CrossWord Puzzle 2

1. Across

Across

1. The process of automatically translating text or speech from one language to another using computer algorithms.
2. An MT approach that uses linguistic rules and bilingual dictionaries to translate text, focusing on syntax, morphology, and grammar.
3. An MT approach that uses statistical models based on bilingual text corpora to predict the probability of a translation.
4. An advanced MT approach that uses deep learning models, specifically neural networks, to translate text by analyzing large datasets and capturing context.
5. An MT approach that relies on a database of previously translated examples, finding the closest matches to translate new sentences.
6. A combination of different MT approaches, often integrating RBMT and SMT/NMT to leverage the strengths of each method.
7. Large collections of text in two languages, used to train and evaluate MT systems by providing parallel examples of translations.
8. A type of bilingual corpus where texts in two languages are aligned at the sentence level, facilitating the training of SMT and NMT systems.
9. A specific type of SMT that breaks down text into phrases rather than individual words, improving the fluency of translations.
10. A deep learning model used in NMT that processes sequences of text to generate translations, maintaining the order and context of words.
11. In SMT, a model that predicts the most likely translation of a word or phrase based on bilingual text data.
12. A model that assesses the fluency of the translated text by predicting the likelihood of word sequences in the target language.
13. In MT, the process that selects the best translation hypothesis based on the probabilities generated by the translation and language models.
14. A component in SMT that predicts the correct word order in the target language, addressing differences in syntax between languages.
15. Computational models inspired by the human brain, used in NMT to learn patterns and relationships in language data.
16. A technique in NMT that allows the model to focus on specific parts of the input sentence, improving translation accuracy, especially for long sentences.
17. A framework used in NMT where the encoder processes the input text and the decoder generates the translation, often using an attention mechanism.
18. A metric for evaluating the quality of machine-generated translations by comparing them to one or more reference translations.
19. In NMT, models that have been trained on large datasets and can be fine-tuned for specific tasks or languages, speeding up the development process.
20. The practice of applying knowledge gained from one task (e.g., translating English to French) to another related task (e.g., translating English to Spanish), commonly used in NMT.

1.1. Check Across

Across

1. MACHINE TRANSLATION
2. RULE-BASED MACHINE TRANSLATION
3. STATISTICAL MACHINE TRANSLATION
4. NEURAL MACHINE TRANSLATION
5. EXAMPLE-BASED MACHINE TRANSLATION
6. HYBRID MACHINE TRANSLATION
7. BILINGUAL TEXT CORPORA
8. PARALLEL CORPORA
9. PHRASE-BASED MACHINE TRANSLATION
10. SEQUENCE-TO-SEQUENCE MODEL
11. TRANSLATION MODEL
12. LANGUAGE MODEL
13. DECODING ALGORITHM
14. REORDERING MODEL
15. NEURAL NETWORKS
16. ATTENTION MECHANISM
17. ENCODER-DECODER ARCHITECTURE
18. BLEU SCORE
19. PRE-TRAINED MODELS
20. TRANSFER LEARNING

2. Down

Down

1. A method in NMT training where target language data is translated back into the source language to create additional training data, improving translation quality.
2. Smaller language components, such as prefixes or suffixes, used in NMT to handle rare or compound words more effectively.
3. The process of breaking down text into smaller units, such as words or subwords, to facilitate processing in MT systems.
4. The process of matching corresponding words or phrases between the source and target languages in a parallel corpus, crucial for training SMT and NMT systems.
5. Dense vector representations of words used in NMT to capture semantic meanings and relationships between words in different languages.
6. The process of fine-tuning an MT system to perform better in a specific domain, such as legal or medical translation.
7. The ability of an MT system to apply knowledge from one language pair to another, enhancing translation quality across multiple languages.
8. An NMT approach that handles multiple languages simultaneously, using a shared model that can translate between any pair of supported languages.
9. Languages that have limited digital resources, such as corpora or dictionaries, posing challenges for MT development.
10. Words that are not present in the training data of an MT system, often leading to translation errors.
11. The process of manually correcting errors in machine-generated translations to improve accuracy and fluency.
12. The process of analyzing the grammatical structure of sentences, used in RBMT to generate accurate translations.
13. The study of the structure of words and their components, such as roots and affixes, used in RBMT to handle inflected languages.
14. The process of determining the correct meaning of a word that has multiple possible interpretations, crucial in MT for accurate translations.
15. Identifying the roles played by words in a sentence, such as agent or object, to improve the accuracy of MT systems.
16. The combination of a source language and a target language in MT, such as English to Spanish.
17. An intermediate language used in MT when direct translation between two languages is difficult due to lack of resources.
18. Word embeddings that take into account the context in which a word appears, improving translation quality in NMT.
19. The process of artificially increasing the size of a training dataset by creating variations of existing data, used to improve MT performance.
20. A decoding algorithm used in NMT that considers multiple translation hypotheses simultaneously to find the most probable translation.
21. A regularization technique in NMT that prevents overfitting by randomly dropping units in the neural network during training.
22. The process of automatically finding and extracting parallel sentences from large bilingual corpora, used to improve the training of MT systems.
23. A term referring to the distinct linguistic patterns that emerge in machine-generated translations, often detectable by statistical analysis.
24. An MT approach where human translators interact with the MT system during the translation process, refining the output in real-time.
25. An approach that relies heavily on large text corpora for training MT systems, typical in SMT and NMT.
26. In SMT, a table that lists possible translations for phrases in the source language along with their probabilities.
27. A loss function used in NMT training to measure the difference between the predicted translation and the actual translation.
28. A type of language model used in NMT that predicts the next word in a sentence based on the context of previous words.
29. A technique in NMT where a smaller, simpler model is trained to replicate the behavior of a larger, more complex model, improving efficiency.
30. An MT approach that transfers linguistic structures from the source language to the target language, relying on syntactic and semantic transfer rules.

2.1. Check Down

Down

1. BACK-TRANSLATION
2. SUBWORD UNITS
3. TOKENIZATION
4. ALIGNMENT
5. WORD EMBEDDINGS
6. DOMAIN ADAPTATION
7. CROSS-LINGUAL TRANSFER
8. MULTILINGUAL TRANSLATION
9. LOW-RESOURCE LANGUAGES
10. OUT-OF-VOCABULARY WORDS
11. POST-EDITING
12. SYNTACTIC PARSING
13. MORPHOLOGICAL ANALYSIS
14. LEXICAL DISAMBIGUATION
15. SEMANTIC ROLE LABELING
16. LANGUAGE PAIR
17. PIVOT LANGUAGE
18. CONTEXTUAL EMBEDDINGS
19. DATA AUGMENTATION
20. BEAM SEARCH
21. DROPOUT
22. PARALLEL SENTENCE MINING
23. TRANSLATIONESE
24. INTERACTIVE MT
25. CORPUS-BASED MT
26. PHRASE TABLE
27. CROSS-ENTROPY LOSS
28. NEURAL LANGUAGE MODEL
29. KNOWLEDGE DISTILLATION
30. TRANSFER-BASED MT