TAILIEUCHUNG - Báo cáo khoa học: "Computational Approaches to Sentence Completion"

This paper studies the problem of sentencelevel semantic coherence by answering SATstyle sentence completion questions. These questions test the ability of algorithms to distinguish sense from nonsense based on a variety of sentence-level phenomena. We tackle the problem with two approaches: methods that use local lexical information, such as the n-grams of a classical language model; and methods that evaluate global coherence, such as latent semantic analysis. | Computational Approaches to Sentence Completion Geoffrey Zweig John C. Platt Christopher Meek Christopher . Burges Microsoft Research Redmond WA 98052 Ainur Yessenalina Cornell University Computer Science Dept. Ithaca NY 14853 Qiang Liu Univ. of California Irvine Info. Comp. Sci. Irvine California 92697 Abstract This paper studies the problem of sentencelevel semantic coherence by answering SAT-style sentence completion questions. These questions test the ability of algorithms to distinguish sense from nonsense based on a variety of sentence-level phenomena. We tackle the problem with two approaches methods that use local lexical information such as the n-grams of a classical language model and methods that evaluate global coherence such as latent semantic analysis. We evaluate these methods on a suite of practice SAT questions and on a recently released sentence completion task based on data taken from five Conan Doyle novels. We find that by fusing local and global information we can exceed 50 on this task chance baseline is 20 and we suggest some avenues for further research. 1 Introduction In recent years standardized examinations have proved a fertile source of evaluation data for language processing tasks. They are valuable for many reasons they represent facets of language understanding recognized as important by educational experts they are organized in various formats designed to evaluate specific capabilities they are yardsticks by which society measures educational progress and they affect a large number of people. Previous researchers have taken advantage of this material to test both narrow and general language processing capabilities. Among the narrower tasks the identification of synonyms and antonyms has 601 been studied by Landauer and Dumais 1997 Mohammed et al. 2008 Mohammed et al. 2011 Turney et al. 2003 Turney 2008 who used questions from the Test of English as a Foreign Language TOEFL Graduate Record Exams GRE and English as a Second .

TỪ KHÓA LIÊN QUAN
TAILIEUCHUNG - Chia sẻ tài liệu không giới hạn
Địa chỉ : 444 Hoang Hoa Tham, Hanoi, Viet Nam
Website : tailieuchung.com
Email : tailieuchung20@gmail.com
Tailieuchung.com là thư viện tài liệu trực tuyến, nơi chia sẽ trao đổi hàng triệu tài liệu như luận văn đồ án, sách, giáo trình, đề thi.
Chúng tôi không chịu trách nhiệm liên quan đến các vấn đề bản quyền nội dung tài liệu được thành viên tự nguyện đăng tải lên, nếu phát hiện thấy tài liệu xấu hoặc tài liệu có bản quyền xin hãy email cho chúng tôi.
Đã phát hiện trình chặn quảng cáo AdBlock
Trang web này phụ thuộc vào doanh thu từ số lần hiển thị quảng cáo để tồn tại. Vui lòng tắt trình chặn quảng cáo của bạn hoặc tạm dừng tính năng chặn quảng cáo cho trang web này.