Interpersonal language style shifting in dialogues is an interesting and almost instinctive ability of human. Understanding interpersonal relationship from language content is also a crucial step toward further understanding dialogues. Previous work mainly focuses on relation extraction between named entities in texts. In this paper, we propose the task of relation classification of interlocutors based on their dialogues. We crawled movie scripts from IMSDb, and annotated the relation labels for each session according to 13 pre-defined relationships. The annotated dataset DDRel consists of 6300 dyadic dialogue sessions between 694 pair of speakers with 53,126 utterances in total. We also construct session-level and pair-level relation classification tasks with widely-accepted baselines. The experimental results show that this task is challenging for existing models and the dataset will be useful for future research.

The training phases of Deep neural network (DNN) consumes enormous processing time and energy. Compression techniques utilizing the sparsity of DNNs can effectively accelerate the inference phase of DNNs. However, it can be hardly used in the training phase because the training phase involves dense matrix-multiplication using General Purpose Computation on Graphics Processors (GPGPU), which endorse regular and structural data layout. In this paper, we propose the Approximate Random Dropout that replaces the conventional random dropout of neurons and synapses with a regular and predefined patterns to eliminate the unnecessary computation and data access. To compensate the potential performance loss we develop a SGDbased Search Algorithm to produce the distribution of dropout patterns. We prove our approach is statistically equivalent to the previous dropout method. Experiments results on MLP and LSTM using well-known benchmarks show that the proposed Approximate Random Dropout can reduce the training time by 20%-77% (19%-60%) when dropout rate is 0.3-0.7 on MLP (LSTM) with marginal accuracy drop.

Chlorophyll molecules are non-covalently associated with chlorophyll-binding proteins to harvest light and perform charge separation vital for energy conservation during photosynthetic electron transfer in photosynthesis for photosynthetic organisms. The present study characterized a pale-green leaf (pgl) maize mutant controlled by a single recessive gene causing chlorophyll reduction throughout the whole life cycle. Through positional mapping and complementation allelic test, Zm00001d008230 (ZmCRD1) with two missense mutations (p.A44T and p.T326M) was identified as the causal gene encoding magnesium-protoporphyrin IX monomethyl ester cyclase (MgPEC). Phylogenetic analysis of ZmCRD1 within and among species revealed that the p.T326M mutation was more likely to be causal. Subcellular localization showed that ZmCRD1 was targeted to chloroplasts. The pgl mutant showed a malformed chloroplast morphology and reduced number of starch grains in bundle sheath cells. The ZmCRD1 gene was mainly expressed in WT and mutant leaves, but the expression was reduced in the mutant. Most of the genes involved in chlorophyll biosynthesis, chlorophyll degradation, chloroplast development and photosynthesis were down-regulated in pgl. The photosynthetic capacity was limited along with developmental retardation and production reduction in pgl. These results confirmed the crucial role of ZmCRD1 in chlorophyll biosynthesis, chloroplast development and photosynthesis in maize.

Interpersonal language style shifting in dialogues is an interesting and almost instinctive ability of human. Understanding interpersonal relationship from language content is also a crucial step toward further understanding dialogues. Previous work mainly focuses on relation extraction between named entities in texts or within a single dialogue session. In this paper, we propose the task of relation classification of interlocutors based on their dialogues. We crawled movie scripts from IMSDb, and annotated the relation label for each session according to 13 pre-defined relationships. The annotated dataset DDRel consists of 6,300 dyadic dialogue sessions between 694 pairs of speakers with 53,126 utterances in total. We also construct session-level and pair-level relation classification tasks with widely-accepted baselines. The experimental results show that both tasks are challenging for existing models and the dataset will be useful for future research.

No abstract