We need a measured approach to metrics
نویسندگان
چکیده
منابع مشابه
Changing the Conversation, Why We Need to Reframe Corruption as a Public Health Issue; Comment on “We Need to Talk About Corruption in Health Systems”
There has been slow progress with finding practical solutions to health systems corruption, a topic that has long languished in policy-makers “too difficult tray.” Efforts to achieve universal health coverage (UHC) provide a new imperative for addressing the long-standing problem of corruption in health systems making fighting corruption at all levels and in all its for...
متن کاملWhy We Need a Non-reductionist Approach to Trust
Dynamic trust federation in grids p. 3 Being trusted in a social network : trust as relational capital p. 19 A requirements-driven trust framework for secure interoperation in open environments p. 33 Normative structures in trust management p. 48 Gathering experience in trust-based interactions p. 62 Multilateral decisions for collaborative defense against unsolicited bulk e-mail p. 77 Generati...
متن کاملWe Need to Talk About Corruption in Health Systems
The health sector consistently appears prominently in surveys of perceived corruption, with considerable evidence that this has serious adverse consequences for patients. Yet this issue is far from prominent in the international health policy discourse. We identify five reasons why the health policy community has been reluctant to talk about it. These are the problem of defining corruption, the...
متن کاملDo we need a new approach to making vaccine recommendations?
We are on a steep trajectory away from an era of inexpensive vaccines for diseases that are widespread in the absence of immunisation. Vaccines are increasingly being produced for diseases that are devastating at an individual level but have less impact on population health. Moreover, the costs of developing and getting a vaccine tomarket are rising because of increasingly complex technologies ...
متن کاملWhy We Need New Evaluation Metrics for NLG
The majority of NLG evaluation relies on automatic metrics, such as BLEU. In this paper, we motivate the need for novel, systemand data-independent automatic evaluation methods: We investigate a wide range of metrics, including state-of-the-art word-based and novel grammar-based ones, and demonstrate that they only weakly reflect human judgements of system outputs as generated by data-driven, e...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Nature
سال: 2015
ISSN: 0028-0836,1476-4687
DOI: 10.1038/523129a