arXiv subjects

Jiang Guo

Publications and source records attributed to Jiang Guo.

28 records · Page 2Linked to original sources

arXiv2021

Curriculum CycleGAN for Textual Sentiment Domain Adaptation with Multiple Sources

Sentiment analysis of user-generated reviews or comments on products and services in social networks can help enterprises to analyze the feedback from customers and take corresponding actions for improvement. To mitigate large-scale annotations on the target domain, domain adaptation (DA) provides an alternate solution by learning a transferable model from other labeled source domains. Existing multi-source domain adaptation (MDA) methods either fail to extract some discriminative features in the target domain that are related to sentiment, neglect the correlations of different sources and the distribution difference among different sub-domains even in the same source, or cannot reflect the varying optimal weighting during different training stages. In this paper, we propose a novel instance-level MDA framework, named curriculum cycle-consistent generative adversarial network (C-CycleGAN), to address the above issues. Specifically, C-CycleGAN consists of three components: (1) pre-trained text encoder which encodes textual input from different domains into a continuous representation space, (2) intermediate domain generator with curriculum instance-level adaptation which bridges the gap across source and target domains, and (3) task classifier trained on the intermediate domain for final sentiment classification. C-CycleGAN transfers source samples at instance-level to an intermediate domain that is closer to the target domain with sentiment semantics preserved and without losing discriminative features. Further, our dynamic instance-level weighting mechanisms can assign the optimal weights to different source samples in each training stage. We conduct extensive experiments on three benchmark datasets and achieve substantial gains over state-of-the-art DA approaches. Our source code is released at: https://github.com/WArushrush/Curriculum-CycleGAN.

cs.CL↗

arXiv2019

Working Hard or Hardly Working: Challenges of Integrating Typology into Neural Dependency Parsers

This paper explores the task of leveraging typology in the context of cross-lingual dependency parsing. While this linguistic information has shown great promise in pre-neural parsing, results for neural architectures have been mixed. The aim of our investigation is to better understand this state-of-the-art. Our main findings are as follows: 1) The benefit of typological information is derived from coarsely grouping languages into syntactically-homogeneous clusters rather than from learning to leverage variations along individual typological dimensions in a compositional manner; 2) Typology consistent with the actual corpus statistics yields better transfer performance; 3) Typological similarity is only a rough proxy of cross-lingual transferability with respect to parsing.

cs.CL↗

arXiv2019

Cross-Lingual BERT Transformation for Zero-Shot Dependency Parsing

This paper investigates the problem of learning cross-lingual representations in a contextual space. We propose Cross-Lingual BERT Transformation (CLBT), a simple and efficient approach to generate cross-lingual contextualized word embeddings based on publicly available pre-trained BERT models (Devlin et al., 2018). In this approach, a linear transformation is learned from contextual word alignments to align the contextualized embeddings independently trained in different languages. We demonstrate the effectiveness of this approach on zero-shot cross-lingual transfer parsing. Experiments show that our embeddings substantially outperform the previous state-of-the-art that uses static embeddings. We further compare our approach with XLM (Lample and Conneau, 2019), a recently proposed cross-lingual language model trained with massive parallel data, and achieve highly competitive results.

cs.CL↗

arXiv2019

GraphIE: A Graph-Based Framework for Information Extraction

Most modern Information Extraction (IE) systems are implemented as sequential taggers and only model local dependencies. Non-local and non-sequential context is, however, a valuable source of information to improve predictions. In this paper, we introduce GraphIE, a framework that operates over a graph representing a broad set of dependencies between textual units (i.e. words or sentences). The algorithm propagates information between connected nodes through graph convolutions, generating a richer representation that can be exploited to improve word-level predictions. Evaluation on three different tasks --- namely textual, social media and visual information extraction --- shows that GraphIE consistently outperforms the state-of-the-art sequence tagging model by a significant margin.

cs.CL↗

arXiv2019

Expanding the horizon of automated metamaterials discovery via quantum annealing

Complexity of materials designed by machine learning is currently limited by the inefficiency of classical computers. We show how quantum annealing can be incorporated into automated materials discovery and conduct a proof-of-principle study on designing complex thermofunctional metamaterials consisting of SiO2, SiC, and Poly(methyl methacrylate). Empirical computing time of our quantum-classical hybrid algorithm involving a factorization machine, a rigorous coupled wave analysis, and a D-Wave 2000Q quantum annealer was insensitive to the problem size, while a classical counterpart experienced rapid increase. Our method was used to design complex structures of wavelength selective radiators showing much better concordance with the thermal atmospheric transparency window in comparison to existing human-designed alternatives. Our result shows that quantum annealing provides scientists gigantic computational power that may change how materials are designed.

physics.app-ph↗

arXiv2018

Multi-Source Domain Adaptation with Mixture of Experts

We propose a mixture-of-experts approach for unsupervised domain adaptation from multiple sources. The key idea is to explicitly capture the relationship between a target example and different source domains. This relationship, expressed by a point-to-set metric, determines how to combine predictors trained on various domains. The metric is learned in an unsupervised fashion using meta-training. Experimental results on sentiment analysis and part-of-speech tagging demonstrate that our approach consistently outperforms multiple baselines and can robustly handle negative transfer.

cs.CL↗

arXiv2016

A General Framework for Content-enhanced Network Representation Learning

This paper investigates the problem of network embedding, which aims at learning low-dimensional vector representation of nodes in networks. Most existing network embedding methods rely solely on the network structure, i.e., the linkage relationships between nodes, but ignore the rich content information associated with it, which is common in real world networks and beneficial to describing the characteristics of a node. In this paper, we propose content-enhanced network embedding (CENE), which is capable of jointly leveraging the network structure and the content information. Our approach integrates text modeling and structure modeling in a general framework by treating the content information as a special kind of node. Experiments on several real world net- works with application to node classification show that our models outperform all existing network embedding methods, demonstrating the merits of content information and joint learning.

cs.SI↗

arXiv2016

Exploiting Multi-typed Treebanks for Parsing with Deep Multi-task Learning

Various treebanks have been released for dependency parsing. Despite that treebanks may belong to different languages or have different annotation schemes, they contain syntactic knowledge that is potential to benefit each other. This paper presents an universal framework for exploiting these multi-typed treebanks to improve parsing with deep multi-task learning. We consider two kinds of treebanks as source: the multilingual universal treebanks and the monolingual heterogeneous treebanks. Multiple treebanks are trained jointly and interacted with multi-level parameter sharing. Experiments on several benchmark datasets in various languages demonstrate that our approach can make effective use of arbitrary source treebanks to improve target parsing models.

cs.CL↗

arXiv2016

Exploring Segment Representations for Neural Segmentation Models

Many natural language processing (NLP) tasks can be generalized into segmentation problem. In this paper, we combine semi-CRF with neural network to solve NLP segmentation tasks. Our model represents a segment both by composing the input units and embedding the entire segment. We thoroughly study different composition functions and different segment embeddings. We conduct extensive experiments on two typical segmentation tasks: named entity recognition (NER) and Chinese word segmentation (CWS). Experimental results show that our neural semi-CRF model benefits from representing the entire segment and achieves the state-of-the-art performance on CWS benchmark dataset and competitive results on the CoNLL03 dataset.

cs.CL↗

arXiv2015

Design and Simulation of a high order mode cavity bunch length monitor

A new bunch length measurement method based on high order mode cavity was proposed. Operating the harmonic cavity at mode TM0n0 so that its radius could be chosen, in order to break the limitation of beam pipe radius. A two-cavity bunch length monitor for linac of positron source was designed. Operating frequency selection for different bunch time structure was discussed and calculation formula of bunch length was deducted. Fundamental harmonic cavity resonates at 2.856 GHz with mode TM010. Fifth harmonic cavity resonates at 14.28 GHz (fifth harmonic of the linac fundamental frequency 2.856 GHz) with mode TM020, which could provide larger radius. Each cavity equipped with a filter to suppress unwanted signal. A simulation measurement was conducted in CST Particle Studio for beam current from 100-300mA, bunch length from 5-10ps, calculation results shows a fairly high accuracy (better than 3%). Several cases were discussed.

physics.acc-ph↗