Báo cáo khoa học: "Learning to Rank Answers on Large Online QA Collections" pptx

... situation is different once one moves beyond the task of factoid QA. Comparatively little research has focused on QA models for non-factoid ques- tions such as causation, manner, or reason questions. Because ... 2008. c 2008 Association for Computational Linguistics Learning to Rank Answers on Large Online QA Collections Mihai Surdeanu, Massimiliano Ciaramita, Hugo Zaragoz...

Ngày tải lên: 31/03/2014, 00:20

... focus on the ranking of definitions and not on the interaction with users in this paper. We also assume that the definitions to be ranked are given. Section 2 describes the task of ranking definitions, and ... deviation of 0.13. Finally, taking the means of ranks given to each definition, we merged the indi- vidual rankings to create the reference rankings. An example of a reference ran...

Ngày tải lên: 08/03/2014, 03:20

Ngày tải lên: 23/03/2014, 17:20

... the solutions to Eq. 2 also solutions to Eq. 1 (i.e. pareto-optimal) and vice-versa? The theory says: Theorem 1. Sufficient Condition: If w ∗ is solution to Eq. 2, then it is weakly pareto-optimal. ... method not only learns to dis- criminate pareto vs. non-pareto but also also learns to discriminate among competing non-pareto points. Also, like other MT works, in line 5 the N-best l...

Ngày tải lên: 19/02/2014, 19:20

... 3 Method To find translations for a given term on the Web, a promising approach is automatically learning to extract phrasal translations or transliterations of phrase based on machine learning, ... information to generate transliteration feature for a Chinese token with respect to English words in the query. We extract person or location entries in Wikipedia as name trans...

Ngày tải lên: 19/02/2014, 19:20

... algorithm is not dependent on a determin- istic transition function and can be applied to domains with stochastic transitions, such as robot locomotion. 808 4.2 Action An action a ∈ A is composed of ... clarification or giving con- firmation. The landmarks on the instruction fol- lower map sometimes differ in location from the instruction giver’s. We ignore this caveat, giving the system...

Ngày tải lên: 20/02/2014, 04:20

... user to work on the given solution • - ask user to commit solution implementation User found solution useful - encourage the user to work on the solution • • • • - ask user to commit solution implementation ... harder to detect than others, the system’s classification accuracy depends largely on the user’s barrier. To prevent classification accuracy distorting the user evaluat...

Ngày tải lên: 20/02/2014, 12:20

... 1234567890123456789012345678901234567890123456789012345678901234567890 01: Raw-steel production by the nation's mills increased 4~ last week to 02:1,833,000 tons from 1,570,000 tons the previous week, the American Iron and Steel Institute said. 03: ... table can contain caption or title information, like "How Some Highly Con- ditionai 'Bids' Fared", or header...

Ngày tải lên: 20/02/2014, 19:20

Ngày tải lên: 22/02/2014, 03:20

... learn from data whether to rely on syntax or not, or to revert back to mono- tone phrase-based translation. In experiments on Chinese-English and Arabic- English translation, we find that when both ... tree -to- tree ex- traction does not lose any rules relative to string- to- string extraction. On the other hand, if several rules are extracted 1446 that differ only in their non...

Ngày tải lên: 07/03/2014, 22:20