Recent interest in entity linking has focused in the zero-shot scenario, where at test time the entity mention to be labelled is never seen during training, or may belong to a different domain from the source domain. Current work leverage pre-trained BERT with the implicit assumption that it bridges the gap between the source and target domain distributions. However, fine-tuned BERT has a considerable underperformance at zero-shot when applied in a different domain. We solve this problem by proposing a Transformational Biencoder that incorporates a transformation into BERT to perform a zero-shot transfer from the source domain during training. As like previous work, we rely on negative entities to encourage our model to discriminate the golden entities during training. To generate these negative entities, we propose a simple but effective strategy that takes the domain of the golden entity into perspective. Our experimental results on the benchmark dataset Zeshel show effectiveness of our approach and achieve new state-of-the-art.

The introduction of VAE provides an efficient framework for the learning of generative models, including generative topic models. However, when the topic model is a Latent Dirichlet Allocation (LDA) model, a central technique of VAE, the reparameterization trick, fails to be applicable. This is because no reparameterization form of Dirichlet distributions is known to date that allows the use of the reparameterization trick. In this work, we propose a new method, which we call Rounded Reparameterization Trick (RRT), to reparameterize Dirichlet distributions for the learning of VAE-LDA models. This method, when applied to a VAE-LDA model, is shown experimentally to outperform the existing neural topic models on several benchmark datasets and on a synthetic dataset.

The dependencies between system and user utterances in the same turn and across different turns are not fully considered in existing multidomain dialogue state tracking (MDST) models. In this study, we argue that the incorporation of these dependencies is crucial for the design of MDST and propose Parallel Interactive Networks (PIN) to model these dependencies. Specifically, we integrate an interactive encoder to jointly model the in-turn dependencies and cross-turn dependencies. The slot-level context is introduced to extract more expressive features for different slots. And a distributed copy mechanism is utilized to selectively copy words from historical system utterances or historical user utterances. Empirical studies demonstrated the superiority of the proposed PIN model.

The idea of using multi-task learning approaches to address the joint extraction of entity and relation is motivated by the relatedness between the entity recognition task and the relation classification task. Existing methods using multi-task learning techniques to address the problem learn interactions among the two tasks through a shared network, where the shared information is passed into the task-specific networks for prediction. However, such an approach hinders the model from learning explicit interactions between the two tasks to improve the performance on the individual tasks. As a solution, we design a multi-task learning model which we refer to as recurrent interaction network which allows the learning of interactions dynamically, to effectively model task-specific features for classification. Empirical studies on two real-world datasets confirm the superiority of the proposed model.

Dialogue state tracking (DST) is an important part of a spoken dialogue system. Existing DST models either ignore temporal feature dependencies across dialogue turns or fail to explicitly model temporal state dependencies in a dialogue. In this work, we propose Temporally Expressive Networks (TEN) to jointly model the two types of temporal dependencies in DST. The TEN model utilizes the power of recurrent networks and probabilistic graphical models. Evaluating on standard datasets, TEN is demonstrated to improve the accuracy of turn-level-state prediction and the state aggregation.

Distant supervision for relation extraction enables one to effectively acquire structured relations out of very large text corpora with less human efforts. Nevertheless, most of the prior-art models for such tasks assume that the given text can be noisy, but their corresponding labels are clean. Such unrealistic assumption is contradictory with the fact that the given labels are often noisy as well, thus leading to significant performance degradation of those models on real-world data. To cope with this challenge, we propose a novel label-denoising framework that combines neural network with probabilistic modelling, which naturally takes into account the noisy labels during learning. We empirically demonstrate that our approach significantly improves the current art in uncovering the ground-truth relation labels.

We propose a method based on neural networks to identify the sentiment polarity of opinion words expressed on a specific aspect of a sentence. Although a large majority of works typically focus on leveraging the expressive power of neural networks in handling this task, we explore the possibility of integrating dependency trees with neural networks for representation learning. To this end, we present a convolution over a dependency tree (CDT) model which exploits a Bi-directional Long Short Term Memory (Bi-LSTM) to learn representations for features of a sentence, and further enhance the embeddings with a graph convolutional network (GCN) which operates directly on the dependency tree of the sentence. Our approach propagates both contextual and dependency information from opinion words to aspect words, offering discriminative properties for supervision. Experimental results ranks our approach as the new state-of-the-art in aspect-based sentiment classification.

We propose a novel strategy to encode the syntax parse tree of sentence into a learnable distributed representation. The proposed syntax encoding scheme is provably information-lossless. In specific, an embedding vector is constructed for each word in the sentence, encoding the path in the syntax tree corresponding to the word. The one-to-one correspondence between these “syntax-embedding” vectors and the words (hence their embedding vectors) in the sentence makes it easy to integrate such a representation with all word-level NLP models. We empirically show the benefits of the syntax embeddings on the Authorship Attribution domain, where our approach improves upon the prior art and achieves new performance records on five benchmarking data sets.

In this paper, we study the problem of question answering over knowledge base. We identify that the primary bottleneck in this problem is the difficulty in accurately predicting the relations connecting the subject entity to the object entities. We advocate a new model architecture, APVA, which includes a verification mechanism responsible for checking the correctness of predicted relations. The APVA framework naturally supports a well-principled iterative training procedure, which we call turbo training. We demonstrate via experiments that the APVA-TUBRO approach drastically improves the question answering performance.