Dependency parsing is a natural language processing technique that represents the grammatical structure of a sentence as dependencies between words. Each word is linked to a governing word, for example subject and object to the verb: in 'The customer orders two lamps', 'customer' and 'lamps' depend on 'orders'. This helps with information extraction, for instance to identify who did what.
Part-of-speech tagging automatically assigns each word in a sentence its grammatical category, such as noun, verb, adjective or preposition. Because many words are ambiguous (“book” as a noun or a verb, “light” as an adjective or a noun), the methods take the sentence context into account. POS tagging is a classic pre-processing step for parsing, information extraction or spell checking and is offered by libraries such as spaCy and NLTK.
Natural language processing is the branch of AI that enables computers to analyse, understand and generate human language in text or speech. It covers tasks such as translation, classification, summarisation, sentiment analysis and question answering. Rules and statistical methods once dominated; today the field is shaped by large language models.
spaCy is an open-source Python library for natural language processing, developed by the Berlin-based company Explosion. It splits texts into words and sentences, determines parts of speech and base forms, analyses sentence structure and recognises named entities such as people, companies or places. Pre-trained models are available for many languages, including German. spaCy is designed for speed and for use in real applications, for example to pre-process large volumes of documents.
Coreference resolution is a natural language processing task that identifies which expressions in a text refer to the same person, thing or matter. In “Ms Weber called. She would like a call back”, the system must understand that “she” means Ms Weber. This matters for summaries, information extraction and chatbots that need to keep track of references across several sentences or conversation turns.
