arXiv subjects

Zhiyuan Liu

Publications and source records attributed to Zhiyuan Liu.

At least 541 records · Page 30Linked to original sources

arXiv2018

Denoising Distant Supervision for Relation Extraction via Instance-Level Adversarial Training

Existing neural relation extraction (NRE) models rely on distant supervision and suffer from wrong labeling problems. In this paper, we propose a novel adversarial training mechanism over instances for relation extraction to alleviate the noise issue. As compared with previous denoising methods, our proposed method can better discriminate those informative instances from noisy ones. Our method is also efficient and flexible to be applied to various NRE architectures. As shown in the experiments on a large-scale benchmark dataset in relation extraction, our denoising method can effectively filter out noisy instances and achieve significant improvements as compared with the state-of-the-art models.

cs.CL↗

arXiv2018

Distributions of Historic Market Data -- Implied and Realized Volatility

We undertake a systematic comparison between implied volatility, as represented by VIX (new methodology) and VXO (old methodology), and realized volatility. We compare visually and statistically distributions of realized and implied variance (volatility squared) and study the distribution of their ratio. We find that the ratio is best fitted by heavy-tailed -- lognormal and fat-tailed (power-law) -- distributions, depending on whether preceding or concurrent month of realized variance is used. We do not find substantial difference in accuracy between VIX and VXO. Additionally, we study the variance of theoretical realized variance for Heston and multiplicative models of stochastic volatility and compare those with realized variance obtained from historic market data.

q-fin.MF↗

arXiv2018

Does William Shakespeare REALLY Write Hamlet? Knowledge Representation Learning with Confidence

Knowledge graphs (KGs), which could provide essential relational information between entities, have been widely utilized in various knowledge-driven applications. Since the overall human knowledge is innumerable that still grows explosively and changes frequently, knowledge construction and update inevitably involve automatic mechanisms with less human supervision, which usually bring in plenty of noises and conflicts to KGs. However, most conventional knowledge representation learning methods assume that all triple facts in existing KGs share the same significance without any noises. To address this problem, we propose a novel confidence-aware knowledge representation learning framework (CKRL), which detects possible noises in KGs while learning knowledge representations with confidence simultaneously. Specifically, we introduce the triple confidence to conventional translation-based methods for knowledge representation learning. To make triple confidence more flexible and universal, we only utilize the internal structural information in KGs, and propose three kinds of triple confidences considering both local and global structural information. In experiments, We evaluate our models on knowledge graph noise detection, knowledge graph completion and triple classification. Experimental results demonstrate that our confidence-aware models achieve significant and consistent improvements on all tasks, which confirms the capability of CKRL modeling confidence with structural information in both KG noise detection and knowledge representation learning.

cs.CL↗

arXiv2017

Distributions of Historic Market Data - Stock Returns

We show that the moments of the distribution of historic stock returns are in excellent agreement with the Heston model and not with the multiplicative model, which predicts power-law tails of volatility and stock returns. We also show that the mean realized variance of returns is a linear function of the number of days over which the returns are calculated. The slope is determined by the mean value of the variance (squared volatility) in the mean-reverting stochastic volatility models, such as Heston and multiplicative, independent of stochasticity. The distribution function of stock returns, which rescales with the increase of the number of days of return, is obtained from the steady-state variance distribution function using the product distribution with the normal distribution.

q-fin.MF↗

arXiv2017

Decomposition of Nonlinear Dynamical Systems Using Koopman Gramians

In this paper we propose a new Koopman operator approach to the decomposition of nonlinear dynamical systems using Koopman Gramians. We introduce the notion of an input-Koopman operator, and show how input-Koopman operators can be used to cast a nonlinear system into the classical state-space form, and identify conditions under which input and state observable functions are well separated. We then extend an existing method of dynamic mode decomposition for learning Koopman operators from data known as deep dynamic mode decomposition to systems with controls or disturbances. We illustrate the accuracy of the method in learning an input-state separable Koopman operator for an example system, even when the underlying system exhibits mixed state-input terms. We next introduce a nonlinear decomposition algorithm, based on Koopman Gramians, that maximizes internal subsystem observability and disturbance rejection from unwanted noise from other subsystems. We derive a relaxation based on Koopman Gramians and multi-way partitioning for the resulting NP-hard decomposition problem. We lastly illustrate the proposed algorithm with the swing dynamics for an IEEE 39-bus system.

eess.SY↗

arXiv2017

A Koopman Operator Approach for Computing and Balancing Gramians for Discrete Time Nonlinear Systems

In this paper, we consider the problem of quantifying controllability and observability of a nonlinear discrete time dynamical system. We introduce the Koopman operator as a canonical representation of the system and apply a lifting technique to compute gramians in the space of full-state observables. We illustrate the properties of these gramians and identify several relationships with canonical results on local controllability and observability. Once defined, we show that these gramians can be balanced through a change of coordinates on the observables space, which in turn allows for direct application of balanced truncation. Throughout the paper, we highlight the aspects of our approach with an example nonlinear system.

eess.SY↗

arXiv2017

Incorporating Relation Paths in Neural Relation Extraction

Distantly supervised relation extraction has been widely used to find novel relational facts from plain text. To predict the relation between a pair of two target entities, existing methods solely rely on those direct sentences containing both entities. In fact, there are also many sentences containing only one of the target entities, which provide rich and useful information for relation extraction. To address this issue, we build inference chains between two target entities via intermediate entities, and propose a path-based neural relation extraction model to encode the relational semantics from both direct sentences and inference chains. Experimental results on real-world datasets show that, our model can make full use of those sentences containing only one target entity, and achieves significant and consistent improvements on relation extraction as compared with baselines. The source code of this paper can be obtained from https: //github.com/thunlp/PathNRE.

cs.CL↗

arXiv2017

Stochastic Dual Algorithm for Voltage Regulation in Distribution Networks with Discrete Loads

This paper considers power distribution networks with distributed energy resources and designs an incentive-based algorithm that allows the network operator and customers to pursue given operational and economic objectives while concurrently ensuring that voltages are within prescribed limits. Heterogeneous DERs with continuous and discrete control commands are considered. We address four major challenges: discrete decision variables, non-convexity due to a Stackelberg game structure, unavailability of private information from customers, and asynchronous operation. Starting from a non-convex setting, we develop a distributed stochastic dual algorithm that solves a relaxed problem, and prove that the proposed algorithm achieves the global optimal solution of the original problem on average. Feasible values for discrete decision variables are also recovered. Stability of the algorithm is analytically established and numerically corroborated.

math.OC↗

arXiv2017

A Neural Network Approach to Joint Modeling Social Networks and Mobile Trajectories

The accelerated growth of mobile trajectories in location-based services brings valuable data resources to understand users' moving behaviors. Apart from recording the trajectory data, another major characteristic of these location-based services is that they also allow the users to connect whomever they like. A combination of social networking and location-based services is called as location-based social networks (LBSN). As shown in previous works, locations that are frequently visited by socially-related persons tend to be correlated, which indicates the close association between social connections and trajectory behaviors of users in LBSNs. In order to better analyze and mine LBSN data, we present a novel neural network model which can joint model both social networks and mobile trajectories. In specific, our model consists of two components: the construction of social networks and the generation of mobile trajectories. We first adopt a network embedding method for the construction of social networks: a networking representation can be derived for a user. The key of our model lies in the component of generating mobile trajectories. We have considered four factors that influence the generation process of mobile trajectories, namely user visit preference, influence of friends, short-term sequential contexts and long-term sequential contexts. To characterize the last two contexts, we employ the RNN and GRU models to capture the sequential relatedness in mobile trajectories at different levels, i.e., short term or long term. Finally, the two components are tied by sharing the user network representations. Experimental results on two important applications demonstrate the effectiveness of our model. Especially, the improvement over baselines is more significant when either network structure or trajectory data is sparse.

cs.SI↗

arXiv2017

End-to-End Neural Ad-hoc Ranking with Kernel Pooling

This paper proposes K-NRM, a kernel based neural model for document ranking. Given a query and a set of documents, K-NRM uses a translation matrix that models word-level similarities via word embeddings, a new kernel-pooling technique that uses kernels to extract multi-level soft match features, and a learning-to-rank layer that combines those features into the final ranking score. The whole model is trained end-to-end. The ranking layer learns desired feature patterns from the pairwise ranking loss. The kernels transfer the feature patterns into soft-match targets at each similarity level and enforce them on the translation matrix. The word embeddings are tuned accordingly so that they can produce the desired soft matches. Experiments on a commercial search engine's query log demonstrate the improvements of K-NRM over prior feature-based and neural-based states-of-the-art, and explain the source of K-NRM's advantage: Its kernel-guided embedding encodes a similarity metric tailored for matching query words to document words, and provides effective multi-level soft matches.

cs.IR↗

arXiv2017

Image-embodied Knowledge Representation Learning

Entity images could provide significant visual information for knowledge representation learning. Most conventional methods learn knowledge representations merely from structured triples, ignoring rich visual information extracted from entity images. In this paper, we propose a novel Image-embodied Knowledge Representation Learning model (IKRL), where knowledge representations are learned with both triple facts and images. More specifically, we first construct representations for all images of an entity with a neural image encoder. These image representations are then integrated into an aggregated image-based representation via an attention-based method. We evaluate our IKRL models on knowledge graph completion and triple classification. Experimental results demonstrate that our models outperform all baselines on both tasks, which indicates the significance of visual information for knowledge representations and the capability of our models in learning knowledge representations with images.

cs.CV↗

arXiv2017

On absence of steady state in the Bouchaud-Mézard network model

In the limit of infinite number of nodes (agents), the Itô-reduced Bouchaud-Mézard network model of economic exchange has a time-independent mean and a steady-state inverse gamma distribution. We show that for a finite number of nodes the mean is actually distributed as a time-dependent lognormal and inverse gamma is quasi-stationary, with the time-dependent scale parameter.

cond-mat.stat-mech↗

arXiv2016

Neural Emoji Recommendation in Dialogue Systems

Emoji is an essential component in dialogues which has been broadly utilized on almost all social platforms. It could express more delicate feelings beyond plain texts and thus smooth the communications between users, making dialogue systems more anthropomorphic and vivid. In this paper, we focus on automatically recommending appropriate emojis given the contextual information in multi-turn dialogue systems, where the challenges locate in understanding the whole conversations. More specifically, we propose the hierarchical long short-term memory model (H-LSTM) to construct dialogue representations, followed by a softmax classifier for emoji classification. We evaluate our models on the task of emoji classification in a real-world dataset, with some further explorations on parameter sensitivity and case study. Experimental results demonstrate that our method achieves the best performances on all evaluation metrics. It indicates that our method could well capture the contextual information and emotion flow in dialogues, which is significant for emoji recommendation.

cs.CL↗

arXiv2016

Joint Representation Learning of Text and Knowledge for Knowledge Graph Completion

Joint representation learning of text and knowledge within a unified semantic space enables us to perform knowledge graph completion more accurately. In this work, we propose a novel framework to embed words, entities and relations into the same continuous vector space. In this model, both entity and relation embeddings are learned by taking knowledge graph and plain text into consideration. In experiments, we evaluate the joint learning model on three tasks including entity prediction, relation prediction and relation classification from text. The experiment results show that our model can significantly and consistently improve the performance on the three tasks as compared with other baselines.

cs.CL↗

arXiv2016

Neural Headline Generation with Sentence-wise Optimization

Recently, neural models have been proposed for headline generation by learning to map documents to headlines with recurrent neural networks. Nevertheless, as traditional neural network utilizes maximum likelihood estimation for parameter optimization, it essentially constrains the expected training objective within word level rather than sentence level. Moreover, the performance of model prediction significantly relies on training data distribution. To overcome these drawbacks, we employ minimum risk training strategy in this paper, which directly optimizes model parameters in sentence level with respect to evaluation metrics and leads to significant improvements for headline generation. Experiment results show that our models outperforms state-of-the-art systems on both English and Chinese headline generation tasks.

cs.CL↗

arXiv2016

Knowledge Representation via Joint Learning of Sequential Text and Knowledge Graphs

Textual information is considered as significant supplement to knowledge representation learning (KRL). There are two main challenges for constructing knowledge representations from plain texts: (1) How to take full advantages of sequential contexts of entities in plain texts for KRL. (2) How to dynamically select those informative sentences of the corresponding entities for KRL. In this paper, we propose the Sequential Text-embodied Knowledge Representation Learning to build knowledge representations from multiple sentences. Given each reference sentence of an entity, we first utilize recurrent neural network with pooling or long short-term memory network to encode the semantic information of the sentence with respect to the entity. Then we further design an attention model to measure the informativeness of each sentence, and build text-based representations of entities. We evaluate our method on two tasks, including triple classification and link prediction. Experimental results demonstrate that our method outperforms other baselines on both tasks, which indicates that our method is capable of selecting informative sentences and encoding the textual information well into knowledge representations.

cs.CL↗

arXiv2016

Topic Sensitive Neural Headline Generation

Neural models have recently been used in text summarization including headline generation. The model can be trained using a set of document-headline pairs. However, the model does not explicitly consider topical similarities and differences of documents. We suggest to categorizing documents into various topics so that documents within the same topic are similar in content and share similar summarization patterns. Taking advantage of topic information of documents, we propose topic sensitive neural headline generation model. Our model can generate more accurate summaries guided by document topics. We test our model on LCSTS dataset, and experiments show that our method outperforms other baselines on each topic and achieves the state-of-art performance.

cs.CL↗

arXiv2015

Category Enhanced Word Embedding

Distributed word representations have been demonstrated to be effective in capturing semantic and syntactic regularities. Unsupervised representation learning from large unlabeled corpora can learn similar representations for those words that present similar co-occurrence statistics. Besides local occurrence statistics, global topical information is also important knowledge that may help discriminate a word from another. In this paper, we incorporate category information of documents in the learning of word representations and to learn the proposed models in a document-wise manner. Our models outperform several state-of-the-art models in word analogy and word similarity tasks. Moreover, we evaluate the learned word vectors on sentiment analysis and text classification tasks, which shows the superiority of our learned word vectors. We also learn high-quality category embeddings that reflect topical meanings.

cs.CL↗