#nlp

• 23 Jul 2025 · Study

  NLP · Text classification

  Multi-class topic classification on 20 Newsgroups, comparing Naive Bayes, logistic regression and a linear SVM, with a per-class report and the most confused pairs.

• 14 Jul 2025 · Study

  NLP · Sentiment analysis

  Classifying movie-review sentiment on the Rotten Tomatoes dataset: a TF-IDF plus logistic regression baseline, its most telling words, and where it fails.

• 4 Jul 2025 · Study

  NLP · Named entity recognition

  NER as token-level sequence labelling with BIO tags, running spaCy's pretrained pipeline, and why entity spans make evaluation tricky.

• 25 Jun 2025 · Study

  NLP · Attention (Bahdanau)

  Additive attention lets the decoder look at every encoder state instead of one summary vector; the same reversal task with attention, and its alignment weights.

• 17 Jun 2025 · Study

  NLP · Seq2seq

  The encoder–decoder architecture for sequence-to-sequence tasks, teacher forcing, and a small GRU model learning to reverse digit strings.

• 6 Jun 2025 · Study

  NLP · GloVe

  GloVe vectors from global co-occurrence statistics, loading pretrained 50-dimensional vectors, analogies, and the bias these vectors inherit.

• 28 May 2025 · Study

  NLP · word2vec

  Dense word vectors learned by predicting context (skip-gram), trained with gensim on the 20 Newsgroups corpus, with nearest neighbours.

• 20 May 2025 · Study

  NLP · Bag of words and TF-IDF

  Turning documents into vectors with CountVectorizer and TfidfVectorizer, n-grams, and finding similar documents with cosine similarity.

• 9 May 2025 · Study

  NLP · Tokenisation

  Word, character and subword tokenisation compared, out-of-vocabulary words, and what a real BERT WordPiece tokenizer does to unusual words.

• 1 May 2025 · Study

  NLP · Text preprocessing

  Cleaning raw text with regex and spaCy: normalisation, lowercasing, stop words, lemmatisation, and why modern models need much less of this.

• 2 Jan 2024 · Paper summary

  Paper summary: DocLLM: A layout-aware generative language model for multimodal document understanding

  DocLLM adds layout awareness to an LLM using only text bounding boxes, with no image encoder, via disentangled text/layout attention and a text-infilling pre-training objective.