Implicit Discourse Relation Recognition (IDRR), which infers discourse relations without the help of explicit connectives, is still a crucial and challenging task for discourse parsing. Recent works tend to exploit the hierarchical structure information from the annotated senses, which demonstrate enhanced discourse relation representations can be obtained by integrating sense hierarchy. Nevertheless, the performance and robustness for IDRR are significantly constrained by the availability of annotated data. Fortunately, there is a wealth of unannotated utterances with explicit connectives, that can be utilized to acquire enriched discourse relation features. In light of such motivation, we propose a Promptbased Logical Semantics Enhancement (PLSE) method for IDRR. Essentially, our method seamlessly injects knowledge relevant to discourse relation into pre-trained language models through prompt-based connective prediction. Furthermore, considering the prompt-based connective prediction exhibits local dependencies due to the deficiency of masked language model (MLM) in capturing global semantics, we design a novel self-supervised learning objective based on mutual information maximization to derive enhanced representations of logical semantics for IDRR. Experimental results on PDTB 2.0 and CoNLL16 datasets demonstrate that our method achieves outstanding and consistent performance against the current state-of-the-art models. 1
This paper describes major challenges to seismic acquisition in China's Tarim Basin (Figure 1) and how high-resolution 3D seismic surveys can improve reservoir imaging in this area.
U.S.A., Ordovician carbonate reservoirs are the very important yet difficult targets in the oil and gas exploration and development of Tarim basin, western China. The main task (also main challenge) of seismic is to image and predict the storage spaces of carbonate reservoirs-the secondary dissolved caves, holes and fractures, which are buried in more than 6500m deep. The target formations are usually in very low signal-to-noise ratio due to the seismic attenuation and the caves and fractures are small and aligned in random directions. Narrow azimuth and conventional wide azimuth seismic fail to image and identify the fracturedcavernous reservoirs accurately, leading to many drilling failures. Here, the effects of some key acquisition parameters such as bin size, fold and aspect ratio on carbonate reservoirs imaging accuracy are carefully examined using seismic forward modeling and new analysis methods. A high-density full-azimuth seismic acquisition was carried out based on the above analysis and the results show that small bin size has the advantage to imaging the ultra-deep carbonate reservoirs and the fracture prediction results from full azimuth data well agree with that from imaging well logging data. A set of well drillings based on the full azimuth data have been proved to be successful.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.