Machine translation in the context of Natural language understanding

Natural language understanding (NLU) or natural language interpretation (NLI) is a subset of natural language processing in artificial intelligence that deals with machine reading comprehension. NLU has been considered an AI-hard problem.

There is considerable commercial interest in the field because of its application to automated reasoning, machine translation, question answering, news-gathering, text categorization, voice-activation, archiving, and large-scale content analysis.

Computer-aided translation (CAT), also referred to as computer-assisted translation or computer-aided human translation (CAHT), is the use of software, also known as a translator, to assist a human translator in the translation process. The translation is created by a human, and certain aspects of the process are facilitated by software; this is in contrast with machine translation (MT), in which the translation is created by a computer, optionally with some human intervention (e.g. pre-editing and post-editing).

CAT tools are typically understood to mean programs that specifically facilitate the actual translation process. Most CAT tools have (a) the ability to translate a variety of source file formats in a single editing environment without needing to use the file format's associated software for most or all of the translation process, (b) translation memory, and (c) integration of various utilities or processes that increase productivity and consistency in translation.

In machine learning, deep learning focuses on utilizing multilayered neural networks to perform tasks such as classification, regression, and representation learning. The field takes inspiration from biological neuroscience and revolves around stacking artificial neurons into layers and "training" them to process data. The adjective "deep" refers to the use of multiple layers (ranging from three to several hundred or thousands) in the network. Methods used can be supervised, semi-supervised or unsupervised.

Some common deep learning network architectures include fully connected networks, deep belief networks, recurrent neural networks, convolutional neural networks, generative adversarial networks, transformers, and neural radiance fields. These architectures have been applied to fields including computer vision, speech recognition, natural language processing, machine translation, bioinformatics, drug design, medical image analysis, climate science, material inspection and board game programs, where they have produced results comparable to and in some cases surpassing human expert performance.

Applications of artificial intelligence covers the ways computer systems are used to do tasks that normally rely on humans, perception or problem solving. AI shows up in many different everyday tools and services. Some examples are search engines, recommendation systems, language translation tools, speech recognition, virtual assistants, fraud detection, medical support systems, robotics and autonomous vehicles. These uses rely on a lot of different branches of AI, like rule-based systems, expert systems and machine learning approaches like deep learning.

AI can function as a stand-alone tool or as a part of a larger system. Its use can look different based on the sector, but it is now common in areas like online platforms, finance, logistics and consumer technology. AI continues to grow in fields like healthcare, scientific research, government operations, manufacturing and transportation. AI's specific capabilities really depend on the methods used and the context in which it is applied.

A language model is a model of the human brain's ability to produce natural language. Language models are useful for a variety of tasks, including speech recognition, machine translation, natural language generation (generating more human-like text), optical character recognition, route optimization, handwriting recognition, grammar induction, and information retrieval.

Large language models (LLMs), currently their most advanced form as of 2019, are predominantly based on transformers trained on larger datasets (frequently using texts scraped from the public internet). They have superseded recurrent neural network-based models, which had previously superseded the purely statistical models, such as the word n-gram language model.

A pro-drop language (from "pronoun-dropping") is a language in which certain classes of pronouns may be omitted when they can be pragmatically or grammatically inferable. The precise conditions vary from language to language, and can be quite intricate. The phenomenon of "pronoun-dropping" is part of the larger topic of zero or null anaphora. The connection between pro-drop languages and null anaphora relates to the fact that a dropped pronoun has referential properties, and so is crucially not a null dummy pronoun.

Pro-drop is a problem when translating to a non-pro-drop language such as English, which requires the pronoun to be added, especially noticeable in machine translation. It can also contribute to transfer errors in language learning.

Optical character recognition or optical character reader (OCR) is the electronic or mechanical conversion of images of typed, handwritten or printed text into machine-encoded text, whether from a scanned document, a photo of a document, a scene photo (for example the text on signs and billboards in a landscape photo) or from subtitle text superimposed on an image (for example: from a television broadcast).

Widely used as a form of data entry from printed paper data records – whether passport documents, invoices, bank statements, computerized receipts, business cards, mail, printed data, or any suitable documentation – it is a common method of digitizing printed texts so that they can be electronically edited, searched, stored more compactly, displayed online, and used in machine processes such as cognitive computing, machine translation, (extracted) text-to-speech, key data and text mining. OCR is a field of research in pattern recognition, artificial intelligence and computer vision.

Warren Weaver (July 17, 1894 – November 24, 1978) was an American scientist, mathematician, and science administrator. He is widely recognized as one of the pioneers of machine translation and as an important figure in creating support for science in the United States.

Google Translate is a multilingual neural machine translation service developed by Google to translate text, documents and websites from one language into another. It offers a website interface, a mobile app for Android and iOS, and an API that helps developers build browser extensions and software applications. As of December 2025, Google Translate supports 249 languages and language varieties at various levels. It served over 200 million people daily in May 2013, and over 500 million total users as of April 2016, with more than 100 billion words translated daily.

Launched in April 2006 as a statistical machine translation service, it originally used United Nations and European Parliament documents and transcripts to gather linguistic data. Rather than translating languages directly, it first translated text to English and then pivoted to the target language in most of the language combinations it posited in its grid, with a few exceptions including Catalan–Spanish. During a translation, it looked for patterns in millions of documents to help decide which words to choose and how to arrange them in the target language. In recent years, it has used a deep learning model to power its translations. Its accuracy, which has been criticized on several occasions, has been measured to vary greatly across languages. In November 2016, Google announced that Google Translate would switch to a neural machine translation engine – Google Neural Machine Translation (GNMT) – which translated "whole sentences at a time, rather than just piece by piece. It uses this broader context to help it figure out the most relevant translation, which it then rearranges and adjusts to be more like a human speaking with proper grammar".

Yehoshua Bar-Hillel (Hebrew: יהושע בר-הלל; 8 September 1915 – 25 September 1975) was an Israeli philosopher, mathematician, and linguist. He was a pioneer in the fields of machine translation and formal linguistics.

Semantic parsing is the task of converting a natural language utterance to a logical form: a machine-understandable representation of its meaning. Semantic parsing can thus be understood as extracting the precise meaning of an utterance. Applications of semantic parsing include machine translation, question answering, ontology induction, automated reasoning, and code generation. The phrase was first used in the 1970s by Yorick Wilks as the basis for machine translation programs working with only semantic representations. Semantic parsing is one of the important tasks in computational linguistics and natural language processing.

Semantic parsing maps text to formal meaningrepresentations. This contrasts with semantic rolelabeling and otherforms of shallow semantic processing, which donot aim to produce complete formal meanings.In computer vision, semantic parsing is a process of segmentation for 3D objects.