複雜話語的自然語言分解與解釋

摘要

自然語言界面通常需要監督數據，將用戶的請求翻譯為程序、數據庫查詢或其他結構化意圖表示。在數據收集過程中，很難預測並正式化用戶需求的全部範圍 -- 例如，在一個旨在處理簡單請求（如找出明天的會議或將我與經理的會議改到中午）的系統中，用戶也可能表達更複雜的請求（如交換星期一和星期二的所有通話）。我們介紹了一種方法，通過分層自然語言分解過程，使簡單的語言轉代碼模型能夠處理複雜的發話。我們的方法使用預訓練語言模型將複雜的發話分解為一系列較小的自然語言步驟，然後使用語言轉代碼模型解釋每個步驟。為了測試我們的方法，我們收集並發布了 DeCU -- 一個新的 NL-to-program 基準測試集，用於評估複雜發話的分解。實驗表明，所提出的方法能夠幾乎不需要複雜的訓練數據即可解釋複雜的發話，同時優於標準的少樣本提示方法。

English

Natural language interfaces often require supervised data to translate user requests into programs, database queries, or other structured intent representations. During data collection, it can be difficult to anticipate and formalize the full range of user needs -- for example, in a system designed to handle simple requests (like find my meetings tomorrow or move my meeting with my manager to noon), users may also express more elaborate requests (like swap all my calls on Monday and Tuesday). We introduce an approach for equipping a simple language-to-code model to handle complex utterances via a process of hierarchical natural language decomposition. Our approach uses a pre-trained language model to decompose a complex utterance into a sequence of smaller natural language steps, then interprets each step using the language-to-code model. To test our approach, we collect and release DeCU -- a new NL-to-program benchmark to evaluate Decomposition of Complex Utterances. Experiments show that the proposed approach enables the interpretation of complex utterances with almost no complex training data, while outperforming standard few-shot prompting approaches.

複雜話語的自然語言分解與解釋

Natural Language Decomposition and Interpretation of Complex Utterances

摘要

Support