We argue that semantic meanings of a sentence or clause can not be interpreted independently from the rest of a paragraph, or independently from all discourse relations and the overall paragraph-level discourse structure. With the goal of improving implicit discourse relation classification, we introduce a paragraph-level neural networks that model inter-dependencies between discourse units as well as discourse relation continuity and patterns, and predict a sequence of discourse relations in a paragraph. Experimental results show that our model outperforms the previous state-of-the-art systems on the benchmark corpus of PDTB.

We argue that external commonsense knowledge and linguistic constraints need to be incorporated into neural network models for mitigating data sparsity issues and further improving the performance of discourse parsing. Realizing that external knowledge and linguistic constraints may not always apply in understanding a particular context, we propose a regularization approach that tightly integrates these constraints with contexts for deriving word representations. Meanwhile, it balances attentions over contexts and constraints through adding a regularization term into the objective function. Experiments show that our knowledge regularization approach outperforms all previous systems on the benchmark dataset PDTB for discourse parsing.

Recent neural network models have achieved state-of-the-art performance on the task of named entity recognition (NER). However, previous neural network models typically treat the input sentences as a linear sequence of words but ignore rich structural information, such as the coreference relations among non-adjacent words, phrases or entities. In this paper, we propose a novel approach to learn coreference-aware word representations for the NER task at the document level. In particular, we enrich the well-known neural architecture ``CNN-BiLSTM-CRF'' with a coreference layer on top of the BiLSTM layer to incorporate coreferential relations. Furthermore, we introduce the coreference regularization to ensure the coreferential entities to share similar representations and consistent predictions within the same coreference cluster. Our proposed model achieves new state-of-the-art performance on two NER benchmarks: CoNLL-2003 and OntoNotes v5.0. More importantly, we demonstrate that our framework does not rely on gold coreference knowledge, and can still work well even when the coreferential relations are generated by a third-party toolkit.

Subevents elaborate an event and widely exist in event descriptions. Subevent knowledge is useful for discourse analysis and event-centric applications. Acknowledging the scarcity of subevent knowledge, we propose a weakly supervised approach to extract subevent relation tuples from text and build the first large scale subevent knowledge base. We first obtain the initial set of event pairs that are likely to have the subevent relation, by exploiting two observations that 1) subevents are temporally contained by the parent event, and 2) the definitions of the parent event can be used to further guide the identification of subevents. Then, we collect rich weak supervision using the initial seed subevent pairs to train a contextual classifier using BERT and apply the classifier to identify new subevent pairs. The evaluation showed that the acquired subevent tuples (239K) are of high quality (90.1% accuracy) and cover a wide range of event types. The acquired subevent knowledge has been shown useful for discourse analysis and identifying a range of event-event relations 1 .

Pyrimidine ribonucleotide de novo biosynthesis pathway (PRdnBP) is an important pathway to produce pyrimidine nucleosides. We attempted to systematically investigate PRdnBP in Escherichia coli with genome-scale metabolic models and utilized the models to guide strain design. The balance of central carbon metabolism and PRdnBP affected the production of cytidine from glucose. Using Bayesian metabolic flux analysis, the effect of modified PRdnBP on the metabolic network was analyzed. The acetate overflow became coupled with PRdnBP flux, while they were originally independent under oxygen-sufficient conditions. The coupling between cytidine production and acetate secretion in the modified strain was weakened by arcA deletion, which resulted in further improving the efficient accumulation of cytidine. In total, 1.28 g/L of cytidine with a yield of 0.26 g/g glucose was produced. The yield of cytidine produced by E. coli is higher than previous reports. Our strategy provides an effective attempt to find metabolic bottlenecks in genetically engineered bacteria by using flux coupling analysis.