Yansong Feng

Semantic Relation Classification via Convolutional Neural Networks with Simple Negative Sampling

Syntactic features play an essential role in identifying relationship in a sentence. Previous neural network models directly work on raw word sequences or constituent parse trees, thus often suffer from irrelevant information introduced when subjects and objects are in a long distance. In this paper, we propose to learn more robust relation representations from shortest dependency paths through a convolution neural network. We further take the relation directionality into account and propose a straightforward negative sampling strategy to improve the assignment of subjects and objects. Experimental results show that our method outperforms the state-of-theart approaches on the SemEval-2010 Task 8 dataset.

Question Answering on Freebase via Relation Extraction and Textual Evidence

Existing knowledge-based question answering systems often rely on small annotated training data. While shallow methods like relation extraction are robust to data scarcity, they are less expressive than the deep meaning representation methods like semantic parsing, thereby failing at answering questions involving multiple constraints. Here we alleviate this problem by empowering a relation extraction method with additional evidence from Wikipedia. We first present a neural network based relation extractor to retrieve the candidate answers from Freebase, and then infer over Wikipedia to validate these answers. Experiments on the WebQuestions question answering dataset show that our method achieves an F_1 of 53.3%, a substantial improvement over the state-of-the-art.

Answering Natural Language Questions via Phrasal Semantic Parsing

Understanding natural language questions and converting them into structured queries have been considered as a crucial way to help users access large scale structured knowledge bases. However, the task usually involves two main challenges: recognizing users’ query intention and mapping the involved semantic items against a given knowledge base (KB). In this paper, we propose an efficient pipeline framework to model a user’s query intention as a phrase level dependency DAG which is then instantiated regarding a specific KB to construct the final structured query. Our model benefits from the efficiency of linear structured prediction models and the separation of KB-independent and KB-related modelings. We evaluate our model on two datasets, and the experimental results showed that our method outperforms the state-of-the-art methods on the Free917 dataset, and, with limited training data from Free917, our model can smoothly adapt to new challenging dataset, WebQuestion, without extra training efforts while maintaining promising performances.

Personalized news recommendation using ontologies harvested from the web

In this paper, we concentrate on exploiting background knowledge to boost personalized news recommendation by capturing underlying semantic relatedness without expensive human involvement. We propose an Ontology Based Similarity Model (OBSM) to calculate the news-user similarity through collaboratively built ontological structures and compare our approach with other ontology-based baselines on both English and Chinese data sets. Our experimental results show that OBSM outperforms other baselines by a large margin.

S-store: An Engine for Large RDF Graph Integrating Spatial Information

The semantic web data and the SPARQL query language allow users to write precise queries. However, the lack of spatial information limits the use of the semantic web data on position-oriented query. In this paper, we introduce spatial SPARQL, a variant of SPARQL language, for querying spatial information integrated RDF data. Besides, we design a novel index SS-tree for evaluating the spatial queries. Based on the index, we propose a search algorithm. The experimental results show the effectiveness and the efficiency of our approach.

How to Make Context More Useful? An Empirical Study on Context-Aware Neural Conversational Models

Generative conversational systems are attracting increasing attention in natural language processing (NLP). Recently, researchers have noticed the importance of context information in dialog processing, and built various models to utilize context. However, there is no systematic comparison to analyze how to use context effectively. In this paper, we conduct an empirical study to compare various models and investigate the effect of context information in dialog systems. We also propose a variant that explicitly weights context vectors by context-query relevance, outperforming the other baselines.

A Convolution BiLSTM Neural Network Model for Chinese Event Extraction

Chinese event extraction is a challenging task in information extraction. Previous approaches highly depend on sophisticated feature engineering and complicated natural language processing (NLP) tools. In this paper, we first come up with the language specific issue in Chinese event extraction, and then propose a convolution bidirectional LSTM neural network that combines LSTM and CNN to capture both sentence-level and lexical information without any hand-craft features. Experiments on ACE 2005 dataset show that our approaches can achieve competitive performances in both trigger labeling and argument role labeling.

Towards Implicit Content-Introducing for Generative Short-Text Conversation Systems

The study on human-computer conversation systems is a hot research topic nowadays. One of the prevailing methods to build the system is using the generative Sequence-to-Sequence (Seq2Seq) model through neural networks. However, the standard Seq2Seq model is prone to generate trivial responses. In this paper, we aim to generate a more meaningful and informative reply when answering a given question. We propose an implicit content-introducing method which incorporates additional information into the Seq2Seq model in a flexible way. Specifically, we fuse the general decoding and the auxiliary cue word information through our proposed hierarchical gated fusion unit. Experiments on real-life data demonstrate that our model consistently outperforms a set of competitive baselines in terms of BLEU scores and human evaluation.

Encoding Relation Requirements for Relation Extraction via Joint Inference

Most existing relation extraction models make predictions for each entity pair locally and individually, while ignoring implicit global clues available in the knowledge base, sometimes leading to conflicts among local predictions from different entity pairs. In this paper, we propose a joint inference framework that utilizes these global clues to resolve disagreements among local predictions. We exploit two kinds of clues to generate constraints which can capture the implicit type and cardinality requirements of a relation. Experimental results on three datasets, in both English and Chinese, show that our framework outperforms the state-of-theart relation extraction models when such clues are applicable to the datasets. And, we find that the clues learnt automatically from existing knowledge bases perform comparably to those refined by human.

Knowledge Base Completion Using Matrix Factorization

With the development of Semantic Web, the automatic construction of large scale knowledge bases (KBs) has been receiving increasing attention in recent years. Although these KBs are very large, they are still often incomplete. Many existing approaches to KB completion focus on performing inference over a single KB and suffer from the feature sparsity problem. Moreover, traditional KB completion methods ignore complementarity which exists in various KBs implicitly. In this paper, we treat KBs completion as a large matrix completion task and integrate different KBs to infer new facts simultaneously. We present two improvements to the quality of inference over KBs. First, in order to reduce the data sparsity, we utilize the type consistency constraints between relations and entities to initialize negative data in the matrix. Secondly, we incorporate the similarity of relations between different KBs into matrix factorization model to take full advantage of the complementarity of various KBs. Experimental results show that our approach performs better than methods that consider only existing facts or only a single knowledge base, achieving significant accuracy improvements in binary relation prediction.