg/voynich-nlp-analysis

In our #ISE2025 lecture last Wednesday, we learned how in n-gram language models via Markov assumption and maximum likelihood estimation we can predict the probability of the occurrence of a word given a specific context (i.e. n words previous in the sequence of words).
#NLP

SeisCoDE: 3D Seismic Interpretation Foundation Model with Contrastive Self-Distillation Learning
Goodluck Archibong, Ardiansyah Koeshidayatullah, Umair Waheed, Weichang Li, Dicky Harishidayat, Motaz Alfarraj
https://arxiv.org/abs/2505.20518

SeisCoDE: 3D Seismic Interpretation Foundation Model with Contrastive Self-Distillation Learning
Seismic interpretation is vital for understanding subsurface structures but remains labor-intensive, subjective, and computationally demanding. While deep learning (DL) offers promise, its success hinges on large, high-quality datasets, often scarce in geophysics. Foundation Models (FMs), which have shown significant success in fields like natural language processing and computer vision, offer a transformative opportunity for seismic interpretation by enabling knowledge transfer and generalizat…

Next stop on our NLP timeline (as part of the #ISE2025 lecture) was Terry Winograd's SHRDLU, an early natural language understanding system developed in 1968-70 that could manipulate blocks in a virtual world.
Winograd, T. Procedures as a Representation for Data in a Computer Program for Understanding Natural Language. MIT AI Technical Report 235.

Opportunities and Applications of GenAI in Smart Cities: A User-Centric Survey
Ankit Shetgaonkar, Dipen Pradhan, Lakshit Arora, Sanjay Surendranath Girija, Shashank Kapoor, Aman Raj
https://arxiv.org/abs/2505.08034

Opportunities and Applications of GenAI in Smart Cities: A User-Centric Survey
The proliferation of IoT in cities, combined with Digital Twins, creates a rich data foundation for Smart Cities aimed at improving urban life and operations. Generative AI (GenAI) significantly enhances this potential, moving beyond traditional AI analytics and predictions by processing multimodal content and generating novel outputs like text and simulations. Using specialized or foundational models, GenAI's natural language abilities such as Natural Language Understanding (NLU) and Natural L…

With the advent of ELIZA, Joseph Weizenbaum's first psychotherapist chatbot, NLP took another major step with pattern-based substitution algorithms based on simple regular expressions.
Weizenbaum, Joseph (1966). ELIZA—a computer program for the study of natural language communication between man and machine. Com. of the ACM. 9: 36–45.

This week, we were discussing the central question Can we "predict" a word? as the basis for statistical language models in our #ISE2025 lecture. Of course, I wasx trying Shakespeare quotes to motivate the (international) students to complement the quotes with "predicted" missing words ;-)
"All the world's a stage, and all the men and women merely...."

Last leg on our brief history of NLP (so far) is the advent of large language models with GPT-3 in 2020 and the introduction of learning from the prompt (aka few-shot learning).
T. B. Brown et al. (2020). Language models are few-shot learners. NIPS'20
https://…

Retrieval-Augmented Generation in Biomedicine: A Survey of Technologies, Datasets, and Clinical Applications
Jiawei He, Boya Zhang, Hossein Rouhizadeh, Yingjian Chen, Rui Yang, Jin Lu, Xudong Chen, Nan Liu, Irene Li, Douglas Teodoro
https://arxiv.org/abs/2505.01146

Retrieval-Augmented Generation in Biomedicine: A Survey of Technologies, Datasets, and Clinical Applications
Recent advances in large language models (LLMs) have demonstrated remarkable capabilities in natural language processing tasks. However, their application in the biomedical domain presents unique challenges, particularly regarding factual accuracy and up-to-date knowledge integration. Retrieval Augmented Generation (RAG) has emerged as a promising solution to address these challenges by combining the generative capabilities of LLMs with external knowledge retrieval. This comprehensive survey ex…

Building on the 90s, statistical n-gram language models, trained on vast text collections, became the backbone of NLP research. They fueled advancements in nearly all NLP techniques of the era, laying the groundwork for today's AI.
F. Jelinek (1997), Statistical Methods for Speech Recognition, MIT Press, Cambridge, MA
#NLP

Last week, our students learned how to conduct a proper evaluation for an NLP experiment. To this end, we introduced a small textcorpus with sentences about Joseph Fourier, who counts as one of the discoverers of the greenhouse effect, responsible for global warming.

Next stop in our NLP timeline is 2013, the introduction of low dimensional dense word vectors - so-called "word embeddings" - based on distributed semantics, as e.g. word2vec by Mikolov et al. from Google, which enabled representation learning on text.
T. Mikolov et al. (2013). Efficient Estimation of Word Representations in Vector Space.
…

Efficient Estimation of Word Representations in Vector Space
We propose two novel model architectures for computing continuous vector representations of words from very large data sets. The quality of these representations is measured in a word similarity task, and the results are compared to the previously best performing techniques based on different types of neural networks. We observe large improvements in accuracy at much lower computational cost, i.e. it takes less than a day to learn high quality word vectors from a 1.6 billion words data set. Fur…