How AI Understands Answers Across Multiple Documents

Microsoft's 2024 patent on using AI to find answers by understanding how information in one document relates to information in another.

What it covers

This patent describes a method for a computer to find answers to a query. It starts by getting a query and then finding several documents that might contain the answer. These documents are broken down into 'tokens' (like words or parts of words). The system then uses a special AI model, called a transformer, to process these tokens. The key part is that the AI learns to pay 'attention' to how tokens in one document relate to tokens in another document. For example, it can see how a word in a first document helps explain a word in a second document. This helps the AI create a better understanding of the information and then pick out the specific tokens that form the answer to the original query, which is then presented to the user. Claim 21 specifically mentions propagating attention from first tokens of a first result document to second tokens of a second result document.

What it doesn't cover

• —Methods that do not use a transformer-based machine learning model.
• —Systems that only process a single document to find an answer.
• —Methods that do not involve propagating attention between tokens from different documents.
• —Systems that do not output an answer in response to a query.
• —AI models that do not generate contextualized semantic representations of words.

The clever bit

The innovation lies in teaching an AI to understand how information in one document 'attends' to or relates to information in another document. This allows the AI to build a richer, interconnected understanding of the data, leading to more precise answer extraction.

Why it matters

This technology is crucial for modern search engines and AI assistants that need to synthesize information from multiple sources. It enables systems to go beyond simply finding documents and instead understand the relationships between pieces of information across those documents to provide more direct and accurate answers.

Real-world examples

• 1.AI-powered search engines
• 2.Virtual assistants like Cortana
• 3.Document analysis tools
• 4.Information retrieval systems