Neural Machine Translation (NMT) models are trained on parallel corpora with unbalanced word frequency distribution. As a result, NMT models are likely to prefer high-frequency words than low-frequency ones despite low-frequency word may carry the crucial semantic information, which may hamper the translation quality once they are neglected. The objective of this study is to enhance the translation of meaningful but low-frequency words. Our general idea is to optimize the translation of low-frequency words through knowledge distillation. Specifically, we employ a low-frequency teacher model that excels in translating low-frequency words to guide the learning of the student model. To remain the translation quality of high-frequency words, we further introduce a dual-teacher distillation framework, leveraging both the low-frequency and high-frequency teacher models to guide the student model’s training. Our single-teacher distillation method already achieves a +0.64 BLEU improvements over the state-of-the-art method on the WMT 16 English-to-German translation task on the low-frequency test set. While our dual-teacher framework leads to +0.87, +1.24, +0.47, +0.87 and +0.86 BLEU improvements on the IWSLT 14 German-to-English, WMT 16 English-to-German, WMT 15 English-to-Czech, WMT 14 English-to-French and WMT 18 Chinese-to-English tasks respectively compared to the baseline, while maintaining the translation performance of high-frequency words.
The DimABSA task requires fine-grained sentiment intensity prediction for restaurant reviews, including scores for Valence and Arousal dimensions for each Aspect Term. In this study, we propose a Coarse-to-Fine In-context Learning(CFICL) method based on the Baichuan2-7B model for the DimABSA task in the SIGHAN 2024 workshop. Our method improves prediction accuracy through a two-stage optimization process. In the first stage, we use fixed in-context examples and prompt templates to enhance the model’s sentiment recognition capability and provide initial predictions for the test data. In the second stage, we encode the Opinion field using BERT and select the most similar training data as new in-context examples based on similarity. These examples include the Opinion field and its scores, as well as related opinion words and their average scores. By filtering for sentiment polarity, we ensure that the examples are consistent with the test data. Our method significantly improves prediction accuracy and consistency by effectively utilizing training data and optimizing in-context examples, as validated by experimental results.
The rapid development of Chinese large language models (LLMs) poses big challenges for efficient LLM evaluation. While current initiatives have introduced new benchmarks or evaluation platforms for assessing Chinese LLMs, many of these focus primarily on capabilities, usually overlooking potential alignment and safety issues. To address this gap, we introduce OpenEval, an evaluation testbed that benchmarks Chinese LLMs across capability, alignment and safety. For capability assessment, we include 12 benchmark datasets to evaluate Chinese LLMs from 4 sub-dimensions: NLP tasks, disciplinary knowledge, commonsense reasoning and mathematical reasoning. For alignment assessment, OpenEval contains 7 datasets that examines the bias, offensiveness and illegalness in the outputs yielded by Chinese LLMs. To evaluate safety, especially anticipated risks (e.g., power-seeking, self-awareness) of advanced LLMs, we include 6 datasets. In addition to these benchmarks, we have implemented a phased public evaluation and benchmark update strategy to ensure that OpenEval is in line with the development of Chinese LLMs or even able to provide cutting-edge benchmark datasets to guide the development of Chinese LLMs. In our first public evaluation, we have tested a range of Chinese LLMs, spanning from 7B to 72B parameters, including both open-source and proprietary models. Evaluation results indicate that while Chinese LLMs have shown impressive performance in certain tasks, more attention should be directed towards broader aspects such as commonsense reasoning, alignment, and safety.
In medical information extraction, medical Named Entity Recognition (NER) is indispensable, playing a crucial role in developing medical knowledge graphs, enhancing medical question-answering systems, and analyzing electronic medical records. The challenge in medical NER arises from the complex nested structures and sophisticated medical terminologies, distinguishing it from its counterparts in traditional domains. In response to these complexities, we propose a medical NER model based on Machine Reading Comprehension (MRC), which uses a task-adaptive pre-training strategy to improve the model’s capability in the medical field. Meanwhile, our model introduces multiple word-pair embeddings and multi-granularity dilated convolution to enhance the model’s representation ability and uses a combined predictor of Biaffine and MLP to improve the model’s recognition performance. Experimental evaluations conducted on the CMeEE, a benchmark for Chinese nested medical NER, demonstrate that our proposed model outperforms the compared state-of-the-art (SOTA) models.
Artificial Intelligence (AI), along with the recent progress in biomedical language understanding, is gradually offering great promise for 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.
Emotion recognition in conversation is important for an empathetic dialogue system to understand the user’s emotion and then generate appropriate emotional responses. However, most previous researches focus on modeling conversational contexts primarily based on the textual modality or simply utilizing multimodal information through feature concatenation. In order to exploit multimodal information and contextual information more effectively, we propose a multimodal directed acyclic graph (MMDAG) network by injecting information flows inside modality and across modalities into the DAG architecture. Experiments on IEMOCAP and MELD show that our model outperforms other state-of-the-art models. Comparative studies validate the effectiveness of the proposed modality fusion method.
Paraphrasing, i.e., restating the same meaning in different ways, is an important data augmentation approach for natural language processing (NLP). Zhang et al. (2019b) propose to extract sentence-level paraphrases from multiple Chinese translations of the same source texts, and construct the PKU Paraphrase Bank of 0.5M sentence pairs. However, despite being the largest Chinese parabank to date, the size of PKU parabank is limited by the availability of one-to-many sentence translation data, and cannot well support the training of large Chinese paraphrasers. In this paper, we relieve the restriction with one-to-many sentence translation data, and construct ParaZh-22M, a larger Chinese parabank that is composed of 22M sentence pairs, based on one-to-one bilingual sentence translation data and machine translation (MT). In our data augmentation experiments, we show that paraphrasing based on ParaZh-22M can bring about consistent and significant improvements over several strong baselines on a wide range of Chinese NLP tasks, including a number of Chinese natural language understanding benchmarks (CLUE) and low-resource machine translation.
电子病历是医疗信息的重要来源,包含大量与医疗相关的领域知识。本文从糖尿病电子病历文本入手,在调研了国内外已有的电子病历语料库的基础上,参考坉圲坂圲实体及关系分类,建立了糖尿病电子病历实体及实体关系分类体系,并制定了标注规范。利用实体及关系标注平台,进行了实体及关系预标注及多轮人工校对工作,形成了糖尿病电子病历实体及关系标注语料库(Diabetes Electronic Medical Record entity and Related Corpus DEMRC)。所构建的DEMRC包含8899个实体、456个实体修饰及16564个关系。对DEMRC进行一致性评价和分析,标注结果达到了较高的一致性。针对实体识别和实体关系抽取任务,分别采用基于迁移学习的Bi-LSTM-CRF模型和RoBERTa模型进行初步实验,并对语料库中的各类实体及关系进行评估,为后续糖尿病电子病历实体识别及关系抽取研究以及糖尿病知识图谱构建打下基础。
本文探讨了在脑卒中疾病中文电子病历文本中实体及实体间关系的标注问题,提出了适用于脑卒中疾病电子病历文本的实体及实体关系标注体系和规范。在标注体系和规范的指导下,进行了多轮的人工标注及校正工作,完成了158万余字的脑卒中电子病历文本实体及实体关系的标注工作。构建了脑卒中电子病历实体及实体关系标注语料库(Stroke Electronic Medical Record entity and entity related Corpus SEMRC)。所构建的语料库共包含命名实体10594个,实体关系14457个。实体名标注一致率达到85.16%,实体关系标注一致率达到94.16%。
Spelling Error Correction (SEC) that requires high-level language understanding is a challenging but useful task. Current SEC approaches normally leverage a pre-training then fine-tuning procedure that treats data equally. By contrast, Curriculum Learning (CL) utilizes training data differently during training and has shown its effectiveness in improving both performance and training efficiency in many other NLP tasks. In NMT, a model’s performance has been shown sensitive to the difficulty of training examples, and CL has been shown effective to address this. In SEC, the data from different language learners are naturally distributed at different difficulty levels (some errors made by beginners are obvious to correct while some made by fluent speakers are hard), and we expect that designing a curriculum correspondingly for model learning may also help its training and bring about better performance. In this paper, we study how to further improve the performance of the state-of-the-art SEC method with CL, and propose a Self-Supervised Curriculum Learning (SSCL) approach. Specifically, we directly use the cross-entropy loss as criteria for: 1) scoring the difficulty of training data, and 2) evaluating the competence of the model. In our approach, CL improves the model training, which in return improves the CL measurement. In our experiments on the SIGHAN 2015 Chinese spelling check task, we show that SSCL is superior to previous norm-based and uncertainty-aware approaches, and establish a new state of the art (74.38% F1).
The obstetric Electronic Medical Record (EMR) contains a large amount of medical data and health information. It plays a vital role in improving the quality of the diagnosis assistant service. In this paper, we treat the diagnosis assistant as a multi-label classification task and propose a Knowledge-Enabled Diagnosis Assistant (KEDA) model for the obstetric diagnosis assistant. We utilize the numerical information in EMRs and the external knowledge from Chinese Obstetric Knowledge Graph (COKG) to enhance the text representation of EMRs. Specifically, the bidirectional maximum matching method and similarity-based approach are used to obtain the entities set contained in EMRs and linked to the COKG. The final knowledge representation is obtained by a weight-based disease prediction algorithm, and it is fused with the text representation through a linear weighting method. Experiment results show that our approach can bring about +3.53 F1 score improvements upon the strong BERT baseline in the diagnosis assistant task.
Chinese Grammatical Error Diagnosis (CGED) is a natural language processing task for the NLPTEA6 workshop. The goal of this task is to automatically diagnose grammatical errors in Chinese sentences written by L2 learners. This paper proposes a RoBERTa-BiLSTM-CRF model to detect grammatical errors in sentences. Firstly, RoBERTa model is used to obtain word vectors. Secondly, word vectors are input into BiLSTM layer to learn context features. Last, CRF layer without hand-craft features work for processing the output by BiLSTM. The optimal global sequences are obtained according to state transition matrix of CRF and adjacent labels of training data. In experiments, the result of RoBERTa-CRF model and ERNIE-BiLSTM-CRF model are compared, and the impacts of parameters of the models and the testing datasets are analyzed. In terms of evaluation results, our recall score of RoBERTa-BiLSTM-CRF ranks fourth at the detection level.
In the process of learning Chinese, second language learners may have various grammatical errors due to the negative transfer of native language. This paper describes our submission to the NLPTEA 2020 shared task on CGED. We present a hybrid system that utilizes both detection and correction stages. The detection stage is a sequential labelling model based on BiLSTM-CRF and BERT contextual word representation. The correction stage is a hybrid model based on the n-gram and Seq2Seq. Without adding additional features and external data, the BERT contextual word representation can effectively improve the performance metrics of Chinese grammatical error detection and correction.
In the process of learning and using Chinese, many learners of Chinese as foreign language(CFL) may have grammar errors due to negative migration of their native languages. This paper introduces our system that can simultaneously diagnose four types of grammatical errors including redundant (R), missing (M), selection (S), disorder (W) in NLPTEA-5 shared task. We proposed a Bidirectional LSTM CRF neural network (BiLSTM-CRF) that combines BiLSTM and CRF without hand-craft features for Chinese Grammatical Error Diagnosis (CGED). Evaluation includes three levels, which are detection level, identification level and position level. At the detection level and identification level, our system got the third recall scores, and achieved good F1 values.
In the process of learning and using Chinese, foreigners may have grammatical errors due to negative migration of their native languages. Currently, the computer-oriented automatic detection method of grammatical errors is not mature enough. Based on the evaluating task — CGED2016, we select and analyze the classification model and design feature extraction method to obtain grammatical errors including Mission(M), Disorder(W), Selection (S) and Redundant (R) automatically. The experiment results based on the dynamic corpus of HSK show that the Chinese grammatical error automatic detection method, which uses CRF as classification model and n-gram as feature extraction method. It is simple and efficient which play a positive effect on the research of Chinese grammatical error automatic detection and also a supporting and guiding role in the teaching of Chinese as a foreign language.