Commonsense knowledge is vital to many natural language processing tasks. In this paper, we present a novel open-domain conversation generation model to demonstrate how large-scale commonsense knowledge can facilitate language understanding and generation. Given a user post, the model retrieves relevant knowledge graphs from a knowledge base and then encodes the graphs with a static graph attention mechanism, which augments the semantic information of the post and thus supports better understanding of the post. Then, during word generation, the model attentively reads the retrieved knowledge graphs and the knowledge triples within each graph to facilitate better generation through a dynamic graph attention mechanism. This is the first attempt that uses large-scale commonsense knowledge in conversation generation. Furthermore, unlike existing models that use knowledge triples (entities) separately and independently, our model treats each knowledge graph as a whole, which encodes more structured, connected semantic information in the graphs. Experiments show that the proposed model can generate more appropriate and informative responses than state-of-the-art baselines.

In recent years researchers have achieved considerable success applying neural network methods to question answering (QA). These approaches have achieved state of the art results in simplified closed-domain settings 1 such as the SQuAD (Rajpurkar et al. 2016) dataset, which provides a preselected passage, from which the answer to a given question may be extracted. More recently, researchers have begun to tackle open-domain QA, in which the model is given a question and access to a large corpus (e.g., wikipedia) instead of a pre-selected passage (Chen et al. 2017a). This setting is more complex as it requires large-scale search for relevant passages by an information retrieval component, combined with a reading comprehension model that "reads" the passages to generate an answer to the question. Performance in this setting lags well behind closed-domain performance. In this paper, we present a novel open-domain QA system called Reinforced Ranker-Reader (R 3 ), based on two algorithmic innovations. First, we propose a new pipeline for open-domain QA with a Ranker component, which learns to rank retrieved passages in terms of likelihood of extracting the ground-truth answer to a given question. Second, we propose a novel method that jointly trains the Ranker along with an answer-extraction Reader model, based on reinforcement learning. We report extensive experimental results showing that our method significantly improves on the state of the art for multiple open-domain QA datasets. 2

Endowing a chatbot with personality or an identity is quite challenging but critical to deliver more realistic and natural conversations. In this paper, we address the issue of generating responses that are coherent to a pre-specified agent profile. We design a model consisting of three modules: a profile detector to decide whether a post should be responded using the profile and which key should be addressed, a bidirectional decoder to generate responses forward and backward starting from a selected profile value, and a position detector that predicts a word position from which decoding should start given a selected profile value. We show that general conversation data from social media can be used to generate profile-coherent responses. Manual and automatic evaluation shows that our model can deliver more coherent, natural, and diversified responses.

Although the Transformer translation model (Vaswani et al., 2017) has achieved state-ofthe-art performance in a variety of translation tasks, how to use document-level context to deal with discourse phenomena problematic for Transformer still remains a challenge. In this work, we extend the Transformer model with a new context encoder to represent document-level context, which is then incorporated into the original encoder and decoder. As large-scale document-level parallel corpora are usually not available, we introduce a two-step training method to take full advantage of abundant sentence-level parallel corpora and limited document-level parallel corpora. Experiments on the NIST Chinese-English datasets and the IWSLT French-English datasets show that our approach improves over Transformer significantly. 1

Chlorophyll content is one of the most important physiological traits as it is closely related to leaf photosynthesis and crop yield potential. So far, few genes have been reported to be involved in natural variation of chlorophyll content in rice (Oryza sativa) and the extent of variations explored is very limited. We conducted a genome-wide association study (GWAS) using a diverse worldwide collection of 529 O. sativa accessions. A total of 46 significant association loci were identified. Three F2 mapping populations with parents selected from the association panel were tested for validation of GWAS signals. We clearly demonstrated that Grain number, plant height, and heading date7 (Ghd7) was a major locus for natural variation of chlorophyll content at the heading stage by combining evidence from near-isogenic lines and transgenic plants. The enhanced expression of Ghd7 decreased the chlorophyll content, mainly through down-regulating the expression of genes involved in the biosynthesis of chlorophyll and chloroplast. In addition, Narrow leaf1 (NAL1) corresponded to one significant association region repeatedly detected over two years. We revealed a high degree of polymorphism in the 5' UTR and four non-synonymous SNPs in the coding region of NAL1, and observed diverse effects of the major haplotypes. The loci or candidate genes identified would help to fine-tune and optimize the antenna size of canopies in rice breeding.