Total: 11
Although end-to-end Neural Machine Translation (NMT) has achieved remarkable progress in the past two years, it suffers from a major drawback: translations generated by NMT systems often lack of adequacy. It has been widely observed that NMT tends to repeatedly translate some source words while mistakenly ignoring other words. To alleviate this problem, we propose a novel encoder-decoder-reconstructor framework for NMT. The reconstructor, incorporated into the NMT model, manages to reconstruct the input source sentence from the hidden layer of the output target sentence, to ensure that the information in the source side is transformed to the target side as much as possible. Experiments show that the proposed framework significantly improves the adequacy of NMT output and achieves superior translation result over state-of-the-art NMT and statistical MT systems.
Probabilistic topic models could be used to extract low-dimension topics from document collections. However, such models without any human knowledge often produce topics that are not interpretable. In recent years, a number of knowledge-based topic models have been proposed, but they could not process fact-oriented triple knowledge in knowledge graphs. Knowledge graph embeddings, on the other hand, automatically capture relations between entities in knowledge graphs. In this paper, we propose a novel knowledge-based topic model by incorporating knowledge graph embeddings into topic modeling. By combining latent Dirichlet allocation, a widely used topic model with knowledge encoded by entity vectors, we improve the semantic coherence significantly and capture a better representation of a document in the topic space. Our evaluation results will demonstrate the effectiveness of our method.
Knowledge graph embedding represents entities and relations in knowledge graph as low-dimensional, continuous vectors, and thus enables knowledge graph compatible with machine learning models. Though there have been a variety of models for knowledge graph embedding, most methods merely concentrate on the fact triples, while supplementary textual descriptions of entities and relations have not been fully employed. To this end, this paper proposes the semantic space projection (SSP) model which jointly learns from the symbolic triples and textual descriptions. Our model builds interaction between the two information sources, and employs textual descriptions to discover semantic relevance and offer precise semantic embedding. Extensive experiments show that our method achieves substantial improvements against baselines on the tasks of knowledge graph completion and entity classification.
Distant supervision for relation extraction is an efficient method to scale relation extraction to very large corpora which contains thousands of relations. However, the existing approaches have flaws on selecting valid instances and lack of background knowledge about the entities. In this paper, we propose a sentence-level attention model to select the valid instances, which makes full use of the supervision information from knowledge bases. And we extract entity descriptions from Freebase and Wikipedia pages to supplement background knowledge for our task. The background knowledge not only provides more information for predicting relations, but also brings better entity representations for the attention module. We conduct three experiments on a widely used dataset and the experimental results show that our approach outperforms all the baseline systems significantly.
Bag-of-ngrams (BoN) models are commonly used for representing text. One of the main drawbacks of traditional BoN is the ignorance of n-gram's semantics. In this paper, we introduce the concept of Neural Bag-of-ngrams (Neural-BoN), which replaces sparse one-hot n-gram representation in traditional BoN with dense and rich-semantic n-gram representations. We first propose context guided n-gram representation by adding n-grams to word embeddings model. However, the context guided learning strategy of word embeddings is likely to miss some semantics for text-level tasks. Text guided n-gram representation and label guided n-gram representation are proposed to capture more semantics like topic or sentiment tendencies. Neural-BoN with the latter two n-gram representations achieve state-of-the-art results on 4 document-level classification datasets and 6 semantic relatedness categories. They are also on par with some sophisticated DNNs on 3 sentence-level classification datasets. Similar to traditional BoN, Neural-BoN is efficient, robust and easy to implement. We expect it to be a strong baseline and be used in more real-world applications.
Developed so far, multi-document summarization has reached its bottleneck due to the lack of sufficient training data and diverse categories of documents. Text classification just makes up for these deficiencies. In this paper, we propose a novel summarization system called TCSum, which leverages plentiful text classification data to improve the performance of multi-document summarization. TCSum projects documents onto distributed representations which act as a bridge between text classification and summarization. It also utilizes the classification results to produce summaries of different styles. Extensive experiments on DUC generic multi-document summarization datasets show that, TCSum can achieve the state-of-the-art performance without using any hand-crafted features and has the capability to catch the variations of summary styles with respect to different text categories.
More and more users prefer to ask their technical questions online. For machines, understanding a question is nontrivial. Current approaches lack explicit background knowledge.In this paper, we introduce a novel technical question understanding approach to recommending probable solutions to users. First, a knowledge graph is constructed which contains abundant technical information, and an augmented knowledge graph is built on the basis of the knowledge graph, to link the knowledge graph and documents. Then we develop a light weight question driven mechanism to select candidate documents. To improve the online performance, we propose an index-based random walk to support the online search. We use comprehensive experiments to evaluate the effectiveness of our approach on a large scale of real-world query logs. Our system outperforms main-stream search engine and the state-of-art information retrieval methods. Meanwhile, extensive experiments confirm the efficiency of our index-based online search mechanism.
One of the main goals of natural language processing (NLP) is synthetic understanding of natural language documents, especially reading comprehension (RC). An obstacle to the further development of RC systems is the absence of a synthetic methodology to analyze their performance. It is difficult to examine the performance of systems based solely on their results for tasks because the process of natural language understanding is complex. In order to tackle this problem, we propose in this paper a methodology inspired by unit testing in software engineering that enables the examination of RC systems from multiple aspects. Our methodology consists of three steps. First, we define a set of prerequisite skills for RC based on existing NLP tasks. We assume that RC capability can be divided into these skills. Second, we manually annotate a dataset for an RC task with information regarding the skills needed to answer each question. Finally, we analyze the performance of RC systems for each skill based on the annotation. The last two steps highlight two aspects: the characteristics of the dataset, and the weaknesses in and differences among RC systems. We tested the effectiveness of our methodology by annotating the Machine Comprehension Test (MCTest) dataset and analyzing four existing systems (including a neural system) on it. The results of the annotations showed that answering questions requires a combination of skills, and clarified the kinds of capabilities that systems need to understand natural language. We conclude that the set of prerequisite skills we define are promising for the decomposition and analysis of RC.
We present SummaRuNNer, a Recurrent Neural Network (RNN) based sequence model for extractive summarization of documents and show that it achieves performance better than or comparable to state-of-the-art. Our model has the additional advantage of being very interpretable, since it allows visualization of its predictions broken up by abstract features such as information content, salience and novelty. Another novel contribution of our work is abstractive training of our extractive model that can train on human generated reference summaries alone, eliminating the need for sentence-level extractive labels.
Math word problems provide a natural abstraction to a range of natural language understanding problems that involve reasoning about quantities, such as interpreting election results, news about casualties, and the financial section of a newspaper. Units associated with the quantities often provide information that is essential to support this reasoning. This paper proposes a principled way to capture and reason about units and shows how it can benefit an arithmetic word problem solver. This paper presents the concept of Unit Dependency Graphs (UDGs), which provides a compact representation of the dependencies between units of numbers mentioned in a given problem. Inducing the UDG alleviates the brittleness of the unit extraction system and allows for a natural way to leverage domain knowledge about unit compatibility, for word problem solving. We introduce a decomposed model for inducing UDGs with minimal additional annotations, and use it to augment the expressions used in the arithmetic word problem solver of (Roy and Roth 2015) via a constrained inference framework. We show that introduction of UDGs reduces the error of the solver by over 10 %, surpassing all existing systems for solving arithmetic word problems. In addition, it also makes the system more robust to adaptation to new vocabulary and equation forms .
Recognizing lexical entailment (RLE) always plays an important role in inference of natural language, i.e., identifying whether one word entails another, for example, fox entails animal. In the literature, automatically recognizing lexical entailment for word pairs deeply relies on words' contextual representations. However, as a "prototype" vector, a single representation cannot reveal multifaceted aspects of the words due to their homonymy and polysemy. In this paper, we propose a supervised Context-Enriched Neural Network (CENN) method for recognizing lexical entailment. To be specific, we first utilize multiple embedding vectors from different contexts to represent the input word pairs. Then, through different combination methods and attention mechanism, we integrate different embedding vectors and optimize their weights to predict whether there are entailment relations in word pairs. Moreover, our proposed framework is flexible and open to handle different word contexts and entailment perspectives in the text corpus. Extensive experiments on five datasets show that our approach significantly improves the performance of automatic RLE in comparison with several state-of-the-art methods.