“The purpose of the CAMR task is to convert natural language into a formalized semantic representation in the form of a graph structure. Due to the complexity of the AMR graph structure, traditional AMR automatic parsing methods often require the design of complex models and strategies. Thanks to the powerful generative capabilities of LLMs, adopting an autore-gressive generative approach for AMR parsing has many advantages such as simple modeling and strong extensibility. To further explore the generative AMR automatic parsing technology based on LLMs, we design a two-stage AMR automatic parsing method based on LLMs in this CAMR evaluation. Specifically, we design two pipeline subtasks of alignment-aware node generation and relationship-aware node generation to reduce the difficulty of LLM understanding and generation. Additionally, to boost the system’s transferability, we incorporate a retrieval-augmented strategy during both training and inference phases. The experimental results show that the method we proposed has achieved promising results in this evaluation.”

Due to the high complexity of Discourse Dependency Parsing (DDP) tasks, their existing annotation resources are relatively scarce compared to other NLP tasks, and different DDP tasks also have significant differences in annotation schema. These issues have led to the dilemma of low resources for DDP tasks. Thanks to the powerful capabilities of Large Language Models (LLMs) in cross-task learning, we can use LLMs to model dependency parsing under different annotation schema in an unified manner, in order to alleviate the dilemma of low resources for DDP tasks. However, enabling LLMs to deeply comprehend dependency parsing tasks is a challenge that remains underexplored. Inspired by the application of code-based methods in complex tasks, we propose a code-based unified dependency parsing method. We treat the process of dependency parsing as a search process of dependency paths and use code to represent this search process. Furthermore, we use a curriculum-learning based instruction tuning strategy for joint training of multiple dependency parsing tasks. The experimental results show that our proposed code-based DDP system has achieved good performance on two Chinese DDP tasks (especially significant improvement on the DDP task with relatively less training data).

Deep learning-based Chinese zero pronoun resolution model has achieved better performance than traditional machine learning-based model. However, the existing work related to Chinese zero pronoun resolution has not yet well integrated linguistic information into the deep learningbased Chinese zero pronoun resolution model. This paper adopts the idea based on the pre-trained model, and integrates the semantic representations in the pre-trained Chinese semantic dependency graph parser into the Chinese zero pronoun resolution model. The experimental results on OntoNotes-5.0 dataset show that our proposed Chinese zero pronoun resolution model with pretrained Chinese semantic dependency parser improves the F-score by 0.4% compared with our baseline model, and obtains better results than other deep learning-based Chinese zero pronoun resolution models. In addition, we integrate the BERT representations into our model so that the performance of our model was improved by 0.7% compared with our baseline model.

Grammatical error diagnosis is an important task in natural language processing. This paper introduces our system at NLPTEA-2020 Task: Chinese Grammatical Error Diagnosis (CGED). CGED aims to diagnose four types of grammatical errors which are missing words (M), redundant words (R), bad word selection (S) and disordered words (W). Our system is built on the model of multi-layer bidirectional transformer encoder and ResNet is integrated into the encoder to improve the performance. We also explore two ensemble strategies including weighted averaging and stepwise ensemble selection from libraries of models to improve the performance of single model. In official evaluation, our system obtains the highest F1 scores at identification level and position level. We also recommend error corrections for specific error types and achieve the second highest F1 score at correction level.