Refinements to Interactive Translation Prediction Based on Search Graphs
نویسندگان
چکیده
We propose a number of refinements to the canonical approach to interactive translation prediction. By more permissive matching criteria, placing emphasis on matching the last word of the user prefix, and dealing with predictions to partially typed words, we observe gains in both word prediction accuracy (+5.4%) and letter prediction accuracy (+9.3%).
منابع مشابه
Neural Interactive Translation Prediction
We present an interactive translation prediction method based on neural machine translation. Even with the same translation quality of the underlying machine translation systems, the neural prediction method yields much higher word prediction accuracy (61.6% vs. 43.3%) than the traditional method based on search graphs, mainly due to better recovery from errors. We also develop efficient means ...
متن کاملOn the optimal decision rule for sequential interactive structured prediction
Interactive structured prediction (ISP) is an emerging framework for structured prediction (SP) where the user and the system collaborate to produce a high quality output. Typically, search algorithms applied to ISP problems have been based on the algorithms for fully-automatic SP systems. However, the decision rule applied should not be considered as optimal since the goal in ISP is to reduce ...
متن کاملThe Effect of Metapragmatic Awareness, Interactive Translation, and Discussion through Video-Enhanced Input on EFL Learners’ Comprehension of Implicature
It is substantiated that particular features of pragmatics are teachable, and instruction is both necessary and effective. Determining what kind of intervention is most effectual for facilitating learners’ pragmatic development has been a central issue for researchers. To respond to the inconclusive findings in intervention studies and to extend the instructional studies in L2 pragmatics to les...
متن کاملImproved Search Strategy for Interactive Predictions in Computer-Assisted Translation
The statistical machine translation outputs are not error-free and in a high quality yet. So in the cases that we need high quality translations we definitely need the human intervention. An interactive-predictive machine translation is a framework, which enables the collaboration of the human and the translation system. Here, we address the problem of searching the best suffix to propose to th...
متن کاملSupervised graph summarization for structuring academic search results
In this paper we address the problem of visualizing the query results of the academic search services. We suggest representing the search results as concise topic hierarchies, and propose a method of building such hierarchies through summarization of the intermediate large topic graphs. We describe a supervised learning technique for summarizing the topic graphs in the most informative way usin...
متن کامل