Recent progress regarding the use of language models (LMs) as knowledge bases (KBs) has shown that language models can act as structured knowledge bases for storing relational facts. However, most existing works only considered the LM-as-KB paradigm in a static setting, which ignores the analysis of temporal dynamics of world knowledge. Furthermore, a basic function of KBs, i.e., the ability to store conflicting information (i.e., 1-N, N-1, and N-M relations), is underexplored. In this paper, we formulate two practical requirements for treating LMs as temporal KBs: (i) The capacity to store temporally-scoped knowledge that contains conflicting information and (ii) the ability to use stored knowledge for temporally-scoped knowledge queries. We introduce a new dataset called LAMA-TK which is aimed at probing temporally-scoped knowledge, and investigate the two above requirements to explore the LM-as-KB paradigm in the temporal domain. On the one hand, experiments show that LMs can memorize millions of temporally-scoped facts with relatively high accuracy and transfer stored knowledge to temporal knowledge queries, thereby expanding the LM-as-KB paradigm to the temporal domain. On the other hand, we show that memorizing conflicting information, which has been neglected by previous works, is still challenging for LMs and hinders the memorization of other unrelated one-to-one relationships.

Medication recommendation is a crucial task for intelligent healthcare systems. Previous studies mainly recommend medications with electronic health records (EHRs). However, some details of interactions between doctors and patients may be ignored or omitted in EHRs, which are essential for automatic medication recommendation. Therefore, we make the first attempt to recommend medications with the conversations between doctors and patients. In this work, we construct DIALMED, the first high-quality dataset for medical dialogue-based medication recommendation task. It contains 11, 996 medical dialogues related to 16 common diseases from 3 departments and 70 corresponding common medications. Furthermore, we propose a Dialogue structure and Disease knowledge aware Network (DDN), where a QA Dialogue Graph mechanism is designed to model the dialogue structure and the knowledge graph is used to introduce external disease knowledge. The extensive experimental results demonstrate that the proposed method is a promising solution to recommend medications with medical dialogues. The dataset and code are available at https://github.com/f-window/DialMed.

The detection of hyperbole is an important stepping stone to understanding the intentions of a hyperbolic utterance. We propose a model that combines pre-trained language models with privileged information for the task of hyperbole detection. We also introduce a suite of behavioural tests to probe the capabilities of hyperbole detection models across a range of hyperbole types. Our experiments show that our model improves upon baseline models on an existing hyperbole detection dataset. Probing experiments combined with analysis using local linear approximations (LIME) show that our model excels at detecting one particular type of hyperbole. Further, we discover that our experiments highlight annotation artifacts introduced through the process of literal paraphrasing of hyperbole. These annotation artifacts are likely to be a roadblock to further improvements in hyperbole detection.

In natural language processing, it is common that many entities contain other entities inside them. Most existing works on named entity recognition (NER) only deal with flat entities but ignore nested ones. We propose a boundary-aware neural model for nested NER which leverages entity boundaries to predict entity categorical labels. Our model can locate entities precisely by detecting boundaries using sequence labeling models. Based on the detected boundaries, our model utilizes the boundary-relevant regions to predict entity categorical labels, which can decrease computation cost and relieve error propagation problem in layered sequence labeling model. We introduce multitask learning to capture the dependencies of entity boundaries and their categorical labels, which helps to improve the performance of identifying entities. We conduct our experiments on GENIA dataset and the experimental results demonstrate that our model outperforms other state-of-the-art methods.