Recently, knowledge graphs (KGs) have won noteworthy success in commonsense question answering. Existing methods retrieve relevant subgraphs in the KGs through key entities and reason about the answer with language models (LMs) and graph neural networks. However, they ignore (i) optimizing the knowledge representation and structure of subgraphs and (ii) deeply fusing heterogeneous QA context with subgraphs. In this paper, we propose a dynamic heterogeneous-graph reasoning method with LMs and knowledge representation learning (DHLK), which constructs a heterogeneous knowledge graph (HKG) based on multiple knowledge sources and optimizes the structure and knowledge representation of the HKG using a two-stage pruning strategy and knowledge representation learning (KRL). It then performs joint reasoning by LMs and Relation Mask Self-Attention (RMSA). Specifically, DHLK filters key entities based on the dictionary vocabulary to achieve the first-stage pruning while incorporating the paraphrases in the dictionary into the subgraph to construct the HKG. Then, DHLK encodes and fuses the QA context and HKG using LM, and dynamically removes irrelevant KG entities based on the attention weights of LM for the second-stage pruning. Finally, DHLK introduces KRL to optimize the knowledge representation and perform answer reasoning on the HKG by RMSA.We evaluate DHLK at CommonsenseQA and OpenBookQA, and show its improvement on existing LM and LM+KG methods.

Existing model pretraining methods only consider local information. For example, in the popular token masking strategy, the words closer to the masked token are more important for prediction than words far away. This results in pretrained models that generate high-quality sentence embeddings, but low-quality embeddings for large documents. We propose a new pretraining method called DocSplit which forces models to consider the entire global context of a large document. Our method uses a contrastive loss where the positive examples are randomly sampled sections of the input document, and negative examples are randomly sampled sections of unrelated documents. Like previous pretraining methods, DocSplit is fully unsupervised, easy to implement, and can be used to pretrain any model architecture. Our experiments show that DocSplit outperforms other pretraining methods for document classification, few shot learning, and information retrieval tasks.

This paper describes the BLCU-ICALL system used in the SemEval-2022 Task 1 Comparing Dictionaries and Word Embeddings, the Definition Modeling subtrack, achieving 1st on Italian, 2nd on Spanish and Russian, and 3rd on English and French. We propose a transformer-based multitasking framework to explore the task. The framework integrates multiple embedding architectures through the cross-attention mechanism, and captures the structure of glosses through a masking language model objective. Additionally, we also investigate a simple but effective model ensembling strategy to further improve the robustness. The evaluation results show the effectiveness of our solution. We release our code at: https://github.com/blcuicall/SemEval2022-Task1-DM.

The construct of linguistic complexity has been widely used in language learning research. Several text analysis tools have been created to automatically analyze linguistic complexity. However, the indexes supported by several existing Chinese text analysis tools are limited and different because of different research purposes. CTAP is an open-source linguistic complexity measurement extraction tool, which prompts any research purposes. Although it was originally developed for English, the Unstructured Information Management (UIMA) framework it used allows the integration of other languages. In this study, we integrated the Chinese component into CTAP, describing the index sets it incorporated and comparing it with three linguistic complexity tools for Chinese. The index set includes four levels of 196 linguistic complexity indexes: character level, word level, sentence level, and discourse level. So far, CTAP has implemented automatic calculation of complexity characteristics for four languages, aiming to help linguists without NLP background study language complexity.