Chinese Word Segmentation Based on Deep Learning

Wang, Mengge; Li, Xiaoge; Wei, Zheng; Zhi, Shuting; Wang, Haoyue

doi:10.1145/3195106.3195135

Cited by 12 publications

(7 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among patients with grade 3, the response rate was found to be 66.7%, with a complete response rate of only 16.7%. Furthermore, relevant guidelines advise against the use of formaldehyde therapy in patients with radiation injury of grade 3 or higher (7). Our results suggest that formalin therapy may be more likely to achieve satisfactory therapeutic effects in patients with grade 1-2 radiation injuries.…”

Section: Discussionmentioning

confidence: 70%

“…The treatment options commonly used for radiation proctitis encompass a range of therapeutic methods, such as topical corticosteroids, 5-aminosalicylic acid, pentoxifylline or sucralfate enemas, hyperbaric oxygen treatment, and endoscopic therapy involving argon laser or heater probes (among others). Surgery is considered a last resort and is only performed in lifethreatening rectal hemorrhage situations (6)(7)(8). Furthermore, technological advances, which concern both the use of highly conformal image-guided radiotherapy techniques and the personalization of target delineation to minimize unnecessary radiation delivery to the rectum, together with the early application of some topical drugs, could be helpful for preventing the onset of proctitis (9,10).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Transcolonoscopic spraying formalin solution for hemorrhagic radiation proctitis: a retrospective analysis

Huang,

Zhao,

et al. 2024

Front. Med.

View full text Add to dashboard Cite

BackgroundRadiation proctitis is a common complication that occurs as a result of radiation therapy used to treat pelvic malignancies. The most common and bothersome symptom resulting from radiation proctitis is rectal bleeding, which can be persistent or recurrent. This study aimed to review our experience and evaluate the efficacy and safety of transcolonoscopic spraying of formalin solution in patients with hemorrhagic radiation proctitis.MethodsA total of 37 patients with hemorrhagic radiation proctitis, aged between 48 and 79 years (mean age 62.56 ± 8.48 years), were divided into three cohorts based on the severity of radiation injury. Under direct endoscopic vision, a 4% formalin solution was applied directly to the rectal hemorrhagic mucosa. The patients were followed for a period of over 6 months after receiving treatment, during which the therapeutic effectiveness and occurrence of complications were observed.ResultsThe study resulted in an overall response rate of 89.2% among all patients. The response rates for patients with grades 1–3 were 100, 100, and 66.7%, respectively. Notably, the rate of response among patients with grade 3 radiation injury was significantly lower compared to those with grades 1–2 (p = 0.009). Mild adverse reactions, such as anal pain and tenesmus, were reported in a small number of patients but could be alleviated without any intervention.ConclusionThe endoscopic application of formalin solution for the treatment of hemorrhagic radiation proctitis has shown a significant effect, particularly in patients with grades 1–2 radiation injury. The observed effect is superior to that observed in patients with grade 3 radiation injury.

show abstract

Section: Discussionmentioning

confidence: 70%

Section: Introductionmentioning

confidence: 99%

Transcolonoscopic spraying formalin solution for hemorrhagic radiation proctitis: a retrospective analysis

Huang,

Zhao,

et al. 2024

Front. Med.

View full text Add to dashboard Cite

show abstract

“…Wang et al [21] introduced spatiotemporal memory units (M) into ConvLSTM and connected them through a zigzag structure, proposing the PredRNN model, which demonstrates outstanding performance in precipitation forecasting tasks. In 2018, Wang et al extended PredRNN to PredRNN++ [22], which uses gradient highways (GHU) to alleviate the vanishing gradient problem. Subsequently, they further improved unit structures and the overall framework, introducing models such as MIM [23], E3D-LSTM [24], and PredRNN-V2 [25], achieving significant success in precipitation forecasting and other spatiotemporal prediction problems.…”

Section: Spatiotemporal Prediction Modelmentioning

confidence: 99%

Improving Precipitation Forecasting through Early Fusion and Spatiotemporal Prediction: A Case Study Using the MultiPred Model

Wang,

Tian,

Fang

et al. 2024

Atmosphere

View full text Add to dashboard Cite

Due to the complexity and uncertainty of meteorological systems, traditional precipitation forecasting methods have certain limitations. Therefore, based on the common characteristics of meteorological data, a precipitation forecasting model named MultiPred is proposed, with the goal of continuously predicting precipitation for 4 h in a specific region. This model combines the multimodal fusion method with recursive spatiotemporal prediction models. The training and testing process of the model roughly involves using spatial feature extraction networks and temporal feature extraction networks to generate preliminary predictions for multimodal data. Subsequently, a modal fusion layer is employed to further extract and fuse the spatial features of the preliminary predictions from the previous step, outputting the predicted precipitation values for the target area. Experimental tests and training were conducted using ERA5 multi-meteorological modal data and GPM satellite precipitation data from 2017 to 2020, covering longitudes from 110° to 122° and latitudes from 20° to 32°. The training set used data from the first three years, while the validation set and test set each comprised 50% of the data from the fourth year. The initial learning rate for the experiment was set to 1 × 10−4, and training was performed for 1000 epochs. Additionally, the training process utilized a loss function composed of Mean Absolute Error (MAE), Mean Squared Error (MSE), and Structural Similarity Index (SSIM). The model was evaluated using the Critical Success Index (CSI), Probability of Detection (POD), and the Heidke Skill Score (HSS). Experimental results demonstrate that MultiPred excels in precipitation forecasting, particularly for light precipitation events with amounts greater than or equal to 0.1 mm and less than 2 mm. It achieves optimal performance in both light and heavy precipitation forecasting tasks.

show abstract

“…While in optimization problems local solutions often produce optimal results, structured prediction represents a valid alternative to solve NLP tasks requiring complex output, such as syntactic parsing (Roth and Yih, 2004), co-reference resolution (Yu and Joachims, 2009;Fernan-des et al, 2014), and clustering (Finley and Joachims, 2005;Haponchyk et al, 2018). Nonetheless, relatively few works extend structured prediction theory to deep learning Durrett and Klein, 2015;Weiss et al, 2015;Kiperwasser and Goldberg, 2016;Peng et al, 2018;Milidiú and Rocha, 2018;Wang et al, 2019). In particular, when it comes to clustering, designing a differentiable loss function that captures the global characteristics of good clustering is particularly hard; for this reason, when dealing with coreference resolution -a closely related task - Lee et al (2017) use simple losses, which already perform well but do not strictly take into account the cluster structure.…”

Section: Structured Predictionmentioning

confidence: 99%

Supervised Clustering Loss for Clustering-Friendly Sentence Embeddings: an Application to Intent Clustering

Barnabò,

Uva,

Pollastrini

et al. 2023

Findings of the Association for Computational Linguistics: IJCNLP-AACL 2023 (Findings)

View full text Add to dashboard Cite

Modern virtual assistants are trained to classify customer requests into a taxonomy of predesigned intents. Requests that fall outside of this taxonomy, however, are often unhandled and need to be clustered to define new experiences. Recently, state-of-the-art results in intent clustering were achieved by training a neural network with a latent structured prediction loss. Unfortunately, though, this new approach suffers from a quadratic bottleneck as it requires to compute a joint embedding representation for all pairs of utterances to cluster. To overcome this limitation, we instead cast the problem into a representation learning task, and we adapt the latent structured prediction loss to fine-tune sentence encoders, thus making it possible to obtain clustering-friendly single-sentence embeddings. Our experiments show that the supervised clustering loss returns state-of-the-art results in terms of clustering accuracy and adjusted mutual information.

show abstract

Chinese Word Segmentation Based on Deep Learning

Cited by 12 publications

References 4 publications

Transcolonoscopic spraying formalin solution for hemorrhagic radiation proctitis: a retrospective analysis

Transcolonoscopic spraying formalin solution for hemorrhagic radiation proctitis: a retrospective analysis

Improving Precipitation Forecasting through Early Fusion and Spatiotemporal Prediction: A Case Study Using the MultiPred Model

Supervised Clustering Loss for Clustering-Friendly Sentence Embeddings: an Application to Intent Clustering

Contact Info

Product

Resources

About