Artificial Intelligence (AI), along with the recent progress in biomedical language understanding, is gradually changing medical practice. With the development of biomedical language understanding benchmarks, AI applications are widely used in the medical field. However, most benchmarks are limited to English, which makes it challenging to replicate many of the successes in English for other languages. To facilitate research in this direction, we collect real-world biomedical data and present the first Chinese Biomedical Language Understanding Evaluation (CBLUE) benchmark: a collection of natural language understanding tasks including named entity recognition, information extraction, clinical diagnosis normalization, single-sentence/sentence-pair classification, and an associated online platform for model evaluation, comparison, and analysis. To establish evaluation on these tasks, we report empirical results with the current 11 pre-trained Chinese models, and experimental results show that state-of-the-art neural models perform by far worse than the human ceiling. Our benchmark is released at \url{https://tianchi.aliyun.com/dataset/dataDetail?dataId=95414&lang=en-us}.
Aspect Sentiment Triplet Extraction (ASTE) aims to recognize targets, their sentiment polarities and opinions explaining the sentiment from a sentence. ASTE could be naturally divided into 3 atom subtasks, namely target detection, opinion detection and sentiment classification. We argue that the proper subtask combination, compositional feature extraction for target-opinion pairs, and interaction between subtasks would be the key to success. Prior work, however, may fail on `one-to-many' or `many-to-one' situations, or derive non-existent sentiment triplets due to defective subtask formulation, sub-optimal feature representation or the lack of subtask interaction. In this paper, we divide ASTE into target-opinion joint detection and sentiment classification subtasks, which is in line with human cognition, and correspondingly propose sequence encoder and table encoder. Table encoder extracts sentiment at token-pair level, so that the compositional feature between targets and opinions can be easily captured. To establish explicit interaction between subtasks, we utilize the table representation to guide the sequence encoding, and inject the sequence features back into the table encoder. Experiments show that our model outperforms state-of-the-art methods on six popular ASTE datasets.
Document-level relation extraction has attracted much attention in recent years. It is usually formulated as a classification problem that predicts relations for all entity pairs in the document. However, previous works indiscriminately represent intra- and inter-sentential relations in the same way, confounding the different patterns for predicting them. Besides, they create a document graph and use paths between entities on the graph as clues for logical reasoning. However, not all entity pairs can be connected with a path and have the correct logical reasoning paths in their graph. Thus many cases of logical reasoning cannot be covered. This paper proposes an effective architecture, SIRE, to represent intra- and inter-sentential relations in different ways. We design a new and straightforward form of logical reasoning module that can cover more logical reasoning chains. Experiments on the public datasets show SIRE outperforms the previous state-of-the-art methods. Further analysis shows that our predictions are reliable and explainable. Our code is available at https://github.com/DreamInvoker/SIRE.
Document-level event extraction aims to recognize event information from a whole piece of article. Existing methods are not effective due to two challenges of this task: a) the target event arguments are scattered across sentences; b) the correlation among events in a document is non-trivial to model. In this paper, we propose Heterogeneous Graph-based Interaction Model with a Tracker (GIT) to solve the aforementioned two challenges. For the first challenge, GIT constructs a heterogeneous graph interaction network to capture global interactions among different sentences and entity mentions. For the second, GIT introduces a Tracker module to track the extracted events and hence capture the interdependency among the events. Experiments on a large-scale dataset (Zheng et al., 2019) show GIT outperforms the previous methods by 2.8 F1. Further analysis reveals GIT is effective in extracting multiple correlated events and event arguments that scatter across the document. Our code is available at https://github.com/RunxinXu/GIT.
Evaluation in natural language processing guides and promotes research on models and methods. In recent years, new evalua-tion data sets and evaluation tasks have been continuously proposed. At the same time, a series of problems exposed by ex-isting evaluation have also restricted the progress of natural language processing technology. Starting from the concept, com-position, development and meaning of natural language evaluation, this article classifies and summarizes the tasks and char-acteristics of mainstream natural language evaluation, and then summarizes the problems and causes of natural language pro-cessing evaluation. Finally, this article refers to the human language ability evaluation standard, puts forward the concept of human-like machine language ability evaluation, and proposes a series of basic principles and implementation ideas for hu-man-like machine language ability evaluation from the three aspects of reliability, difficulty and validity.
Conventional Machine Reading Comprehension (MRC) has been well-addressed by pattern matching, but the ability of commonsense reasoning remains a gap between humans and machines. Previous methods tackle this problem by enriching word representations via pre-trained Knowledge Graph Embeddings (KGE). However, they make limited use of a large number of connections between nodes in Knowledge Graphs (KG), which could be pivotal cues to build the commonsense reasoning chains. In this paper, we propose a Plug-and-play module to IncorporatE Connection information for commonsEnse Reasoning (PIECER). Beyond enriching word representations with knowledge embeddings, PIECER constructs a joint query-passage graph to explicitly guide commonsense reasoning by the knowledge-oriented connections between words. Further, PIECER has high generalizability since it can be plugged into suitable positions in any MRC model. Experimental results on ReCoRD, a large-scale public MRC dataset requiring commonsense reasoning, show that PIECER introduces stable performance improvements for four representative base MRC models, especially in low-resource settings.
In open domain table-to-text generation, we notice that the unfaithful generation usually contains hallucinated content which can not be aligned to any input table record. We thus try to evaluate the generation faithfulness with two entity-centric metrics: table record coverage and the ratio of hallucinated entities in text, both of which are shown to have strong agreement with human judgements. Then based on these metrics, we quantitatively analyze the correlation between training data quality and generation fidelity which indicates the potential usage of entity information in faithful generation. Motivated by these findings, we propose two methods for faithful generation: 1) augmented training by incorporating the auxiliary entity information, including both an augmented plan-based model and an unsupervised model and 2) training instance selection based on faithfulness ranking. We show these approaches improve generation fidelity in both full dataset setting and few shot learning settings by both automatic and human evaluations.
Recent years have seen significant advancement in text generation tasks with the help of neural language models. However, there exists a challenging task: generating math problem text based on mathematical equations, which has made little progress so far. In this paper, we present a novel equation-to-problem text generation model. In our model, 1) we propose a flexible scheme to effectively encode math equations, we then enhance the equation encoder by a Varitional Autoen-coder (VAE) 2) given a math equation, we perform topic selection, followed by which a dynamic topic memory mechanism is introduced to restrict the topic distribution of the generator 3) to avoid commonsense violation in traditional generation model, we pretrain word embedding with background knowledge graph (KG), and we link decoded words to related words in KG, targeted at injecting background knowledge into our model. We evaluate our model through both automatic metrices and human evaluation, experiments demonstrate our model outperforms baseline and previous models in both accuracy and richness of generated problem text.
Document-level Relation Extraction (RE) requires extracting relations expressed within and across sentences. Recent works show that graph-based methods, usually constructing a document-level graph that captures document-aware interactions, can obtain useful entity representations thus helping tackle document-level RE. These methods either focus more on the entire graph, or pay more attention to a part of the graph, e.g., paths between the target entity pair. However, we find that document-level RE may benefit from focusing on both of them simultaneously. Therefore, to obtain more comprehensive entity representations, we propose the \textbf{C}oarse-to-\textbf{F}ine \textbf{E}ntity \textbf{R}epresentation model (\textbf{CFER}) that adopts a coarse-to-fine strategy involving two phases. First, CFER uses graph neural networks to integrate global information in the entire graph at a coarse level. Next, CFER utilizes the global information as a guidance to selectively aggregate path information between the target entity pair at a fine level. In classification, we combine the entity representations from both two levels into more comprehensive representations for relation extraction. Experimental results on a large-scale document-level RE dataset show that CFER achieves better performance than previous baseline models. Further, we verify the effectiveness of our strategy through elaborate model analysis.