arXiv subjects

Tao Shen

Publications and source records attributed to Tao Shen.

102 records · Page 6Linked to original sources

arXiv2020

Self-Attention Enhanced Patient Journey Understanding in Healthcare System

Understanding patients' journeys in healthcare system is a fundamental prepositive task for a broad range of AI-based healthcare applications. This task aims to learn an informative representation that can comprehensively encode hidden dependencies among medical events and its inner entities, and then the use of encoding outputs can greatly benefit the downstream application-driven tasks. A patient journey is a sequence of electronic health records (EHRs) over time that is organized at multiple levels: patient, visits and medical codes. The key challenge of patient journey understanding is to design an effective encoding mechanism which can properly tackle the aforementioned multi-level structured patient journey data with temporal sequential visits and a set of medical codes. This paper proposes a novel self-attention mechanism that can simultaneously capture the contextual and temporal relationships hidden in patient journeys. A multi-level self-attention network (MusaNet) is specifically designed to learn the representations of patient journeys that is used to be a long sequence of activities. The MusaNet is trained in end-to-end manner using the training data derived from EHRs. We evaluated the efficacy of our method on two medical application tasks with real-world benchmark datasets. The results have demonstrated the proposed MusaNet produces higher-quality representations than state-of-the-art baseline methods. The source code is available in https://github.com/xueping/MusaNet.

cs.LG↗

arXiv2020

Exploiting Structured Knowledge in Text via Graph-Guided Representation Learning

In this work, we aim at equipping pre-trained language models with structured knowledge. We present two self-supervised tasks learning over raw text with the guidance from knowledge graphs. Building upon entity-level masked language models, our first contribution is an entity masking scheme that exploits relational knowledge underlying the text. This is fulfilled by using a linked knowledge graph to select informative entities and then masking their mentions. In addition we use knowledge graphs to obtain distractors for the masked entities, and propose a novel distractor-suppressed ranking objective which is optimized jointly with masked language model. In contrast to existing paradigms, our approach uses knowledge graphs implicitly, only during pre-training, to inject language models with structured knowledge via learning from raw text. It is more efficient than retrieval-based methods that perform entity linking and integration during finetuning and inference, and generalizes more effectively than the methods that directly learn from concatenated graph triples. Experiments show that our proposed model achieves improved performance on five benchmark datasets, including question answering and knowledge base completion tasks.

cs.CL↗

arXiv2019

Self-Attention Enhanced Selective Gate with Entity-Aware Embedding for Distantly Supervised Relation Extraction

Distantly supervised relation extraction intrinsically suffers from noisy labels due to the strong assumption of distant supervision. Most prior works adopt a selective attention mechanism over sentences in a bag to denoise from wrongly labeled data, which however could be incompetent when there is only one sentence in a bag. In this paper, we propose a brand-new light-weight neural framework to address the distantly supervised relation extraction problem and alleviate the defects in previous selective attention framework. Specifically, in the proposed framework, 1) we use an entity-aware word embedding method to integrate both relative position information and head/tail entity embeddings, aiming to highlight the essence of entities for this task; 2) we develop a self-attention mechanism to capture the rich contextual dependencies as a complement for local dependencies captured by piecewise CNN; and 3) instead of using selective attention, we design a pooling-equipped gate, which is based on rich contextual representations, as an aggregator to generate bag-level representation for final relation classification. Compared to selective attention, one major advantage of the proposed gating mechanism is that, it performs stably and promisingly even if only one sentence appears in a bag and thus keeps the consistency across all training examples. The experiments on NYT dataset demonstrate that our approach achieves a new state-of-the-art performance in terms of both AUC and top-n precision metrics.

cs.CL↗

arXiv2019

A realistic dimension-independent approach for charged defect calculations in semiconductors

First-principles calculations of charged defects have become a cornerstone of research in semiconductors and insulators by providing insights into their fundamental physical properties. But current standard approach using the so-called jellium model has encountered both conceptual ambiguity and computational difficulty, especially for low-dimensional semiconducting materials. In this Communication, we propose a physical, straightforward, and dimension-independent universal model to calculate the formation energies of charged defects in both three-dimensional (3D) bulk and low-dimensional semiconductors. Within this model, the ionized electrons or holes are placed on the realistic host band-edge states instead of the virtual jellium state, therefore, rendering it not only naturally keeps the supercell charge neutral, but also has clear physical meaning. This realistic model reproduces the same accuracy as the traditional jellium model for most of the 3D semiconducting materials, and remarkably, for the low-dimensional structures, it is able to cure the divergence caused by the artificial long-range electrostatic energy introduced in the jellium model, and hence gives meaningful formation energies of defects in charged state and transition energy levels of the corresponding defects. Our realistic method, therefore, will have significant impact for the study of defect physics in all low-dimensional systems including quantum dots, nanowires, surfaces, interfaces, and 2D materials.

cond-mat.mtrl-sci↗

arXiv2019

Multi-Task Learning for Conversational Question Answering over a Large-Scale Knowledge Base

We consider the problem of conversational question answering over a large-scale knowledge base. To handle huge entity vocabulary of a large-scale knowledge base, recent neural semantic parsing based approaches usually decompose the task into several subtasks and then solve them sequentially, which leads to following issues: 1) errors in earlier subtasks will be propagated and negatively affect downstream ones; and 2) each subtask cannot naturally share supervision signals with others. To tackle these issues, we propose an innovative multi-task learning framework where a pointer-equipped semantic parsing model is designed to resolve coreference in conversations, and naturally empower joint learning with a novel type-aware entity detection model. The proposed framework thus enables shared supervisions and alleviates the effect of error propagation. Experiments on a large-scale conversational question answering dataset containing 1.6M question answering pairs over 12.8M entities show that the proposed framework improves overall F1 score from 67% to 79% compared with previous state-of-the-art work.

cs.CL↗

arXiv2019

Temporal Self-Attention Network for Medical Concept Embedding

In longitudinal electronic health records (EHRs), the event records of a patient are distributed over a long period of time and the temporal relations between the events reflect sufficient domain knowledge to benefit prediction tasks such as the rate of inpatient mortality. Medical concept embedding as a feature extraction method that transforms a set of medical concepts with a specific time stamp into a vector, which will be fed into a supervised learning algorithm. The quality of the embedding significantly determines the learning performance over the medical data. In this paper, we propose a medical concept embedding method based on applying a self-attention mechanism to represent each medical concept. We propose a novel attention mechanism which captures the contextual information and temporal relationships between medical concepts. A light-weight neural net, "Temporal Self-Attention Network (TeSAN)", is then proposed to learn medical concept embedding based solely on the proposed attention mechanism. To test the effectiveness of our proposed methods, we have conducted clustering and prediction tasks on two public EHRs datasets comparing TeSAN against five state-of-the-art embedding methods. The experimental results demonstrate that the proposed TeSAN model is superior to all the compared methods. To the best of our knowledge, this work is the first to exploit temporal self-attentive relations between medical events.

cs.CL↗

arXiv2019

Effective Search of Logical Forms for Weakly Supervised Knowledge-Based Question Answering

Many algorithms for Knowledge-Based Question Answering (KBQA) depend on semantic parsing, which translates a question to its logical form. When only weak supervision is provided, it is usually necessary to search valid logical forms for model training. However, a complex question typically involves a huge search space, which creates two main problems: 1) the solutions limited by computation time and memory usually reduce the success rate of the search, and 2) spurious logical forms in the search results degrade the quality of training data. These two problems lead to a poorly-trained semantic parsing model. In this work, we propose an effective search method for weakly supervised KBQA based on operator prediction for questions. With search space constrained by predicted operators, sufficient search paths can be explored, more valid logical forms can be derived, and operators possibly causing spurious logical forms can be avoided. As a result, a larger proportion of questions in a weakly supervised training set are equipped with logical forms, and fewer spurious logical forms are generated. Such high-quality training data directly contributes to a better semantic parsing model. Experimental results on one of the largest KBQA datasets (i.e., CSQA) verify the effectiveness of our approach: improving the precision from 67% to 72% and the recall from 67% to 72% in terms of the overall score.

cs.CL↗

arXiv2019

Tensorized Self-Attention: Efficiently Modeling Pairwise and Global Dependencies Together

Neural networks equipped with self-attention have parallelizable computation, light-weight structure, and the ability to capture both long-range and local dependencies. Further, their expressive power and performance can be boosted by using a vector to measure pairwise dependency, but this requires to expand the alignment matrix to a tensor, which results in memory and computation bottlenecks. In this paper, we propose a novel attention mechanism called "Multi-mask Tensorized Self-Attention" (MTSA), which is as fast and as memory-efficient as a CNN, but significantly outperforms previous CNN-/RNN-/attention-based models. MTSA 1) captures both pairwise (token2token) and global (source2token) dependencies by a novel compatibility function composed of dot-product and additive attentions, 2) uses a tensor to represent the feature-wise alignment scores for better expressive power but only requires parallelizable matrix multiplications, and 3) combines multi-head with multi-dimensional attentions, and applies a distinct positional mask to each head (subspace), so the memory and computation can be distributed to multiple heads, each with sequential information encoded independently. The experiments show that a CNN/RNN-free model based on MTSA achieves state-of-the-art or competitive performance on nine NLP benchmarks with compelling memory- and time-efficiency.

cs.CL↗

arXiv2018

Reinforced Self-Attention Network: a Hybrid of Hard and Soft Attention for Sequence Modeling

Many natural language processing tasks solely rely on sparse dependencies between a few tokens in a sentence. Soft attention mechanisms show promising performance in modeling local/global dependencies by soft probabilities between every two tokens, but they are not effective and efficient when applied to long sentences. By contrast, hard attention mechanisms directly select a subset of tokens but are difficult and inefficient to train due to their combinatorial nature. In this paper, we integrate both soft and hard attention into one context fusion model, "reinforced self-attention (ReSA)", for the mutual benefit of each other. In ReSA, a hard attention trims a sequence for a soft self-attention to process, while the soft attention feeds reward signals back to facilitate the training of the hard one. For this purpose, we develop a novel hard attention called "reinforced sequence sampling (RSS)", selecting tokens in parallel and trained via policy gradient. Using two RSS modules, ReSA efficiently extracts the sparse dependencies between each pair of selected tokens. We finally propose an RNN/CNN-free sentence-encoding model, "reinforced self-attention network (ReSAN)", solely based on ReSA. It achieves state-of-the-art performance on both Stanford Natural Language Inference (SNLI) and Sentences Involving Compositional Knowledge (SICK) datasets.

cs.CL↗

arXiv2018

Calculations of point defects in the layered MX2 (M=Mo, W; X=S, Te): Substitution by the groups III, V and VII elements

Dopability in semiconductors plays a crucial role in device performance. Using the first-principles density-functional theory calculations, we investigate systematically the doping properties of layered MX2 (M= Mo, W; X=S, Te) by replacing M or X with the groups III, V and VII elements. It is found that the defect BM is hard to form in MX2 due to the large formation energy originating from the crystal distortion, while AlM is easy to realize compared to the former. In MoS2, WS2 and MoTe2, Al is the most desirable p-type dopant under anion-rich conditions among the group III components, since AlM has relatively low transition and formation energies. With respect to the doping of the group V elements, it is found that the substitutions on the cation sites have deeper defect levels than those on the anion sites due to the strong electronegativity. AsTe and SbTe in MoTe2 and WTe2 are trend to form shallow acceptors under cation-rich conditions, indicating high hole-concentrations for p-type doping, whereas SbS in MoS2 and PTe in WTe2 are shown to be good p-type candidates under cation-rich conditions. In despite of that the substitutions of group VII on X site have low formation energies, the transition energies are too high to achieve n-type MoS2 and WS2. Nevertheless, for MoTe2, the substitutions with the group VII elements on the anion sites are suitable for n-type doping on account of the shallow donor levels and low formation energies under Mo-rich condition. As to WTe2, F is the only potential donor due to the shallow transition energy of FTe. Our findings of filtering out unfavorable and identifying favorable dopants in MX2 are very valuable for experimental implementations.

cond-mat.mtrl-sci↗

arXiv2018

Bi-Directional Block Self-Attention for Fast and Memory-Efficient Sequence Modeling

Recurrent neural networks (RNN), convolutional neural networks (CNN) and self-attention networks (SAN) are commonly used to produce context-aware representations. RNN can capture long-range dependency but is hard to parallelize and not time-efficient. CNN focuses on local dependency but does not perform well on some tasks. SAN can model both such dependencies via highly parallelizable computation, but memory requirement grows rapidly in line with sequence length. In this paper, we propose a model, called "bi-directional block self-attention network (Bi-BloSAN)", for RNN/CNN-free sequence encoding. It requires as little memory as RNN but with all the merits of SAN. Bi-BloSAN splits the entire sequence into blocks, and applies an intra-block SAN to each block for modeling local context, then applies an inter-block SAN to the outputs for all blocks to capture long-range dependency. Thus, each SAN only needs to process a short sequence, and only a small amount of memory is required. Additionally, we use feature-level attention to handle the variation of contexts around the same word, and use forward/backward masks to encode temporal order information. On nine benchmark datasets for different NLP tasks, Bi-BloSAN achieves or improves upon state-of-the-art accuracy, and shows better efficiency-memory trade-off than existing RNN/CNN/SAN.

cs.CL↗

arXiv2017

DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language Understanding

Recurrent neural nets (RNN) and convolutional neural nets (CNN) are widely used on NLP tasks to capture the long-term and local dependencies, respectively. Attention mechanisms have recently attracted enormous interest due to their highly parallelizable computation, significantly less training time, and flexibility in modeling dependencies. We propose a novel attention mechanism in which the attention between elements from input sequence(s) is directional and multi-dimensional (i.e., feature-wise). A light-weight neural net, "Directional Self-Attention Network (DiSAN)", is then proposed to learn sentence embedding, based solely on the proposed attention without any RNN/CNN structure. DiSAN is only composed of a directional self-attention with temporal order encoded, followed by a multi-dimensional attention that compresses the sequence into a vector representation. Despite its simple form, DiSAN outperforms complicated RNN models on both prediction quality and time efficiency. It achieves the best test accuracy among all sentence encoding methods and improves the most recent best result by 1.02% on the Stanford Natural Language Inference (SNLI) dataset, and shows state-of-the-art test accuracy on the Stanford Sentiment Treebank (SST), Multi-Genre natural language inference (MultiNLI), Sentences Involving Compositional Knowledge (SICK), Customer Review, MPQA, TREC question-type classification and Subjectivity (SUBJ) datasets.

cs.CL↗