arXiv subjects

Rui Yan

Publications and source records attributed to Rui Yan.

311 records · Page 18Linked to original sources

arXiv2016

Natural Language Inference by Tree-Based Convolution and Heuristic Matching

In this paper, we propose the TBCNN-pair model to recognize entailment and contradiction between two sentences. In our model, a tree-based convolutional neural network (TBCNN) captures sentence-level semantics; then heuristic matching layers like concatenation, element-wise product/difference combine the information in individual sentences. Experimental results show that our model outperforms existing sentence encoding-based approaches by a large margin.

cs.CL↗

arXiv2016

StalemateBreaker: A Proactive Content-Introducing Approach to Automatic Human-Computer Conversation

Existing open-domain human-computer conversation systems are typically passive: they either synthesize or retrieve a reply provided a human-issued utterance. It is generally presumed that humans should take the role to lead the conversation and introduce new content when a stalemate occurs, and that the computer only needs to "respond." In this paper, we propose StalemateBreaker, a conversation system that can proactively introduce new content when appropriate. We design a pipeline to determine when, what, and how to introduce new content during human-computer conversation. We further propose a novel reranking algorithm Bi-PageRank-HITS to enable rich interaction between conversation context and candidate replies. Experiments show that both the content-introducing approach and the reranking algorithm are effective. Our full StalemateBreaker model outperforms a state-of-the-practice conversation system by +14.4% p@1 when a stalemate occurs.

cs.CL↗

arXiv2016

Backward and Forward Language Modeling for Constrained Sentence Generation

Recent language models, especially those based on recurrent neural networks (RNNs), make it possible to generate natural language from a learned probability. Language generation has wide applications including machine translation, summarization, question answering, conversation systems, etc. Existing methods typically learn a joint probability of words conditioned on additional information, which is (either statically or dynamically) fed to RNN's hidden layer. In many applications, we are likely to impose hard constraints on the generated texts, i.e., a particular word must appear in the sentence. Unfortunately, existing approaches could not solve this problem. In this paper, we propose a novel backward and forward language model. Provided a specific word, we use RNNs to generate previous words and future words, either simultaneously or asynchronously, resulting in two model variants. In this way, the given word could appear at any position in the sentence. Experimental results show that the generated texts are comparable to sequential LMs in quality.

cs.CL↗

arXiv2015

Fast Low-rank Representation based Spatial Pyramid Matching for Image Classification

Spatial Pyramid Matching (SPM) and its variants have achieved a lot of success in image classification. The main difference among them is their encoding schemes. For example, ScSPM incorporates Sparse Code (SC) instead of Vector Quantization (VQ) into the framework of SPM. Although the methods achieve a higher recognition rate than the traditional SPM, they consume more time to encode the local descriptors extracted from the image. In this paper, we propose using Low Rank Representation (LRR) to encode the descriptors under the framework of SPM. Different from SC, LRR considers the group effect among data points instead of sparsity. Benefiting from this property, the proposed method (i.e., LrrSPM) can offer a better performance. To further improve the generalizability and robustness, we reformulate the rank-minimization problem as a truncated projection problem. Extensive experimental studies show that LrrSPM is more efficient than its counterparts (e.g., ScSPM) while achieving competitive recognition rates on nine image data sets.

cs.CV↗

arXiv2007

Particle-in-cell simulations of fast collisionless reconnection in gamma-ray burst outflows

We present preliminary results of particle-in-cell simulations of collisionless magnetic reconnection for conditions that apply to magnetically dominated pair plasma jets such as those in gamma-ray bursts. We find similar behaviour to previous authors but with reduced reconnection efficiency. This results because we include the full electromagnetic field dynamically and allow electric field fluctuations to grow. Although weak, these fluctuations impede early x-point formation by periodically decelerating and even reversing the inflow.

astro-ph↗