TAILIEUCHUNG - Báo cáo khoa học: "Improving QA Accuracy by Question Inversion"

This paper demonstrates a conceptually simple but effective method of increasing the accuracy of QA systems on factoid-style questions. We define the notion of an inverted question, and show that by requiring that the answers to the original and inverted questions be mutually consistent, incorrect answers get demoted in confidence and correct ones promoted. Additionally, we show that lack of validation can be used to assert no-answer (nil) conditions. We demonstrate increases of performance on TREC and other question-sets, and discuss the kinds of future activities that can be particularly beneficial to approaches such as ours. . | Improving QA Accuracy by Question Inversion John Prager IBM . Watson Res. Ctr. Yorktown Heights jprager@ Pablo Duboue IBM . Watson Res. Ctr. Yorktown Heights . 10598 duboue@ Abstract This paper demonstrates a conceptually simple but effective method of increasing the accuracy of QA systems on factoid-style questions. We define the notion of an inverted question and show that by requiring that the answers to the original and inverted questions be mutually consistent incorrect answers get demoted in confidence and correct ones promoted. Additionally we show that lack of validation can be used to assert no-answer nil conditions. We demonstrate increases of performance on TREC and other question-sets and discuss the kinds of future activities that can be particularly beneficial to approaches such as ours. 1 Introduction Most QA systems nowadays consist of the following standard modules Question Processing to determine the bag of words for a query and the desired answer type the type of the entity that will be offered as a candidate answer search which will use the query to extract a set of documents or passages from a corpus and Answer SelectIon which will analyze the returned documents or passages for instances of the answer type in the most favorable contexts. Each of these components implements a set of heuristics or hypotheses as devised by their authors cf. Clarke et al. 2001 Chu-Carroll et al. 2003 . When we perform failure analysis on questions incorrectly answered by our system we find that there are broadly speaking two kinds of failure. There are errors we might call them bugs on the implementation of the said heuristics errors in tagging parsing named-entity recognition omissions in synonym lists missing patterns and just plain programming errors. This class can be characterized by being fixable by identifying incorrect code and fixing it or adding more items either explicitly or through training. The other class of .

• Báo cáo khoa học
• Improving QA Accuracy
• Question Inversion
• John Prager
• báo cáo khoa học
• mô hình ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• Bài giảng Xử lý ngôn ngữ tự nhiên
• Ngôn ngữ tự nhiên
• Kỹ thuật lập trình
• Xử lý nhập nhằng ngữ nghĩa
• Xử lý ngữ nghĩa
• Xử lý ngôn ngữ
• Natural Language Processing
• Ngôn ngữ lập trình
• Nhập nhằng cấu trúc
• Tri thức về ngôn ngữ
• Mô hình n gram
• Dịch máy
• Phương pháp dịch máy
• Hiểu ngôn ngữ
• Phân tích ngữ nghĩa
• Phân loại tin tự động
• Biểu diễn vị từ
• Thuộc tính về sự kiện
• Thuộc tính về sự kiện
• Mô hình ngôn ngữ Google Book N grams
• Mô hình ngôn ngữ KenLM
• Phương pháp làm mịn
• Tách từ tiếng Việt
• Gán nhãn từ loại
• Phân tích cú pháp
• Nghĩa từ vựng
• Phân giải nhập nhằng từ
• Phân loại văn bản
• Lexical chain
• Phản hồi thông tin
• Bài toán PTCP
• Cấu trúc ngữ pháp
• Phân tích cú pháp xác suất
• CKY kết hợp xác suất
• Văn phạm phi ngữ cảnh xác suất
• Hình thái học