arXiv subjects

Maosong Sun

Publications and source records attributed to Maosong Sun.

At least 415 records · Page 23Linked to original sources

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

THUMT: An Open Source Toolkit for Neural Machine Translation

This paper introduces THUMT, an open-source toolkit for neural machine translation (NMT) developed by the Natural Language Processing Group at Tsinghua University. THUMT implements the standard attention-based encoder-decoder framework on top of Theano and supports three training criteria: maximum likelihood estimation, minimum risk training, and semi-supervised training. It features a visualization tool for displaying the relevance between hidden states in neural networks and contextual words, which helps to analyze the internal workings of NMT. Experiments on Chinese-English datasets show that THUMT using minimum risk training significantly outperforms GroundHog, a state-of-the-art toolkit for NMT.

cs.CL↗

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

Joint POS Tagging and Dependency Parsing with Transition-based Neural Networks

While part-of-speech (POS) tagging and dependency parsing are observed to be closely related, existing work on joint modeling with manually crafted feature templates suffers from the feature sparsity and incompleteness problems. In this paper, we propose an approach to joint POS tagging and dependency parsing using transition-based neural networks. Three neural network based classifiers are designed to resolve shift/reduce, tagging, and labeling conflicts. Experiments show that our approach significantly outperforms previous methods for joint POS tagging and dependency parsing across a variety of natural languages.

cs.CL↗

arXiv2017

Neural Machine Translation with Pivot Languages

While recent neural machine translation approaches have delivered state-of-the-art performance for resource-rich language pairs, they suffer from the data scarcity problem for resource-scarce language pairs. Although this problem can be alleviated by exploiting a pivot language to bridge the source and target languages, the source-to-pivot and pivot-to-target translation models are usually independently trained. In this work, we introduce a joint training algorithm for pivot-based neural machine translation. We propose three methods to connect the two models and enable them to interact with each other during training. Experiments on Europarl and WMT corpora show that joint training of source-to-pivot and pivot-to-target models leads to significant improvements over independent training across various languages.

cs.CL↗

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

Semi-Supervised Learning for Neural Machine Translation

While end-to-end neural machine translation (NMT) has made remarkable progress recently, NMT systems only rely on parallel corpora for parameter estimation. Since parallel corpora are usually limited in quantity, quality, and coverage, especially for low-resource languages, it is appealing to exploit monolingual corpora to improve NMT. We propose a semi-supervised approach for training NMT models on the concatenation of labeled (parallel corpora) and unlabeled (monolingual corpora) data. The central idea is to reconstruct the monolingual corpora using an autoencoder, in which the source-to-target and target-to-source translation models serve as the encoder and decoder, respectively. Our approach can not only exploit the monolingual corpora of the target language, but also of the source language. Experiments on the Chinese-English dataset show that our approach achieves significant improvements over state-of-the-art SMT and NMT systems.

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↗

arXiv2016

Minimum Risk Training for Neural Machine Translation

We propose minimum risk training for end-to-end neural machine translation. Unlike conventional maximum likelihood estimation, minimum risk training is capable of optimizing model parameters directly with respect to arbitrary evaluation metrics, which are not necessarily differentiable. Experiments show that our approach achieves significant improvements over maximum likelihood estimation on a state-of-the-art neural machine translation system across various languages pairs. Transparent to architectures, our approach can be applied to more neural networks and potentially benefit more NLP tasks.

cs.CL↗

arXiv2016

Agreement-based Learning of Parallel Lexicons and Phrases from Non-Parallel Corpora

We introduce an agreement-based approach to learning parallel lexicons and phrases from non-parallel corpora. The basic idea is to encourage two asymmetric latent-variable translation models (i.e., source-to-target and target-to-source) to agree on identifying latent phrase and word alignments. The agreement is defined at both word and phrase levels. We develop a Viterbi EM algorithm for jointly training the two unidirectional models efficiently. Experiments on the Chinese-English dataset show that agreement-based learning significantly improves both alignment and translation performance.

cs.CL↗

arXiv2016

Agreement-based Joint Training for Bidirectional Attention-based Neural Machine Translation

The attentional mechanism has proven to be effective in improving end-to-end neural machine translation. However, due to the intricate structural divergence between natural languages, unidirectional attention-based models might only capture partial aspects of attentional regularities. We propose agreement-based joint training for bidirectional attention-based end-to-end neural machine translation. Instead of training source-to-target and target-to-source translation models independently,our approach encourages the two complementary models to agree on word alignment matrices on the same training data. Experiments on Chinese-English and English-French translation tasks show that agreement-based joint training significantly improves both alignment and translation quality over independent training.

cs.CL↗

arXiv2016

Generating Chinese Classical Poems with RNN Encoder-Decoder

We take the generation of Chinese classical poem lines as a sequence-to-sequence learning problem, and build a novel system based on the RNN Encoder-Decoder structure to generate quatrains (Jueju in Chinese), with a topic word as input. Our system can jointly learn semantic meaning within a single line, semantic relevance among lines in a poem, and the use of structural, rhythmical and tonal patterns, without utilizing any constraint templates. Experimental results show that our system outperforms other competitive systems. We also find that the attention mechanism can capture the word associations in Chinese classical poetry and inverting target lines in training can improve performance.

cs.CL↗

arXiv2015

Modeling Relation Paths for Representation Learning of Knowledge Bases

Representation learning of knowledge bases (KBs) aims to embed both entities and relations into a low-dimensional space. Most existing methods only consider direct relations in representation learning. We argue that multiple-step relation paths also contain rich inference patterns between entities, and propose a path-based representation learning model. This model considers relation paths as translations between entities for representation learning, and addresses two key challenges: (1) Since not all relation paths are reliable, we design a path-constraint resource allocation algorithm to measure the reliability of relation paths. (2) We represent relation paths via semantic composition of relation embeddings. Experimental results on real-world datasets show that, as compared with baselines, our model achieves significant and consistent improvements on knowledge base completion and relation extraction from text.

cs.CL↗

arXiv2014

Contrastive Unsupervised Word Alignment with Non-Local Features

Word alignment is an important natural language processing task that indicates the correspondence between natural languages. Recently, unsupervised learning of log-linear models for word alignment has received considerable attention as it combines the merits of generative and discriminative approaches. However, a major challenge still remains: it is intractable to calculate the expectations of non-local features that are critical for capturing the divergence between natural languages. We propose a contrastive approach that aims to differentiate observed training examples from noises. It not only introduces prior knowledge to guide unsupervised learning but also cancels out partition functions. Based on the observation that the probability mass of log-linear models for word alignment is usually highly concentrated, we propose to use top-n alignments to approximate the expectations with respect to posterior distributions. This allows for efficient and accurate calculation of expectations of non-local features. Experiments show that our approach achieves significant improvements over state-of-the-art unsupervised word alignment methods.

cs.CL↗

arXiv2013

Reduce Meaningless Words for Joint Chinese Word Segmentation and Part-of-speech Tagging

Conventional statistics-based methods for joint Chinese word segmentation and part-of-speech tagging (S&T) have generalization ability to recognize new words that do not appear in the training data. An undesirable side effect is that a number of meaningless words will be incorrectly created. We propose an effective and efficient framework for S&T that introduces features to significantly reduce meaningless words generation. A general lexicon, Wikepedia and a large-scale raw corpus of 200 billion characters are used to generate word-based features for the wordhood. The word-lattice based framework consists of a character-based model and a word-based model in order to employ our word-based features. Experiments on Penn Chinese treebank 5 show that this method has a 62.9% reduction of meaningless word generation in comparison with the baseline. As a result, the F1 measure for segmentation is increased to 0.984.

cs.CL↗