Searcharxiv⌕ Search

arXiv subjects

Yinan Liu

Publications and source records attributed to Yinan Liu.

28 records · Page 2Linked to original sources

Low-resource Personal Attribute Prediction from Conversation

Personal knowledge bases (PKBs) are crucial for a broad range of applications such as personalized recommendation and Web-based chatbots. A critical challenge to build PKBs is extracting personal attribute knowledge from users' conversation data. Given some users of a conversational system, a personal attribute and these users' utterances, our goal is to predict the ranking of the given personal attribute values for each user. Previous studies often rely on a relative number of resources such as labeled utterances and external data, yet the attribute knowledge embedded in unlabeled utterances is underutilized and their performance of predicting some difficult personal attributes is still unsatisfactory. In addition, it is found that some text classification methods could be employed to resolve this task directly. However, they also perform not well over those difficult personal attributes. In this paper, we propose a novel framework PEARL to predict personal attributes from conversations by leveraging the abundant personal attribute knowledge from utterances under a low-resource setting in which no labeled utterances or external data are utilized. PEARL combines the biterm semantic information with the word co-occurrence information seamlessly via employing the updated prior attribute knowledge to refine the biterm topic model's Gibbs sampling process in an iterative manner. The extensive experimental results show that PEARL outperforms all the baseline methods not only on the task of personal attribute prediction from conversations over two data sets, but also on the more general weakly supervised text classification task over one data set.

cs.AI↗

Personal Attribute Prediction from Conversations

Personal knowledge bases (PKBs) are critical to many applications, such as Web-based chatbots and personalized recommendation. Conversations containing rich personal knowledge can be regarded as a main source to populate the PKB. Given a user, a user attribute, and user utterances from a conversational system, we aim to predict the personal attribute value for the user, which is helpful for the enrichment of PKBs. However, there are three issues existing in previous studies: (1) manually labeled utterances are required for model training; (2) personal attribute knowledge embedded in both utterances and external resources is underutilized; (3) the performance on predicting some difficult personal attributes is unsatisfactory. In this paper, we propose a framework DSCGN based on the pre-trained language model with a noise-robust loss function to predict personal attributes from conversations without requiring any labeled utterances. We yield two categories of supervision, i.e., document-level supervision via a distant supervision strategy and contextualized word-level supervision via a label guessing method, by mining the personal attribute knowledge embedded in both unlabeled utterances and external resources to fine-tune the language model. Extensive experiments over two real-world data sets (i.e., a profession data set and a hobby data set) show our framework obtains the best performance compared with all the twelve baselines in terms of nDCG and MRR.

cs.CL↗

Multi-View Clustering for Open Knowledge Base Canonicalization

Open information extraction (OIE) methods extract plenty of OIE triples from unstructured text, which compose large open knowledge bases (OKBs). Noun phrases and relation phrases in such OKBs are not canonicalized, which leads to scattered and redundant facts. It is found that two views of knowledge (i.e., a fact view based on the fact triple and a context view based on the fact triple's source context) provide complementary information that is vital to the task of OKB canonicalization, which clusters synonymous noun phrases and relation phrases into the same group and assigns them unique identifiers. However, these two views of knowledge have so far been leveraged in isolation by existing works. In this paper, we propose CMVC, a novel unsupervised framework that leverages these two views of knowledge jointly for canonicalizing OKBs without the need of manually annotated labels. To achieve this goal, we propose a multi-view CH K-Means clustering algorithm to mutually reinforce the clustering of view-specific embeddings learned from each view by considering their different clustering qualities. In order to further enhance the canonicalization performance, we propose a training data optimization strategy in terms of data quantity and data quality respectively in each particular view to refine the learned view-specific embeddings in an iterative manner. Additionally, we propose a Log-Jump algorithm to predict the optimal number of clusters in a data-driven way without requiring any labels. We demonstrate the superiority of our framework through extensive experiments on multiple real-world OKB data sets against state-of-the-art methods.

cs.CL↗

Entity Linking Meets Deep Learning: Techniques and Solutions

Entity linking (EL) is the process of linking entity mentions appearing in web text with their corresponding entities in a knowledge base. EL plays an important role in the fields of knowledge engineering and data mining, underlying a variety of downstream applications such as knowledge base population, content analysis, relation extraction, and question answering. In recent years, deep learning (DL), which has achieved tremendous success in various domains, has also been leveraged in EL methods to surpass traditional machine learning based methods and yield the state-of-the-art performance. In this survey, we present a comprehensive review and analysis of existing DL based EL methods. First of all, we propose a new taxonomy, which organizes existing DL based EL methods using three axes: embedding, feature, and algorithm. Then we systematically survey the representative EL methods along the three axes of the taxonomy. Later, we introduce ten commonly used EL data sets and give a quantitative performance analysis of DL based EL methods over these data sets. Finally, we discuss the remaining limitations of existing methods and highlight some promising future directions.

cs.CL↗

Subjective Bias in Abstractive Summarization

Due to the subjectivity of the summarization, it is a good practice to have more than one gold summary for each training document. However, many modern large-scale abstractive summarization datasets have only one-to-one samples written by different human with different styles. The impact of this phenomenon is understudied. We formulate the differences among possible multiple expressions summarizing the same content as subjective bias and examine the role of this bias in the context of abstractive summarization. In this paper a lightweight and effective method to extract the feature embeddings of subjective styles is proposed. Results of summarization models trained on style-clustered datasets show that there are certain types of styles that lead to better convergence, abstraction and generalization. The reproducible code and generated summaries are available online.

cs.CL↗

On Extending NLP Techniques from the Categorical to the Latent Space: KL Divergence, Zipf's Law, and Similarity Search

Despite the recent successes of deep learning in natural language processing (NLP), there remains widespread usage of and demand for techniques that do not rely on machine learning. The advantage of these techniques is their interpretability and low cost when compared to frequently opaque and expensive machine learning models. Although they may not be be as performant in all cases, they are often sufficient for common and relatively simple problems. In this paper, we aim to modernize these older methods while retaining their advantages by extending approaches from categorical or bag-of-words representations to word embeddings representations in the latent space. First, we show that entropy and Kullback-Leibler divergence can be efficiently estimated using word embeddings and use this estimation to compare text across several categories. Next, we recast the heavy-tailed distribution known as Zipf's law that is frequently observed in the categorical space to the latent space. Finally, we look to improve the Jaccard similarity measure for sentence suggestion by introducing a new method of identifying similar sentences based on the set cover problem. We compare the performance of this algorithm against several baselines including Word Mover's Distance and the Levenshtein distance.

cs.CL↗

Hyperspectral Image Classification Based on Adaptive Sparse Deep Network

Sparse model is widely used in hyperspectral image classification.However, different of sparsity and regularization parameters has great influence on the classification results.In this paper, a novel adaptive sparse deep network based on deep architecture is proposed, which can construct the optimal sparse representation and regularization parameters by deep network.Firstly, a data flow graph is designed to represent each update iteration based on Alternating Direction Method of Multipliers (ADMM) algorithm.Forward network and Back-Propagation network are deduced.All parameters are updated by gradient descent in Back-Propagation.Then we proposed an Adaptive Sparse Deep Network.Comparing with several traditional classifiers or other algorithm for sparse model, experiment results indicate that our method achieves great improvement in HSI classification.

eess.IV↗

Berry Curvature Enhanced Nonlinear Photogalvanic Response of Type-II Weyl Cone

The experimental manifestation of topological effects in bulk materials under ambient conditions, especially those with practical applications, has attracted enormous research interest. Recent discovery of Weyl semimetal provides an ideal material platform for such endeavors. The Berry curvature in a Weyl semimetal becomes singular at the Weyl node, creating an effective magnetic monopole in the k-space. A pair of Weyl nodes carry quantized effective magnetic charges with opposite signs, and therefore, opposite chirality. Although Weyl-point-related signatures such as chiral anomaly and non-closing surface Fermi arcs have been detected through transport and ARPES measurements, direct experimental evidence of the effective k-space monopole of the Weyl nodes has so far been lacking. In this work, signatures of the singular topology in a type-II Weyl semimetal TaIrTe4 is revealed in the photo responses, which are shown to be directly related to the divergence of Berry curvature. As a result of the divergence of Berry curvature at the Weyl nodes, TaIrTe4 exhibits unusually large photo responsivity of 130.2 mA/W with 4-μm excitation in an unbiased field effect transistor at room temperature arising from the third-order nonlinear optical response. The room temperature mid-IR responsivity is approaching the performance of commercial HgCdTe detector operating at low temperature, making Type-II Weyl semimetal TaIrTe4 of practical importance in terms of photo sensing and solar energy harvesting. Furthermore, the high shift photocurrent response at the Weyl cones is found to enhance the circularly polarized galvanic response from Weyl cones with opposite chirality, which opens new experimental possibilities for studying and controlling the chiral polarization of Weyl Fermions through an in-plane DC electric field in addition to the optical helicities.

cond-mat.mtrl-sci↗

Raman Signatures of Broken Inversion Symmetry and In-plane Anisotropy in Type-II Weyl Semimetal Candidate TaIrTe4

The layered ternary compound TaIrTe4 is an important candidate to host the recently predicted type-II Weyl Fermions. However, a direct and definitive proof of the absence of inversion symmetry in this material, a prerequisite for the existence of Weyl Fermions, has so far remained evasive. Herein, an unambiguous identification of the broken inversion symmetry in TaIrTe4 is established using angle-resolved polarized Raman spectroscopy. Combining with high-resolution transmission electron microscopy, we demonstrate an efficient and nondestructive recipe to determine the exact crystallographic orientation of TaIrTe4 crystals. Such technique could be extended to the fast identification and characterization of other type-II Weyl Fermions candidates. A surprisingly strong in-plane electrical anisotropy in TaIrTe4 thin flakes is also revealed, up to 200% at 10K, which is the strongest known electrical anisotropy for materials with comparable carrier density, notably in such good metals as copper and silver.

cond-mat.mtrl-sci↗

Liquid phase mass production of air-stable black phosphorus/phospholipids nanocomposite with ultralow tunneling barrier

Few-layer black phosphorus (FLBP), a recently discovered two-dimensional semiconductor, has attracted substantial attention in the scientific and technical communities due to its great potential in electronic and optoelectronic applications. However, reactivity of FLBP flakes with ambient species limits its direct applications. Among various methods to passivate FLBP in ambient environment, nanocomposites mixing FLBP flakes with stable matrix may be one of the most promising approaches for industry applications. Here, we report a simple one-step procedure to mass produce air-stable FLBP/phospholipids nanocomposite in liquid phase. The resultant nanocomposite is found to have ultralow tunneling barrier for charge carriers which can be described by an Efros-Shklovskii variable range hopping mechanism. Devices made from such mass-produced FLBP/phospholipids nanocomposite show highly stable electrical conductivity and opto-electrical response in ambient conditions, indicating its promising applications in both electronic and optoelectronic applications. This method could also be generalized to the mass production of nanocomposites consisting of other air-sensitive two-dimensional materials, such as FeSe, NbSe2, WTe2, etc.

cond-mat.mtrl-sci↗