TAILIEUCHUNG - Báo cáo khoa học: "Where's the Verb? Correcting Machine Translation During Question Answering"

When a multi-lingual question-answering (QA) system provides an answer that has been incorrectly translated, it is very likely to be regarded as irrelevant. In this paper, we propose a novel method for correcting a deletion error that affects overall understanding of the sentence. Our post-editing technique uses information available at query time: examples drawn from related documents determined to be relevant to the query. | Where s the Verb Correcting Machine Translation During Question Answering Wei-Yun Ma Kathleen McKeown Department of Computer Science Columbia University New York NY 10027 UsA ma kathy @ Abstract When a multi-lingual question-answering QA system provides an answer that has been incorrectly translated it is very likely to be regarded as irrelevant. In this paper we propose a novel method for correcting a deletion error that affects overall understanding of the sentence. Our post-editing technique uses information available at query time examples drawn from related documents determined to be relevant to the query. Our results show that 4 -7 of MT sentences are missing the main verb and on average 79 of the modified sentences are judged to be more comprehensible. The QA performance also benefits from the improved MT 7 of irrelevant response sentences become relevant. 1. Introduction We are developing a multi-lingual questionanswering QA system that must provide relevant English answers for a given query drawing pieces of the answer from translated foreign source. Relevance and translation quality are usually inseparable an incorrectly translated sentence in the answer is very likely to be regarded as irrelevant even when the corresponding source language sentence is actually relevant. We use a phrase-based statistical machine translation system for the MT component and thus for us MT serves as a black box that produces the translated documents in our corpus we cannot change the MT system itself. As MT is used in more and more multi-lingual applications this situation will become quite common. We propose a novel method which uses redundant information available at questionanswering time to correct errors. We present a post-editing mechanism to both detect and correct errors in translated documents determined to be relevant for the response. In this paper we focus on cases where the main verb of a Chinese sentence has not been translated. The main verb .

• Báo cáo khoa học
• Wheres the Verb
• Correcting Machine Translation During Question Answerin
• Wei Yun Ma
• báo cáo khoa học
• báo cáo 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 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