Network representation has been recently exploited for many applications, such as citation recommendation, multi-label classification and link prediction. It learns low-dimensional vector representation for each vertex in networks. Existing network representation methods only focus on incomplete aspects of vertex information (i.e., vertex content, network structure or partial integration), moreover they are commonly designed for homogeneous information networks where all the vertices of a network are of the same type. In this paper, we propose a deep network representation model that integrates network structure and the vertex content information into a unified framework by exploiting generative adversarial network, and represents different types of vertices in the heterogeneous network in a continuous and common vector space. Based on the proposed model, we can obtain heterogeneous bibliographic network representation for efficient citation recommendation. The proposed model also makes personalized citation recommendation possible, which is a new issue that a few papers addressed in the past. When evaluated on the AAN and DBLP datasets, the performance of the proposed heterogeneous bibliographic network based citation recommendation approach is comparable with that of the other network representation based citation recommendation approaches. The results also demonstrate that the personalized citation recommendation approach is more effective than the non-personalized citation recommendation approach.

Nowadays, it is very common for one person to be in different social networks. Linking identical users across different social networks, also known as the User Identity Linkage (UIL) problem, is fundamental for many applications. There are two major challenges in the UIL problem. First, it's extremely expensive to collect manually linked user pairs as training data. Second, the user attributes in different networks are usually defined and formatted very differently which makes attribute alignment very hard. In this paper we propose CoLink, a general unsupervised framework for the UIL problem. CoLink employs a co-training algorithm, which manipulates two independent models, the attribute-based model and the relationship-based model, and makes them reinforce each other iteratively in an unsupervised way. We also propose the sequence-to-sequence learning as a very effective implementation of the attribute-based model, which can well handle the challenge of the attribute alignment by treating it as a machine translation problem. We apply CoLink to a UIL task of mapping the employees in an enterprise network to their LinkedIn profiles. The experiment results show that CoLink generally outperforms the state-of-the-art unsupervised approaches by an F1 increase over 20%.

Linguistic Inquiry and Word Count (LIWC) is a word counting software tool which has been used for quantitative text analysis in many fields. Due to its success and popularity, the core lexicon has been translated into Chinese and many other languages. However, the lexicon only contains several thousand of words, which is deficient compared with the number of common words in Chinese. Current approaches often require manually expanding the lexicon, but it often takes too much time and requires linguistic experts to extend the lexicon. To address this issue, we propose to expand the LIWC lexicon automatically. Specifically, we consider it as a hierarchical classification problem and utilize the Sequence-to-Sequence model to classify words in the lexicon. Moreover, we use the sememe information with the attention mechanism to capture the exact meanings of a word, so that we can expand a more precise and comprehensive lexicon. The experimental results show that our model has a better understanding of word meanings with the help of sememes and achieves significant and consistent improvements compared with the state-of-the-art methods. The source code of this paper can be obtained from https://github.com/thunlp/Auto_CLIWC.

We present StarSpace, a general-purpose neural embedding model that can solve a wide variety of problems: labeling tasks such as text classification,ranking tasks such as information retrieval/web search,collaborative filtering-based  or content-based recommendation,embedding of multi-relational graphs, and learning word, sentence or document level embeddings.In each case the model works by embedding those entities comprised of discrete features and comparing them against each other -- learning similarities dependent on the task.Empirical results on a number of tasks show that StarSpace is highly competitive with existing methods, whilst also being generally applicable to new cases where those methods are not.

A major goal of grounded language learning research is to enable robots to connect language predicates to a robot's physical interactive perception of the world. Coupling object exploratory behaviors such as grasping, lifting, and looking with multiple sensory modalities (e.g., audio, haptics, and vision) enables a robot to ground non-visual words like ``heavy'' as well as visual words like ``red''. A major limitation of existing approaches to multi-modal language grounding is that a robot has to exhaustively explore training objects with a variety of actions when learning a new such language predicate. This paper proposes a method for guiding a robot's behavioral exploration policy when learning a novel predicate based on known grounded predicates and the novel predicate's linguistic relationship to them. We demonstrate our approach on two datasets in which a robot explored large sets of objects and was tasked with learning to recognize whether novel words applied to those objects.

Models that can execute natural language instructions for situated robotic tasks such as assembly and navigation have several useful applications in homes, offices, and remote scenarios.We study the semantics of spatially-referred configuration and arrangement instructions, based on the challenging Bisk-2016 blank-labeled block dataset. This task involves finding a source block and moving it to the target position (mentioned via a reference block and offset), where the blocks have no names or colors and are just referred to via spatial location features.We present novel models for the subtasks of source block classification and target position regression, based on joint-loss language and spatial-world representation learning, as well as CNN-based and dual attention models to compute the alignment between the world blocks and the instruction phrases. For target position prediction, we compare two inference approaches: annealed sampling via policy gradient versus expectation inference via supervised regression. Our models achieve the new state-of-the-art on this task, with an improvement of 47% on source block accuracy and 22% on target position distance.

In this work, we investigate word embedding algorithms in the context of natural language processing. In particular, we examine the notion of ``negative examples'', the unobserved or insignificant word-context co-occurrences, in spectral methods. we provide a new formulation for the word embedding problem by proposing a new intuitive objective function that perfectly justifies the use of negative examples. In fact, our algorithm not only learns from the important word-context co-occurrences, but also it learns from the abundance of unobserved or insignificant co-occurrences to improve the distribution of words in the latent embedded space. We analyze the algorithm theoretically and provide an optimal solution for the problem using spectral analysis. We have trained various word embedding algorithms on articles of Wikipedia with 2.1 billion tokens and show that negative sampling can boost the quality of spectral methods. Our algorithm provides results as good as the state-of-the-art but in a much faster and efficient way.

Automated multi-document extractive text summarization is a widely studied research problem in the field of natural language understanding. Such extractive mechanisms compute in some form the worthiness of a sentence to be included into the summary. While the conventional approaches rely on human crafted document-independent features to generate a summary, we develop a data-driven novel summary system called HNet, which exploits the various semantic and compositional aspects latent in a sentence to capture document independent features. The network learns sentence representation in a way that, salient sentences are closer in the vector space than non-salient sentences. This semantic and compositional feature vector is then concatenated with the document-dependent features for sentence ranking. Experiments on the DUC benchmark datasets (DUC-2001, DUC-2002 and DUC-2004) indicate that our model shows significant performance gain of around 1.5-2 points in terms of ROUGE score compared with the state-of-the-art baselines.

A major challenge in Entity Linking (EL) is making effective use of contextual information to disambiguate mentions to Wikipedia that might refer to different entities in different contexts. The problem exacerbates with cross-lingual EL which involves linking mentions written in non-English documents to entries in the English Wikipedia: to compare textual clues across languages we need to compute similarity between textual fragments across languages. In this paper, we propose a neural EL model that trains fine-grained similarities and dissimilarities between the query and candidate document from multiple perspectives, combined with convolution and tensor networks. Further, we show that this English-trained system can be applied, in zero-shot learning, to other languages by making surprisingly effective use of multi-lingual embeddings. The proposed system has strong empirical evidence yielding state-of-the-art results in English as well as cross-lingual: Spanish and Chinese TAC 2015 datasets.

Variational encoder-decoders (VEDs) have shown promising results in dialogue generation. However, the latent variable distributions are usually approximated by a much simpler model than the powerful RNN structure used for encoding and decoding, yielding the KL-vanishing problem and inconsistent training objective. In this paper, we separate the training step into two phases: The first phase learns to autoencode discrete texts into continuous embeddings, from which the second phase learns to generalize latent representations by reconstructing the encoded embedding.  In this case, latent variables are sampled by transforming Gaussian noise through multi-layer perceptrons and are trained with a separate VED model, which has the potential of realizing a much more flexible distribution. We compare our model with current popular models and the experiment demonstrates substantial improvement in both metric-based and human evaluations.