tailieunhanh - Báo cáo khoa học: "Underspecifying and Predicting Voice for Surface Realisation Ranking"

This paper addresses a data-driven surface realisation model based on a large-scale reversible grammar of German. We investigate the relationship between the surface realisation performance and the character of the input to generation, . its degree of underspecification. We extend a syntactic surface realisation system, which can be trained to choose among word order variants, such that the candidate set includes active and passive variants. | Underspecifying and Predicting Voice for Surface Realisation Ranking Sina Zarriefi Aoife Cahill and Jonas Kuhn Institut fur maschinelle Sprachverarbeitung Universitat Stuttgart Germany @ Abstract This paper addresses a data-driven surface realisation model based on a large-scale reversible grammar of German. We investigate the relationship between the surface realisation performance and the character of the input to generation . its degree of underspecification. We extend a syntactic surface realisation system which can be trained to choose among word order variants such that the candidate set includes active and passive variants. This allows us to study the interaction of voice and word order alternations in realistic German corpus data. We show that with an appropriately underspecified input a linguistically informed realisation model trained to regenerate strings from the underlying semantic representation achieves accuracy over a baseline of in the prediction of the original voice. 1 Introduction This paper1 presents work on modelling the usage of voice and word order alternations in a free word order language. Given a set of meaning-equivalent candidate sentences such as in the simplified English Example 1 our model makes predictions about which candidate sentence is most appropriate or natural given the context. 1 Context The Parliament started the debate about the state budget in April. a. It wasn t until June that the Parliament approved it. b. It wasn t until .lime that it was approved by the Parliament. c. It wasn t until .une that it was approved. We address the problem of predicting the usage of linguistic alternations in the framework of a surface 1This work has been supported by the Deutsche Forschungs-gemeinschaft DFG German Research Foundation in SFB 732 Incremental specification in context project D2 Pls Jonas Kuhn and Christian Rohrer . 1007 realisation ranking system. Such .

TỪ KHÓA LIÊN QUAN
TÀI LIỆU MỚI ĐĂNG
31    253    0    29-04-2024
46    187    0    29-04-2024
8    176    0    29-04-2024
22    121    0    29-04-2024
41    122    0    29-04-2024
7    128    0    29-04-2024
crossorigin="anonymous">
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.