The recent MSMARCO passage retrieval collection has allowed researchers to develop highly tuned retrieval systems. One aspect of this data set that makes it distinctive compared to traditional corpora is that most of the topics only have a single answer passage marked relevant. Here we carry out a "what if" sensitivity study, asking whether a set of systems would still have the same relative performance if more passages per topic were deemed to be "relevant", exploring several mechanisms for identifying sets of passages to be so categorized. Our results show that, in general, while run scores can vary markedly if additional plausible passages are presumed to be relevant, the derived system ordering is relatively insensitive to additional relevance, providing support for the methodology that was used at the time the MSMARCO passage collection was created.
相關內容
Most governments employ a set of quasi-standard measures to fight COVID-19 including wearing masks, social distancing, virus testing, contact tracing, and vaccination. However, combining these measures into an efficient holistic pandemic response instrument is even more involved than anticipated. We argue that some non-trivial factors behind the varying effectiveness of these measures are selfish decision making and the differing national implementations of the response mechanism. In this paper, through simple games, we show the effect of individual incentives on the decisions made with respect to mask wearing, social distancing and vaccination, and how these may result in sub-optimal outcomes. We also demonstrate the responsibility of national authorities in designing these games properly regarding data transparency, the chosen policies and their influence on the preferred outcome. We promote a mechanism design approach: it is in the best interest of every government to carefully balance social good and response costs when implementing their respective pandemic response mechanism; moreover, there is no one-size-fits-all solution when designing an effective solution.
Randomized controlled trials (RCT's) allow researchers to estimate causal effects in an experimental sample with minimal identifying assumptions. However, to generalize or transport a causal effect from an RCT to a target population, researchers must adjust for a set of treatment effect moderators. In practice, it is impossible to know whether the set of moderators has been properly accounted for. In the following paper, I propose a three parameter sensitivity analysis for generalizing or transporting experimental results using weighted estimators, with several advantages over existing methods. First, the framework does not require assumptions on the underlying data generating process for either the experimental sample selection mechanism or treatment effect heterogeneity. Second, I show that the sensitivity parameters are guaranteed to be bounded and propose several tools researchers can use to perform sensitivity analysis: (1) graphical and numerical summaries for researchers to assess how robust a point estimate is to killer confounders; (2) an extreme scenario analysis; and (3) a formal benchmarking approach for researchers to estimate potential sensitivity parameter values using existing data. Finally, I demonstrate that the proposed framework can be easily extended to the class of doubly robust, augmented weighted estimators. The sensitivity analysis framework is applied to a set of Jobs Training Program experiments.
Analytical database systems are typically designed to use a column-first data layout to access only the desired fields. On the other hand, storing data row-first works great for accessing, inserting, or updating entire rows. Transforming rows to columns at runtime is expensive, hence, many analytical systems ingest data in row-first form and transform it in the background to columns to facilitate future analytical queries. How will this design change if we can always efficiently access only the desired set of columns? To address this question, we present a radically new approach to data transformation from rows to columns. We build upon recent advancements in embedded platforms with re-programmable logic to design native in-memory access on rows and columns. Our approach, termed Relational Memory, relies on an FPGA- based accelerator that sits between the CPU and main memory and transparently transforms base data to any group of columns with minimal overhead at runtime. This design allows accessing any group of columns as if it already exists in memory. We implement and deploy Relational Memory in real hardware, and we show that we can access the desired columns up to 1.63x faster than accessing them from their row-wise counterpart, while matching the performance of a pure columnar access for low projectivity, and outperforming it by up to 1.87x as projectivity (and tuple re-construction cost) increases. Moreover, our approach can be easily extended to support offloading of a number of operations to hardware, e.g., selection, group by, aggregation, and joins, having the potential to vastly simplify the software logic and accelerate the query execution.
Memory disaggregation addresses memory imbalance in a cluster by decoupling CPU and memory allocations of applications while also increasing the effective memory capacity for (memory-intensive) applications beyond the local memory limit imposed by traditional fixed-capacity servers. As the network speeds in the tightly-knit environments like modern datacenters inch closer to the DRAM speeds, there has been a recent proliferation of work in this space ranging from software solutions that pool memory of traditional servers for the shared use of the cluster to systems targeting the memory disaggregation in the hardware. In this report, we look at some of these recent memory disaggregation systems and study the important factors that guide their design, such as the interface through which the memory is exposed to the application, their runtime design and relevant optimizations to retain the near-native application performance, various approaches they employ in managing cluster memory to maximize utilization, etc. and we analyze the associated trade-offs. We conclude with a discussion on some open questions and potential future directions that can render disaggregation more amenable for adoption.
Recommender system is one of the most important information services on today's Internet. Recently, graph neural networks have become the new state-of-the-art approach of recommender systems. In this survey, we conduct a comprehensive review of the literature in graph neural network-based recommender systems. We first introduce the background and the history of the development of both recommender systems and graph neural networks. For recommender systems, in general, there are four aspects for categorizing existing works: stage, scenario, objective, and application. For graph neural networks, the existing methods consist of two categories, spectral models and spatial ones. We then discuss the motivation of applying graph neural networks into recommender systems, mainly consisting of the high-order connectivity, the structural property of data, and the enhanced supervision signal. We then systematically analyze the challenges in graph construction, embedding propagation/aggregation, model optimization, and computation efficiency. Afterward and primarily, we provide a comprehensive overview of a multitude of existing works of graph neural network-based recommender systems, following the taxonomy above. Finally, we raise discussions on the open problems and promising future directions of this area. We summarize the representative papers along with their codes repositories in //github.com/tsinghua-fib-lab/GNN-Recommender-Systems.
Recommender systems exploit interaction history to estimate user preference, having been heavily used in a wide range of industry applications. However, static recommendation models are difficult to answer two important questions well due to inherent shortcomings: (a) What exactly does a user like? (b) Why does a user like an item? The shortcomings are due to the way that static models learn user preference, i.e., without explicit instructions and active feedback from users. The recent rise of conversational recommender systems (CRSs) changes this situation fundamentally. In a CRS, users and the system can dynamically communicate through natural language interactions, which provide unprecedented opportunities to explicitly obtain the exact preference of users. Considerable efforts, spread across disparate settings and applications, have been put into developing CRSs. Existing models, technologies, and evaluation methods for CRSs are far from mature. In this paper, we provide a systematic review of the techniques used in current CRSs. We summarize the key challenges of developing CRSs into five directions: (1) Question-based user preference elicitation. (2) Multi-turn conversational recommendation strategies. (3) Dialogue understanding and generation. (4) Exploitation-exploration trade-offs. (5) Evaluation and user simulation. These research directions involve multiple research fields like information retrieval (IR), natural language processing (NLP), and human-computer interaction (HCI). Based on these research directions, we discuss some future challenges and opportunities. We provide a road map for researchers from multiple communities to get started in this area. We hope this survey helps to identify and address challenges in CRSs and inspire future research.
Since deep neural networks were developed, they have made huge contributions to everyday lives. Machine learning provides more rational advice than humans are capable of in almost every aspect of daily life. However, despite this achievement, the design and training of neural networks are still challenging and unpredictable procedures. To lower the technical thresholds for common users, automated hyper-parameter optimization (HPO) has become a popular topic in both academic and industrial areas. This paper provides a review of the most essential topics on HPO. The first section introduces the key hyper-parameters related to model training and structure, and discusses their importance and methods to define the value range. Then, the research focuses on major optimization algorithms and their applicability, covering their efficiency and accuracy especially for deep learning networks. This study next reviews major services and toolkits for HPO, comparing their support for state-of-the-art searching algorithms, feasibility with major deep learning frameworks, and extensibility for new modules designed by users. The paper concludes with problems that exist when HPO is applied to deep learning, a comparison between optimization algorithms, and prominent approaches for model evaluation with limited computational resources.
The bidirectional encoder representations from transformers (BERT) model has recently advanced the state-of-the-art in passage re-ranking. In this paper, we analyze the results produced by a fine-tuned BERT model to better understand the reasons behind such substantial improvements. To this aim, we focus on the MS MARCO passage re-ranking dataset and provide potential reasons for the successes and failures of BERT for retrieval. In more detail, we empirically study a set of hypotheses and provide additional analysis to explain the successful performance of BERT.
Humans gather information by engaging in conversations involving a series of interconnected questions and answers. For machines to assist in information gathering, it is therefore essential to enable them to answer conversational questions. We introduce CoQA, a novel dataset for building Conversational Question Answering systems. Our dataset contains 127k questions with answers, obtained from 8k conversations about text passages from seven diverse domains. The questions are conversational, and the answers are free-form text with their corresponding evidence highlighted in the passage. We analyze CoQA in depth and show that conversational questions have challenging phenomena not present in existing reading comprehension datasets, e.g., coreference and pragmatic reasoning. We evaluate strong conversational and reading comprehension models on CoQA. The best system obtains an F1 score of 65.1%, which is 23.7 points behind human performance (88.8%), indicating there is ample room for improvement. We launch CoQA as a challenge to the community at //stanfordnlp.github.io/coqa/
We propose the task of free-form and open-ended Visual Question Answering (VQA). Given an image and a natural language question about the image, the task is to provide an accurate natural language answer. Mirroring real-world scenarios, such as helping the visually impaired, both the questions and answers are open-ended. Visual questions selectively target different areas of an image, including background details and underlying context. As a result, a system that succeeds at VQA typically needs a more detailed understanding of the image and complex reasoning than a system producing generic image captions. Moreover, VQA is amenable to automatic evaluation, since many open-ended answers contain only a few words or a closed set of answers that can be provided in a multiple-choice format. We provide a dataset containing ~0.25M images, ~0.76M questions, and ~10M answers (www.visualqa.org), and discuss the information it provides. Numerous baselines and methods for VQA are provided and compared with human performance. Our VQA demo is available on CloudCV (//cloudcv.org/vqa).
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191