Although considerable efforts have been devoted to transformer-based ranking models for document search, the relevance-efficiency tradeoff remains a critical problem for ad-hoc ranking. To overcome this challenge, this paper presents BECR (BERT-based Composite Re-Ranking), a composite re-ranking scheme that combines deep contextual token interactions and traditional lexical term-matching features. In particular, BECR exploits a token encoding mechanism to decompose the query representations into pre-computable uni-grams and skip-n-grams. By applying token encoding on top of a dual-encoder architecture, BECR separates the attentions between a query and a document while capturing the contextual semantics of a query. In contrast to previous approaches, this framework does not perform expensive BERT computations during online inference. Thus, it is significantly faster, yet still able to achieve high competitiveness in ad-hoc ranking relevance. Finally, an in-depth comparison between BECR and other start-of-the-art neural ranking baselines is described using the TREC datasets, thereby further demonstrating the enhanced relevance and efficiency of BECR.
In this paper, we study the cross-modal image retrieval, where the inputs contain a source image plus some text that describes certain modifications to this image and the desired image. Prior work usually uses a three-stage strategy to tackle this task: 1) extract the features of the inputs; 2) fuse the feature of the source image and its modified text to obtain fusion feature; 3) learn a similarity metric between the desired image and the source image + modified text by using deep metric learning. Since classical image/text encoders can learn the useful representation and common pair-based loss functions of distance metric learning are enough for cross-modal retrieval, people usually improve retrieval accuracy by designing new fusion networks. However, these methods do not successfully handle the modality gap caused by the inconsistent distribution and representation of the features of different modalities, which greatly influences the feature fusion and similarity learning. To alleviate this problem, we adopt the contrastive self-supervised learning method Deep InforMax (DIM) to our approach to bridge this gap by enhancing the dependence between the text, the image, and their fusion. Specifically, our method narrows the modality gap between the text modality and the image modality by maximizing mutual information between their not exactly semantically identical representation. Moreover, we seek an effective common subspace for the semantically same fusion feature and desired image's feature by utilizing Deep InforMax between the low-level layer of the image encoder and the high-level layer of the fusion network. Extensive experiments on three large-scale benchmark datasets show that we have bridged the modality gap between different modalities and achieve state-of-the-art retrieval performance.
Recent years have witnessed deep neural networks gaining increasing popularity in the field of time series forecasting. A primary reason of their success is their ability to effectively capture complex temporal dynamics across multiple related time series. However, the advantages of these deep forecasters only start to emerge in the presence of a sufficient amount of data. This poses a challenge for typical forecasting problems in practice, where one either has a small number of time series, or limited observations per time series, or both. To cope with the issue of data scarcity, we propose a novel domain adaptation framework, Domain Adaptation Forecaster (DAF), that leverages the statistical strengths from another relevant domain with abundant data samples (source) to improve the performance on the domain of interest with limited data (target). In particular, we propose an attention-based shared module with a domain discriminator across domains as well as private modules for individual domains. This allows us to jointly train the source and target domains by generating domain-invariant latent features while retraining domain-specific features. Extensive experiments on various domains demonstrate that our proposed method outperforms state-of-the-art baselines on synthetic and real-world datasets.
Recent years have witnessed deep neural net-works gaining increasing popularity in the field oftime series forecasting. A primary reason of theirsuccess is their ability to effectively capture com-plex temporal dynamics across multiple relatedtime series. However, the advantages of thesedeep forecasters only start to emerge in the pres-ence of a sufficient amount of data. This poses achallenge for typical forecasting problems in prac-tice, where one either has a small number of timeseries, or limited observations per time series, orboth. To cope with the issue of data scarcity, wepropose a novel domain adaptation framework,Domain Adaptation Forecaster (DAF), that lever-ages the statistical strengths from another relevantdomain with abundant data samples (source) toimprove the performance on the domain of inter-est with limited data (target). In particular, we pro-pose an attention-based shared module with a do-main discriminator across domains as well as pri-vate modules for individual domains. This allowsus to jointly train the source and target domains bygenerating domain-invariant latent features whileretraining domain-specific features. Extensive ex-periments on various domains demonstrate thatour proposed method outperforms state-of-the-artbaselines on synthetic and real-world datasets.
Expert networks are formed by a group of expert-professionals with different specialties to collaboratively resolve specific queries posted to the network. In such networks, when a query reaches an expert who does not have sufficient expertise, this query needs to be routed to other experts for further processing until it is completely solved; therefore, query answering efficiency is sensitive to the underlying query routing mechanism being used. Among all possible query routing mechanisms, decentralized search, operating purely on each expert's local information without any knowledge of network global structure, represents the most basic and scalable routing mechanism, which is applicable to any network scenarios even in dynamic networks. However, there is still a lack of fundamental understanding of the efficiency of decentralized search in expert networks. In this regard, we investigate decentralized search by quantifying its performance under a variety of network settings. Our key findings reveal the existence of network conditions, under which decentralized search can achieve significantly short query routing paths (i.e., between $O(\log n)$ and $O(\log^2 n)$ hops, $n$: total number of experts in the network). Based on such theoretical foundation, we further study how the unique properties of decentralized search in expert networks is related to the anecdotal small-world phenomenon. In addition, we demonstrate that decentralized search is robust against estimation errors introduced by misinterpreting the required expertise levels. To the best of our knowledge, this is the first work studying fundamental behaviors of decentralized search in expert networks. The developed performance bounds, confirmed by real datasets, are able to assist in predicting network performance and designing complex expert networks.
Existing studies on question answering on knowledge bases (KBQA) mainly operate with the standard i.i.d assumption, i.e., training distribution over questions is the same as the test distribution. However, i.i.d may be neither reasonably achievable nor desirable on large-scale KBs because 1) true user distribution is hard to capture and 2) randomly sample training examples from the enormous space would be highly data-inefficient. Instead, we suggest that KBQA models should have three levels of built-in generalization: i.i.d, compositional, and zero-shot. To facilitate the development of KBQA models with stronger generalization, we construct and release a new large-scale, high-quality dataset with 64,331 questions, GrailQA, and provide evaluation settings for all three levels of generalization. In addition, we propose a novel BERT-based KBQA model. The combination of our dataset and model enables us to thoroughly examine and demonstrate, for the first time, the key role of pre-trained contextual embeddings like BERT in the generalization of KBQA.
COVID-19 pandemic has an unprecedented impact all over the world since early 2020. During this public health crisis, reliable forecasting of the disease becomes critical for resource allocation and administrative planning. The results from compartmental models such as SIR and SEIR are popularly referred by CDC and news media. With more and more COVID-19 data becoming available, we examine the following question: Can a direct data-driven approach without modeling the disease spreading dynamics outperform the well referred compartmental models and their variants? In this paper, we show the possibility. It is observed that as COVID-19 spreads at different speed and scale in different geographic regions, it is highly likely that similar progression patterns are shared among these regions within different time periods. This intuition lead us to develop a new neural forecasting model, called Attention Crossing Time Series (\textbf{ACTS}), that makes forecasts via comparing patterns across time series obtained from multiple regions. The attention mechanism originally developed for natural language processing can be leveraged and generalized to materialize this idea. Among 13 out of 18 testings including forecasting newly confirmed cases, hospitalizations and deaths, \textbf{ACTS} outperforms all the leading COVID-19 forecasters highlighted by CDC.