Language Processing and Translation Technology Developments

Automated machine translation system that improves translation quality by preprocessing the source text before translation. The preprocessing involves steps like sentence splitting, simplification, named entity recognition, matching against existing translations, and applying transformational grammar. The goal is to generate semantically meaningful, less complex ordered tokens from the source text that are easier to translate accurately.

Source

Cross-lingual adaptation of language models for low-resource languages using disentangled syntax and shared conceptual latent space. The method involves converting multilingual input sentences into linearized constituency parse trees, masking leaf nodes to separate semantics, passing to a syntactic encoder, and determining if a new language is being learned. For similar scripts, transliteration aligns with syntax. For unique scripts, pseudo translation aligns semantics. This disentangles syntax from concepts, leverages relatedness for adaptation, and improves low-resource cross-lingual performance.

Source

Configuring multiple neural networks to translate documents with hierarchical structure by generating mappings between word locations, meanings, and grammatical rules in the source and destination languages. This provides a way to improve translation accuracy and efficiency by capturing the hierarchical structure of the languages and training neural networks to make corrections based on those mappings. The method involves collecting data in the destination language, generating mappings for word locations, meanings, and grammatical rules, training neural networks on corrections based on those mappings, and using the trained networks to translate documents.

Source

Automated document analysis that emulates human analysis for rapid, low-cost processing of large document sets across many languages. The system uses anomaly detection, word frequency analysis, and ranking metrics to identify and analyze the most important and representative parts of documents like patent claims. This allows efficient analysis of large numbers of documents at rates much faster than manual analysis.

Source

Method and apparatus for generating documents using natural language processing and a dynamic user interface. The system receives text input and produces a flowchart representing the logic and conditions in the text. This flowchart is then converted into a structured document like a contract using templates.

Source

Method for generating patent applications using a dynamic user interface and natural language processing. User interface with objects that can be filled in, dropped into by phrases from claims. The phrases are converted into content for the patent application. The claims are analyzed to identify phrases and their type (e.g., adjective vs verb phrase) and context. The phrases are converted into sentences with proper subject and context. The phrases can be matched with related descriptions in drawings or other documents to improve accuracy.

Source

A method for creating a patent document summary that involves leveraging natural language processing and machine learning techniques to analyze the text of a patent document and generate a concise summary that captures key information from the document. The method involves identifying repetitive word sequences in the document, replacing subsequent occurrences of those sequences with shorter substitutes, and generating the summary based on the modified text.

Source

Generating accurate text for patent applications by combining natural language processing with structured templating. A system uses natural language understanding (NLU) to parse input text and extract structured components. It then leverages natural language generation (NLG) to generate precise output text using a templating language enhanced with functions that manipulate the text based on the data model. This allows the system to generate patent application sections by extracting claims structures from existing applications and inserting the parts into a claim model data object.

Source

Hybrid translation system that combines the strengths of general-purpose neural machine translation with domain-specific translation dictionaries to improve accuracy and suitability for specific fields. The system receives a document, determines the field, translates using a general neural network, then converts some terms from the general translation into more specialized terms from a dictionary for the determined field.

Source

Customizable automatic document translation that allows users to specify translation attributes like adequacy or fluency. When translating a source document, the system uses a machine translator with the specified attribute. It then analyzes the resulting target document and provides a different translation attribute for feedback. This iterative process allows users to balance accuracy and readability in the translations.

Source

Automated machine translation of languages to convert sentences from one natural language into another language using computers. The goal is to have machines accurately translate sentences between different human languages without human intervention.

Source

Automatically translating patent claims from one language to another using a computer-based system that extracts key nouns and phrases from the claim definitions, translates those elements individually, and then combines them into a coherent translated claim. This approach improves accuracy compared to generic automatic translation tools which struggle with the complex grammar and syntax of patent claims.

Source

Automatically translating patent claims from one language to another in a way that makes them easier to understand. The translation is done by organizing the claim elements like nouns, verbs and objects into a structured sentence, then translating them in a specific sequence based on grammatical attributes, such as subordinate clauses, participles, and prepositions. This allows claims to be translated in a more accurate and reliable manner compared to standard machine translation methods.

Source

Machine translation system that combines syntax conversion and word translation models to improve naturalness and appropriateness of machine translations. The system learns syntax conversion and word translation knowledge from parallel corpora, applies them to source sentences in real time, and generates target sentences through decoding processes of a syntax converter and a word translator. This allows changing the word order in the target sentence like syntax-based translation while also translating consecutive words like phrase-based translation. The syntax converter extracts syntax features from the source sentence and the word translator generates target words constrained by the syntax. The syntax converter's output syntax and the word translator's output words are combined with weights learned from the parallel corpora to generate the final target sentence.

Source

Automatically calculating translation costs for patent specifications using a computer system that leverages translation memory analysis. The system receives an original patent specification and a source-target language pair. It compares the original text with previously translated text sections in the same language pair stored in a translation memory. It calculates a modified word count based on the degree of overlap between the original and previously translated text. It then looks up a per-word translation rate for the language pair to compute the modified translation cost.

Source

Hybrid machine translation system that combines rule-based and statistical translation techniques to improve accuracy and speed of translating text and speech between languages. The system uses a hybrid machine translation engine that leverages the strengths of both rule-based and statistical methods to translate source text into target text. It involves a database with source and target text, rule-based and statistical models, and a hybrid translation engine that uses directed acyclic graphs (DAGs) annotated with semantic rules. The engine applies maximum entropy algorithm to weigh inputs from statistical and rule-based translation systems.

Source

A computerized system for improving machine translation accuracy using a phrasal decoder trained on monolingual parallel corpora. The decoder learns mappings between machine translation outputs and human translations to correct raw machine translation outputs. It processes the raw output at run-time and produces a more accurate translated output for display. This reduces the need for expensive human editors by using a trained decoder to automatically improve machine translation quality.

Source

Integrating statistical machine translation (SMT) and translation memory (TM) systems to improve the accuracy of machine translation when annotations are present in the source document. The system distinguishes between annotations and word strings, translating annotations using rules instead of SMT. This allows accurate translation of annotated segments even if they haven't been seen before, while still using SMT for unannotated segments.

Source