Searcharxiv⌕ Search

arXiv subjects

Qun Liu

Publications and source records attributed to Qun Liu.

At least 217 records · Page 12Linked to original sources
arXiv2019

Zero-Shot Paraphrase Generation with Multilingual Language Models

Leveraging multilingual parallel texts to automatically generate paraphrases has drawn much attention as size of high-quality paraphrase corpus is limited. Round-trip translation, also known as the pivoting method, is a typical approach to this end. However, we notice that the pivoting process involves multiple machine translation models and is likely to incur semantic drift during the two-step translations. In this paper, inspired by the Transformer-based language models, we propose a simple and unified paraphrasing model, which is purely trained on multilingual parallel data and can conduct zero-shot paraphrase generation in one step. Compared with the pivoting approach, paraphrases generated by our model is more semantically similar to the input sentence. Moreover, since our model shares the same architecture as GPT (Radford et al., 2018), we are able to pre-train the model on large-scale unparallel corpus, which further improves the fluency of the output sentences. In addition, we introduce the mechanism of denoising auto-encoder (DAE) to improve diversity and robustness of the model. Experimental results show that our model surpasses the pivoting method in terms of relevance, diversity, fluency and efficiency.

cs.CL↗
arXiv2019

Pretrained Language Models for Document-Level Neural Machine Translation

Previous work on document-level NMT usually focuses on limited contexts because of degraded performance on larger contexts. In this paper, we investigate on using large contexts with three main contributions: (1) Different from previous work which pertrained models on large-scale sentence-level parallel corpora, we use pretrained language models, specifically BERT, which are trained on monolingual documents; (2) We propose context manipulation methods to control the influence of large contexts, which lead to comparable results on systems using small and large contexts; (3) We introduce a multi-task training for regularization to avoid models overfitting our training corpora, which further improves our systems together with a deeper encoder. Experiments are conducted on the widely used IWSLT data sets with three language pairs, i.e., Chinese--English, French--English and Spanish--English. Results show that our systems are significantly better than three previously reported document-level systems.

cs.CL↗
arXiv2019

Improving Domain Adaptation Translation with Domain Invariant and Specific Information

In domain adaptation for neural machine translation, translation performance can benefit from separating features into domain-specific features and common features. In this paper, we propose a method to explicitly model the two kinds of information in the encoder-decoder framework so as to exploit out-of-domain data in in-domain training. In our method, we maintain a private encoder and a private decoder for each domain which are used to model domain-specific information. In the meantime, we introduce a common encoder and a common decoder shared by all the domains which can only have domain-independent information flow through. Besides, we add a discriminator to the shared encoder and employ adversarial training for the whole model to reinforce the performance of information separation and machine translation simultaneously. Experiment results show that our method can outperform competitive baselines greatly on multiple data sets.

cs.CL↗
arXiv2019

GPT-based Generation for Classical Chinese Poetry

We present a simple yet effective method for generating high quality classical Chinese poetry with Generative Pre-trained Language Model (GPT). The method adopts a simple GPT model, without using any human crafted rules or features, or designing any additional neural components. While the proposed model learns to generate various forms of classical Chinese poems, including Jueju, Lüshi, various Cipai and Couples, the generated poems are of very high quality. We also propose and implement a method to fine-tune the model to generate acrostic poetry. To the best of our knowledge, this is the first to employ GPT in developing a poetry generation system. We have released an online mini demonstration program on Wechat to show the generation capability of the proposed method for classical Chinese poetry.

cs.CL↗
arXiv2019

PCGAN-CHAR: Progressively Trained Classifier Generative Adversarial Networks for Classification of Noisy Handwritten Bangla Characters

Due to the sparsity of features, noise has proven to be a great inhibitor in the classification of handwritten characters. To combat this, most techniques perform denoising of the data before classification. In this paper, we consolidate the approach by training an all-in-one model that is able to classify even noisy characters. For classification, we progressively train a classifier generative adversarial network on the characters from low to high resolution. We show that by learning the features at each resolution independently a trained model is able to accurately classify characters even in the presence of noise. We experimentally demonstrate the effectiveness of our approach by classifying noisy versions of MNIST, handwritten Bangla Numeral, and Basic Character datasets.

cs.CV↗
arXiv2019

Modeling Semantic Compositionality with Sememe Knowledge

Semantic compositionality (SC) refers to the phenomenon that the meaning of a complex linguistic unit can be composed of the meanings of its constituents. Most related works focus on using complicated compositionality functions to model SC while few works consider external knowledge in models. In this paper, we verify the effectiveness of sememes, the minimum semantic units of human languages, in modeling SC by a confirmatory experiment. Furthermore, we make the first attempt to incorporate sememe knowledge into SC models, and employ the sememeincorporated models in learning representations of multiword expressions, a typical task of SC. In experiments, we implement our models by incorporating knowledge from a famous sememe knowledge base HowNet and perform both intrinsic and extrinsic evaluations. Experimental results show that our models achieve significant performance boost as compared to the baseline methods without considering sememe knowledge. We further conduct quantitative analysis and case studies to demonstrate the effectiveness of applying sememe knowledge in modeling SC. All the code and data of this paper can be obtained on https://github.com/thunlp/Sememe-SC.

cs.CL↗
arXiv2019

Decomposable Neural Paraphrase Generation

Paraphrasing exists at different granularity levels, such as lexical level, phrasal level and sentential level. This paper presents Decomposable Neural Paraphrase Generator (DNPG), a Transformer-based model that can learn and generate paraphrases of a sentence at different levels of granularity in a disentangled way. Specifically, the model is composed of multiple encoders and decoders with different structures, each of which corresponds to a specific granularity. The empirical study shows that the decomposition mechanism of DNPG makes paraphrase generation more interpretable and controllable. Based on DNPG, we further develop an unsupervised domain adaptation method for paraphrase generation. Experimental results show that the proposed model achieves competitive in-domain performance compared to the state-of-the-art neural models, and significantly better performance when adapting to a new domain.

cs.CL↗
arXiv2019

Bridging the Gap between Training and Inference for Neural Machine Translation

Neural Machine Translation (NMT) generates target words sequentially in the way of predicting the next word conditioned on the context words. At training time, it predicts with the ground truth words as context while at inference it has to generate the entire sequence from scratch. This discrepancy of the fed context leads to error accumulation among the way. Furthermore, word-level training requires strict matching between the generated sequence and the ground truth sequence which leads to overcorrection over different but reasonable translations. In this paper, we address these issues by sampling context words not only from the ground truth sequence but also from the predicted sequence by the model during training, where the predicted sequence is selected with a sentence-level optimum. Experiment results on Chinese->English and WMT'14 English->German translation tasks demonstrate that our approach can achieve significant improvements on multiple datasets.

cs.CL↗
arXiv2019

ERNIE: Enhanced Language Representation with Informative Entities

Neural language representation models such as BERT pre-trained on large-scale corpora can well capture rich semantic patterns from plain text, and be fine-tuned to consistently improve the performance of various NLP tasks. However, the existing pre-trained language models rarely consider incorporating knowledge graphs (KGs), which can provide rich structured knowledge facts for better language understanding. We argue that informative entities in KGs can enhance language representation with external knowledge. In this paper, we utilize both large-scale textual corpora and KGs to train an enhanced language representation model (ERNIE), which can take full advantage of lexical, syntactic, and knowledge information simultaneously. The experimental results have demonstrated that ERNIE achieves significant improvements on various knowledge-driven tasks, and meanwhile is comparable with the state-of-the-art model BERT on other common NLP tasks. The source code of this paper can be obtained from https://github.com/thunlp/ERNIE.

cs.CL↗
arXiv2019

Bilingual-GAN: A Step Towards Parallel Text Generation

Latent space based GAN methods and attention based sequence to sequence models have achieved impressive results in text generation and unsupervised machine translation respectively. Leveraging the two domains, we propose an adversarial latent space based model capable of generating parallel sentences in two languages concurrently and translating bidirectionally. The bilingual generation goal is achieved by sampling from the latent space that is shared between both languages. First two denoising autoencoders are trained, with shared encoders and back-translation to enforce a shared latent state between the two languages. The decoder is shared for the two translation directions. Next, a GAN is trained to generate synthetic "code" mimicking the languages' shared latent space. This code is then fed into the decoder to generate text in either language. We perform our experiments on Europarl and Multi30k datasets, on the English-French language pair, and document our performance using both supervised and unsupervised machine translation.

cs.CL↗
arXiv2019

Why do you take that route?

The purpose of this paper is to determine whether a particular context factor among the variables that a researcher is interested in causally affects the route choice behavior of drivers. To our knowledge, there is limited literature that consider the effects of various factors on route choice based on causal inference.Yet, collecting data sets that are sensitive to the aforementioned factors are challenging and the existing approaches usually take into account only the general factors motivating drivers route choice behavior. To fill these gaps, we carried out a study using Immersive Virtual Environment (IVE) tools to elicit drivers' route choice behavioral data, covering drivers' network familiarity, educationlevel, financial concern, etc, apart from conventional measurement variables. Having context-aware, high-fidelity properties, IVE data affords the opportunity to incorporate the impacts of human related factors into the route choice causal analysis and advance a more customizable research tool for investigating causal factors on path selection in network routing. This causal analysis provides quantitative evidence to support drivers' diversion decision.

cs.CY↗
arXiv2019

Improving Route Choice Models by Incorporating Contextual Factors via Knowledge Distillation

Route Choice Models predict the route choices of travelers traversing an urban area. Most of the route choice models link route characteristics of alternative routes to those chosen by the drivers. The models play an important role in prediction of traffic levels on different routes and thus assist in development of efficient traffic management strategies that result in minimizing traffic delay and maximizing effective utilization of transport system. High fidelity route choice models are required to predict traffic levels with higher accuracy. Existing route choice models do not take into account dynamic contextual conditions such as the occurrence of an accident, the socio-cultural and economic background of drivers, other human behaviors, the dynamic personal risk level, etc. As a result, they can only make predictions at an aggregate level and for a fixed set of contextual factors. For higher fidelity, it is highly desirable to use a model that captures significance of subjective or contextual factors in route choice. This paper presents a novel approach for developing high-fidelity route choice models with increased predictive power by augmenting existing aggregate level baseline models with information on drivers' responses to contextual factors obtained from Stated Choice Experiments carried out in an Immersive Virtual Environment through the use of knowledge distillation.

cs.LG↗
arXiv2018

The resistance distance and Kirchhoff index on quadrilateral graph and pentagonal graph

The quadrilateral graph Q(G) is obtained from G by replacing each edge in G with two parallel paths of length 1 and 3, whereas the pentagonal graph W(G) is obtained from G by replacing each edge in G with two parallel paths of length 1 and 4. In this paper, closed-form formulas of resistance distance and Kirchhoff index for quadrilateral graph and pentagonal graph are obtained whenever G is an arbitrary graph.

math.CO↗
arXiv2018

Improving the Robustness of Speech Translation

Although neural machine translation (NMT) has achieved impressive progress recently, it is usually trained on the clean parallel data set and hence cannot work well when the input sentence is the production of the automatic speech recognition (ASR) system due to the enormous errors in the source. To solve this problem, we propose a simple but effective method to improve the robustness of NMT in the case of speech translation. We simulate the noise existing in the realistic output of the ASR system and inject them into the clean parallel data so that NMT can work under similar word distributions during training and testing. Besides, we also incorporate the Chinese Pinyin feature which is easy to get in speech translation to further improve the translation performance. Experiment results show that our method has a more stable performance and outperforms the baseline by an average of 3.12 BLEU on multiple noisy test sets, even while achieves a generalization improvement on the WMT'17 Chinese-English test set.

cs.CL↗
arXiv2018

Learning to Jointly Translate and Predict Dropped Pronouns with a Shared Reconstruction Mechanism

Pronouns are frequently omitted in pro-drop languages, such as Chinese, generally leading to significant challenges with respect to the production of complete translations. Recently, Wang et al. (2018) proposed a novel reconstruction-based approach to alleviating dropped pronoun (DP) translation problems for neural machine translation models. In this work, we improve the original model from two perspectives. First, we employ a shared reconstructor to better exploit encoder and decoder representations. Second, we jointly learn to translate and predict DPs in an end-to-end manner, to avoid the errors propagated from an external DP prediction model. Experimental results show that our approach significantly improves both translation performance and DP prediction accuracy.

cs.CL↗
arXiv2018

Resistance distance and Kirchhoff index in generalized R-vertex and R-edge corona for graphs

For a graph G, the graph R(G) of a graph G is the graph obtained by adding a new vertex for each edge of G and joining each new vertex to both end vertices of the correspond- ing edge. Let I(G) be the set of newly added vertices. In this paper, we derive closed-form formulas for resistance distance and Kirchhoff index of generalized R-vertex and R-edge corona whenever G and Hi are arbitrary graph. These results generalize the existing results in [9].

math.SP↗
arXiv2018

Refining Source Representations with Relation Networks for Neural Machine Translation

Although neural machine translation with the encoder-decoder framework has achieved great success recently, it still suffers drawbacks of forgetting distant information, which is an inherent disadvantage of recurrent neural network structure, and disregarding relationship between source words during encoding step. Whereas in practice, the former information and relationship are often useful in current step. We target on solving these problems and thus introduce relation networks to learn better representations of the source. The relation networks are able to facilitate memorization capability of recurrent neural network via associating source words with each other, this would also help retain their relationships. Then the source representations and all the relations are fed into the attention component together while decoding, with the main encoder-decoder framework unchanged. Experiments on several datasets show that our method can improve the translation performance significantly over the conventional encoder-decoder model and even outperform the approach involving supervised syntactic knowledge.

cs.CL↗