Search arXiv⌕ Search

arXiv subjects

Wenya Wang

Publications and source records attributed to Wenya Wang.

80 records · Page 5Linked to original sources
arXiv2022

Domain Confused Contrastive Learning for Unsupervised Domain Adaptation

In this work, we study Unsupervised Domain Adaptation (UDA) in a challenging self-supervised approach. One of the difficulties is how to learn task discrimination in the absence of target labels. Unlike previous literature which directly aligns cross-domain distributions or leverages reverse gradient, we propose Domain Confused Contrastive Learning (DCCL) to bridge the source and the target domains via domain puzzles, and retain discriminative representations after adaptation. Technically, DCCL searches for a most domain-challenging direction and exquisitely crafts domain confused augmentations as positive pairs, then it contrastively encourages the model to pull representations towards the other domain, thus learning more stable and effective domain invariances. We also investigate whether contrastive learning necessarily helps with UDA when performing other data augmentations. Extensive experiments demonstrate that DCCL significantly outperforms baselines.

cs.CL↗
arXiv2020

Weakly-supervised Domain Adaption for Aspect Extraction via Multi-level Interaction Transfer

Fine-grained aspect extraction is an essential sub-task in aspect based opinion analysis. It aims to identify the aspect terms (a.k.a. opinion targets) of a product or service in each sentence. However, expensive annotation process is usually involved to acquire sufficient token-level labels for each domain. To address this limitation, some previous works propose domain adaptation strategies to transfer knowledge from a sufficiently labeled source domain to unlabeled target domains. But due to both the difficulty of fine-grained prediction problems and the large domain gap between domains, the performance remains unsatisfactory. This work conducts a pioneer study on leveraging sentence-level aspect category labels that can be usually available in commercial services like review sites to promote token-level transfer for the extraction purpose. Specifically, the aspect category information is used to construct pivot knowledge for transfer with assumption that the interactions between sentence-level aspect category and token-level aspect terms are invariant across domains. To this end, we propose a novel multi-level reconstruction mechanism that aligns both the fine-grained and coarse-grained information in multiple levels of abstractions. Comprehensive experiments demonstrate that our approach can fully utilize sentence-level aspect category labels to improve cross-domain aspect extraction with a large performance gain.

cs.CL↗
arXiv2019

Integrating Deep Learning with Logic Fusion for Information Extraction

Information extraction (IE) aims to produce structured information from an input text, e.g., Named Entity Recognition and Relation Extraction. Various attempts have been proposed for IE via feature engineering or deep learning. However, most of them fail to associate the complex relationships inherent in the task itself, which has proven to be especially crucial. For example, the relation between 2 entities is highly dependent on their entity types. These dependencies can be regarded as complex constraints that can be efficiently expressed as logical rules. To combine such logic reasoning capabilities with learning capabilities of deep neural networks, we propose to integrate logical knowledge in the form of first-order logic into a deep learning system, which can be trained jointly in an end-to-end manner. The integrated framework is able to enhance neural outputs with knowledge regularization via logic rules, and at the same time update the weights of logic rules to comply with the characteristics of the training data. We demonstrate the effectiveness and generalization of the proposed model on multiple IE tasks.

cs.CL↗
arXiv2017

Multi-task memory networks for category-specific aspect and opinion terms co-extraction

In aspect-based sentiment analysis, most existing methods either focus on aspect/opinion terms extraction or aspect terms categorization. However, each task by itself only provides partial information to end users. To generate more detailed and structured opinion analysis, we propose a finer-grained problem, which we call category-specific aspect and opinion terms extraction. This problem involves the identification of aspect and opinion terms within each sentence, as well as the categorization of the identified terms. To this end, we propose an end-to-end multi-task attention model, where each task corresponds to aspect/opinion terms extraction for a specific category. Our model benefits from exploring the commonalities and relationships among different tasks to address the data sparsity issue. We demonstrate its state-of-the-art performance on three benchmark datasets.

cs.CL↗
arXiv2016

Recursive Neural Conditional Random Fields for Aspect-based Sentiment Analysis

In aspect-based sentiment analysis, extracting aspect terms along with the opinions being expressed from user-generated content is one of the most important subtasks. Previous studies have shown that exploiting connections between aspect and opinion terms is promising for this task. In this paper, we propose a novel joint model that integrates recursive neural networks and conditional random fields into a unified framework for explicit aspect and opinion terms co-extraction. The proposed model learns high-level discriminative features and double propagate information between aspect and opinion terms, simultaneously. Moreover, it is flexible to incorporate hand-crafted features into the proposed model to further boost its information extraction performance. Experimental results on the SemEval Challenge 2014 dataset show the superiority of our proposed model over several baseline methods as well as the winning systems of the challenge.

cs.CL↗
arXiv2014

Note on the points with dense orbit under $\times 2$ and $\times 3$ maps

It was conjectured by Furstenberg that for any $x\in [0,1]\backslash Q$, $$ \dim_H \bar{\{2^nx ({\text{mod}}\ 1): n\ge 1\}}+ \dim_H \bar{\{3^nx ({\text{mod}}\ 1): n\ge 1\}}\ge 1. $$ When $x$ is a normal number, the above result holds trivially. In this note, we give explicit non-normal numbers for which the above dimensional formula holds.

math.DS↗
arXiv2006

Spanning Trees on Lattices and Integration Identities

For a lattice $Λ$ with $n$ vertices and dimension $d$ equal or higher than two, the number of spanning trees $N_{ST}(Λ)$ grows asymptotically as $\exp(n z_Λ)$ in the thermodynamic limit. We present exact integral expressions for the asymptotic growth constant $z_Λ$ for spanning trees on several lattices. By taking different unit cells in the calculation, many integration identities can be obtained. We also give $z_{Λ(p)}$ on the homeomorphic expansion of $k$-regular lattices with $p$ vertices inserted on each edge.

cond-mat.stat-mech↗