arXiv subjects

Tong Wang

Publications and source records attributed to Tong Wang.

At least 181 records · Page 10Linked to original sources

arXiv2018

An Interpretable Model with Globally Consistent Explanations for Credit Risk

We propose a possible solution to a public challenge posed by the Fair Isaac Corporation (FICO), which is to provide an explainable model for credit risk assessment. Rather than present a black box model and explain it afterwards, we provide a globally interpretable model that is as accurate as other neural networks. Our "two-layer additive risk model" is decomposable into subscales, where each node in the second layer represents a meaningful subscale, and all of the nonlinearities are transparent. We provide three types of explanations that are simpler than, but consistent with, the global model. One of these explanation methods involves solving a minimum set cover problem to find high-support globally-consistent explanations. We present a new online visualization tool to allow users to explore the global model and its explanations.

cs.LG↗

arXiv2018

MS MARCO: A Human Generated MAchine Reading COmprehension Dataset

We introduce a large scale MAchine Reading COmprehension dataset, which we name MS MARCO. The dataset comprises of 1,010,916 anonymized questions---sampled from Bing's search query logs---each with a human generated answer and 182,669 completely human rewritten generated answers. In addition, the dataset contains 8,841,823 passages---extracted from 3,563,535 web documents retrieved by Bing---that provide the information necessary for curating the natural language answers. A question in the MS MARCO dataset may have multiple answers or no answers at all. Using this dataset, we propose three different tasks with varying levels of difficulty: (i) predict if a question is answerable given a set of context passages, and extract and synthesize the answer as a human would (ii) generate a well-formed answer (if possible) based on the context passages that can be understood with the question and passage context, and finally (iii) rank a set of retrieved passages given a question. The size of the dataset and the fact that the questions are derived from real user search queries distinguishes MS MARCO from other well-known publicly available datasets for machine reading comprehension and question-answering. We believe that the scale and the real-world nature of this dataset makes it attractive for benchmarking machine reading comprehension and question-answering models.

cs.CL↗

arXiv2018

Interpretable Patient Mortality Prediction with Multi-value Rule Sets

We propose a Multi-vAlue Rule Set (MRS) model for in-hospital predicting patient mortality. Compared to rule sets built from single-valued rules, MRS adopts a more generalized form of association rules that allows multiple values in a condition. Rules of this form are more concise than classical single-valued rules in capturing and describing patterns in data. Our formulation also pursues a higher efficiency of feature utilization, which reduces possible cost in data collection and storage. We propose a Bayesian framework for formulating a MRS model and propose an efficient inference method for learning a maximum \emph{a posteriori}, incorporating theoretically grounded bounds to iteratively reduce the search space and improve the search efficiency. Experiments show that our model was able to achieve better performance than baseline method including the current system used by the hospital.

cs.AI↗

arXiv2018

Neural Models for Key Phrase Detection and Question Generation

We propose a two-stage neural model to tackle question generation from documents. First, our model estimates the probability that word sequences in a document are ones that a human would pick when selecting candidate answers by training a neural key-phrase extractor on the answers in a question-answering corpus. Predicted key phrases then act as target answers and condition a sequence-to-sequence question-generation model with a copy mechanism. Empirically, our key-phrase extraction model significantly outperforms an entity-tagging baseline and existing rule-based approaches. We further demonstrate that our question generation system formulates fluent, answerable questions from key phrases. This two-stage system could be used to augment or generate reading comprehension datasets, which may be leveraged to improve machine reading systems or in educational settings.

cs.CL↗

arXiv2018

A Semantic QA-Based Approach for Text Summarization Evaluation

Many Natural Language Processing and Computational Linguistics applications involves the generation of new texts based on some existing texts, such as summarization, text simplification and machine translation. However, there has been a serious problem haunting these applications for decades, that is, how to automatically and accurately assess quality of these applications. In this paper, we will present some preliminary results on one especially useful and challenging problem in NLP system evaluation: how to pinpoint content differences of two text passages (especially for large pas-sages such as articles and books). Our idea is intuitive and very different from existing approaches. We treat one text passage as a small knowledge base, and ask it a large number of questions to exhaustively identify all content points in it. By comparing the correctly answered questions from two text passages, we will be able to compare their content precisely. The experiment using 2007 DUC summarization corpus clearly shows promising results.

cs.CL↗

arXiv2018

Annotating High-Level Structures of Short Stories and Personal Anecdotes

Stories are a vital form of communication in human culture; they are employed daily to persuade, to elicit sympathy, or to convey a message. Computational understanding of human narratives, especially high-level narrative structures, remain limited to date. Multiple literary theories for narrative structures exist, but operationalization of the theories has remained a challenge. We developed an annotation scheme by consolidating and extending existing narratological theories, including Labov and Waletsky's (1967) functional categorization scheme and Freytag's (1863) pyramid of dramatic tension, and present 360 annotated short stories collected from online sources. In the future, this research will support an approach that enables systems to intelligently sustain complex communications with humans.

cs.CL↗

arXiv2017

Multi-Value Rule Sets

We present the Multi-vAlue Rule Set (MARS) model for interpretable classification with feature efficient presentations. MARS introduces a more generalized form of association rules that allows multiple values in a condition. Rules of this form are more concise than traditional single-valued rules in capturing and describing patterns in data. MARS mitigates the problem of dealing with continuous features and high-cardinality categorical features faced by rule-based models. Our formulation also pursues a higher efficiency of feature utilization, which reduces the cognitive load to understand the decision process. We propose an efficient inference method for learning a maximum a posteriori model, incorporating theoretically grounded bounds to iteratively reduce the search space to improve search efficiency. Experiments with synthetic and real-world data demonstrate that MARS models have significantly smaller complexity and fewer features, providing better interpretability while being competitive in predictive accuracy. We conducted a usability study with human subjects and results show that MARS is the easiest to use compared with other competing rule-based models, in terms of the correct rate and response time. Overall, MARS introduces a new approach to rule-based models that balance accuracy and interpretability with feature-efficient representations.

cs.AI↗

arXiv2017

Technical Report for "User-Centric Participatory Sensing: A Game Theoretic Analysis"

Participatory sensing (PS) is a novel and promising sensing network paradigm for achieving a flexible and scalable sensing coverage with a low deploying cost, by encouraging mobile users to participate and contribute their smartphones as sensors. In this work, we consider a general PS system model with location-dependent and time-sensitive tasks, which generalizes the existing models in the literature. We focus on the task scheduling in the user-centric PS system, where each participating user will make his individual task scheduling decision (including both the task selection and the task execution order) distributively. Specifically, we formulate the interaction of users as a strategic game called Task Scheduling Game (TSG) and perform a comprehensive game-theoretic analysis. First, we prove that the proposed TSG game is a potential game, which guarantees the existence of Nash equilibrium (NE). Then, we analyze the efficiency loss and the fairness index at the NE. Our analysis shows the efficiency at NE may increase or decrease with the number of users, depending on the level of competition. This implies that it is not always better to employ more users in the user-centric PS system, which is important for the system designer to determine the optimal number of users to be employed in a practical system.

cs.GT↗

arXiv2017

Predicting the Quality of Short Narratives from Social Media

An important and difficult challenge in building computational models for narratives is the automatic evaluation of narrative quality. Quality evaluation connects narrative understanding and generation as generation systems need to evaluate their own products. To circumvent difficulties in acquiring annotations, we employ upvotes in social media as an approximate measure for story quality. We collected 54,484 answers from a crowd-powered question-and-answer website, Quora, and then used active learning to build a classifier that labeled 28,320 answers as stories. To predict the number of upvotes without the use of social network features, we create neural networks that model textual regions and the interdependence among regions, which serve as strong benchmarks for future research. To our best knowledge, this is the first large-scale study for automatic evaluation of narrative quality.

cs.CL↗

arXiv2017

A Joint Model for Question Answering and Question Generation

We propose a generative machine comprehension model that learns jointly to ask and answer questions based on documents. The proposed model uses a sequence-to-sequence framework that encodes the document and generates a question (answer) given an answer (question). Significant improvement in model performance is observed empirically on the SQuAD corpus, confirming our hypothesis that the model benefits from jointly learning to perform both tasks. We believe the joint model's novelty offers a new perspective on machine comprehension beyond architectural engineering, and serves as a first step towards autonomous information seeking.

cs.CL↗

arXiv2017

Machine Comprehension by Text-to-Text Neural Question Generation

We propose a recurrent neural model that generates natural-language questions from documents, conditioned on answers. We show how to train the model using a combination of supervised and reinforcement learning. After teacher forcing for standard maximum likelihood training, we fine-tune the model using policy gradient techniques to maximize several rewards that measure question quality. Most notably, one of these rewards is the performance of a question-answering system. We motivate question generation as a means to improve the performance of question answering systems. Our model is trained and evaluated on the recent question-answering dataset SQuAD.

cs.CL↗

arXiv2017

NewsQA: A Machine Comprehension Dataset

We present NewsQA, a challenging machine comprehension dataset of over 100,000 human-generated question-answer pairs. Crowdworkers supply questions and answers based on a set of over 10,000 news articles from CNN, with answers consisting of spans of text from the corresponding articles. We collect this dataset through a four-stage process designed to solicit exploratory questions that require reasoning. A thorough analysis confirms that NewsQA demands abilities beyond simple word matching and recognizing textual entailment. We measure human performance on the dataset and compare it to several strong neural models. The performance gap between humans and machines (0.198 in F1) indicates that significant progress can be made on NewsQA through future research. The dataset is freely available at https://datasets.maluuba.com/NewsQA.

cs.CL↗

arXiv2016

Experimental and theoretical analyses of strongly polarized photon emission from non-polar InGaN quantum dots

We present a comprehensive investigation of the polarization properties of non-polar a-plane InGaN quantum dots (QDs) and their origin with statistically significant experimental data and rigorous k.p modelling. The unbiased selection and study of 180 individual QDs allow us to compute an average polarization degree of 0.90, with a standard deviation of only 0.08. When coupled with theoretical insights, we show that a-plane InGaN QDs are highly insensitive to size differences, shape anisotropies, and indium content fluctuations. Furthermore, 91% of the studied QDs exhibit a polarization axis along the crystal [1-100] axis, with the other 9% polarized orthogonal to this direction. When coupled with their ability to emit single-photons, a-plane QDs are good candidates for the generation of linearly polarized single-photons, a feature attractive for quantum cryptography protocols.

cond-mat.mes-hall↗

arXiv2016

An ultrafast polarised single photon source at 220 K

A crucial requirement for the realisation of efficient and scalable on-chip quantum communication is an ultrafast polarised single photon source operating beyond the Peltier cooling barrier of 200 K. While a few systems based on different materials and device structures have achieved single photon generation above this threshold, there has been no report of single quantum emitters with deterministic polarisation properties at the same high temperature conditions. Here, we report the first device to simultaneously achieve single photon emission with a g(2)(0) of only 0.21, a high polarisation degree of 0.80, a fixed polarisation axis determined by the underlying crystallography, and a GHz repetition rate with a radiative lifetime of 357 ps at 220 K. The temperature insensitivity of these properties, together with the simple planar growth method, and absence of complex device geometries, makes this system an excellent candidate for on-chip applications in integrated systems.

cond-mat.mes-hall↗

arXiv2016

Topic Modeling over Short Texts by Incorporating Word Embeddings

Inferring topics from the overwhelming amount of short texts becomes a critical but challenging task for many content analysis tasks, such as content charactering, user interest profiling, and emerging topic detecting. Existing methods such as probabilistic latent semantic analysis (PLSA) and latent Dirichlet allocation (LDA) cannot solve this prob- lem very well since only very limited word co-occurrence information is available in short texts. This paper studies how to incorporate the external word correlation knowledge into short texts to improve the coherence of topic modeling. Based on recent results in word embeddings that learn se- mantically representations for words from a large corpus, we introduce a novel method, Embedding-based Topic Model (ETM), to learn latent topics from short texts. ETM not only solves the problem of very limited word co-occurrence information by aggregating short texts into long pseudo- texts, but also utilizes a Markov Random Field regularized model that gives correlated words a better chance to be put into the same topic. The experiments on real-world datasets validate the effectiveness of our model comparing with the state-of-the-art models.

cs.CL↗

arXiv2016

Ultrafast, polarized, single-photon emission from m-plane InGaN Quantum Dots on GaN nanowires

We demonstrate single photon emission from self-assembled m-plane InGaN quantum dots (QDs) embedded on the side-walls of GaN nanowires. A combination of electron microscopy, cathodoluminescence, time-resolved micro-PL and photon autocorrelation experiments give a thorough evaluation of the QDs structural and optical properties. The QD exhibits anti-bunched emission up to 100 K, with a measured autocorrelation function of g^2(0) = 0.28 (0.03) at 5 K. Studies on a statistically significant number of QDs show that these m-plane QDs exhibit very fast radiative lifetimes (260 +/- 55 ps) suggesting smaller internal fields than any of the previously reported c-plane and a-plane QDs. Moreover, the observed single photons are almost completely linearly polarized aligned perpendicular to the crystallographic c-axis with a degree of linear polarization of 0.84 +/- 0.12. Such InGaN QDs incorporated in a nanowire system meet many of the requirements for implementation into quantum information systems and could potentially open the door to wholly new device concepts.

cond-mat.mes-hall↗

arXiv2016

An Experimental Study of LSTM Encoder-Decoder Model for Text Simplification

Text simplification (TS) aims to reduce the lexical and structural complexity of a text, while still retaining the semantic meaning. Current automatic TS techniques are limited to either lexical-level applications or manually defining a large amount of rules. Since deep neural networks are powerful models that have achieved excellent performance over many difficult tasks, in this paper, we propose to use the Long Short-Term Memory (LSTM) Encoder-Decoder model for sentence level TS, which makes minimal assumptions about word sequence. We conduct preliminary experiments to find that the model is able to learn operation rules such as reversing, sorting and replacing from sequence pairs, which shows that the model may potentially discover and apply rules such as modifying sentence structure, substituting words, and removing words for TS.

cs.CL↗

arXiv2016

Link Prediction in evolving networks based on the popularity of nodes

Link prediction aims to uncover the underlying relationship behind networks, which could be utilized to predict the missing edges or identify the spurious edges, and attracts much attention from various fields. The key issue of link prediction is to estimate the likelihood of two nodes in networks. Most current approaches of link prediction base on static structural analysis and ignore the temporal aspects of evolving networks. Unlike previous work, in this paper, we propose a popularity based structural perturbation method (PBSPM) that characterizes the similarity of an edge not only from existing connections of networks, but also from the popularity of its two endpoints, since popular nodes have much more probability to form links between themselves. By taking popularity of nodes into account, PBSPM could suppress nodes that have high importance, but gradually become inactive. Therefore the proposed method is inclined to predict potential edges between active nodes, rather than edges between inactive nodes. Experimental results on four real networks show that the proposed method outperforms the state-of-the-art methods both in accuracy and robustness in evolving networks.

cs.SI↗