Search

Abstract In recent years, recommendation explanation methods have received widespread attention due to their potentials to enhance user experience and streamline transactions. In scenarios where auxiliary information such as text and attributes are lacking, counterfactual explanation has emerged as a crucial technique for explaining recommendations. However, existing counterfactual explanation methods encounter two primary challenges. First, a substantial bias indeed exists in the calculation of the group impact function, leading to the inaccurate predictions as the counterfactual explanation group expands. In addition, the importance of collaborative filtering as a counterfactual explanation is overlooked, which results in lengthy, narrow, and inaccurate explanations. To address such issues, we propose a counterfactual explanation method based on Modified Group Influence Function for recommendation. In particular, via a rigorous formula derivation, we demonstrate that a simple summation of individual influence functions cannot reflect the group impact in recommendations. After that, building upon the improved influence function, we construct the counterfactual groups by iteratively incorporating the individuals from the training samples, which possess the greatest influence on the recommended results, and continuously adjusting the parameters to ensure accuracy. Finally, we expand the scope of searching for counterfactual groups by incorporating the collaborative filtering information from different users. To evaluate the effectiveness of our method, we employ it to explain the recommendations generated by two common recommendation models, i.e., Matrix Factorization and Neural Collaborative Filtering, on two publicly available datasets. The evaluation of the proposed counterfactual explanation method showcases its superior performance in providing counterfactual explanations. In the most significant case, our proposed method achieves a 17% lead in terms of Counterfactual precision compared to the best baseline explanation method.

Text classification aims to assign predefined labels to unlabeled sentences, which tend to struggle in real-world applications when only a few annotated samples are available. Previous works generally focus on using the paradigm of meta-learning to overcome the classification difficulties brought by insufficient data, where a set of auxiliary tasks is given. Accordingly, prompt-based approaches are proposed to deal with the low-resource issue. However, existing prompt-based methods mainly focus on English tasks, which generally apply English pretrained language models that can not directly adapt to Chinese tasks due to structural and grammatical differences. Thus, we propose a prompt-based Chinese text classification framework that uses generated natural language sequences as hints, which can alleviate the classification bottleneck well in low-resource scenarios. In detail, we first design a prompt-based fine-tuning together with a novel pipeline for automating prompt generation in Chinese. Then, we propose a refined strategy for dynamically and selectively incorporating demonstrations into each context. We present a systematic evaluation for analyzing few-shot performance on a wide range of Chinese text classification tasks. Our approach makes few assumptions about task resources and expertise and therefore constitutes a powerful, task-independent approach for few-shot learning.

Answer selection is a crucial subtask in the question answering (QA) system. Conventional avenues for this task mainly concentrate on developing linguistic tools that are limited in both performance and practicability. Answer selection approaches based on deep learning have been well investigated with the tremendous success of deep learning in natural language processing. However, the traditional neural networks employed in existing answer selection models, i.e., recursive neural network or convolutional neural network, typically suffer from obtaining the global text information due to their operating mechanisms. The recent Transformer neural network is considered to be good at extracting the global information by employing only self-attention mechanism. Thus, in this paper, we design a Transformer-based neural network for answer selection, where we deploy a bidirectional long short-term memory (BiLSTM) behind the Transformer to acquire both global information and sequential features in the question or answer sentence. Different from the original Transformer, our Transformer-based network focuses on sentence embedding rather than the seq2seq task. In addition, we employ a BiLSTM rather than utilizing the position encoding to incorporate sequential features as the universal Transformer does. Furthermore, we apply three aggregated strategies to generate sentence embeddings for question and answer, i.e., the weighted mean pooling, the max pooling, and the attentive pooling, leading to three corresponding Transformer-based models, i.e., QA-TFWP, QA-TFMP, and QA-TFAP, respectively. Finally, we evaluate our proposals on a popular QA dataset WikiQA. The experimental results demonstrate that our proposed Transformer-based answer selection models can produce a better performance compared with several competitive baselines. In detail, our best model outperforms the state-of-the-art baseline by up to 2.37%, 2.83%, and 3.79% in terms of MAP, MRR, and accuracy, respectively.

Answer selection is an essential step in a question answering (QA) system. Traditional methods for this task mainly focus on developing linguistic features that are limited in practice. With the great success of deep learning method in distributed text representation, deep learning-based answer selection approaches have been well investigated, which mainly employ only one neural network, i.e., convolutional neural network (CNN) or long short term memory (LSTM), leading to failures in extracting some rich sentence features. Thus, in this paper, we propose a collaborative learning-based answer selection model (QA-CL), where we deploy a parallel training architecture to collaboratively learn the initial word vector matrix of the sentence by CNN and bidirectional LSTM (BiLSTM) at the same time. In addition, we extend our model by incorporating the sentence embedding generated by the QA-CL model into a joint distributed sentence representation using a strong unsupervised baseline weight removal (WR), i.e., the QA-CLWR model. We evaluate our proposals on a popular QA dataset, InsuranceQA. The experimental results indicate that our proposed answer selection methods can produce a better performance compared with several strong baselines. Finally, we investigate the models’ performance with respect to different question types and find that question types with a medium number of questions have a better and more stable performance than those types with too large or too small number of questions.

Chinese Medical Named Entity Recognition (Chinese-MNER) aims to identify potential entities and their categories from the unstructured Chinese medical text. Existing methods for this task mainly incorporate the dictionary knowledge on the basis of traditional BiLSTM-CRF or BERT architecture. However, the construction of high-quality dictionaries is typically time consuming and labor-intensive, which may also damage the robustness of NER models. What is more, the limited amount of annotated Chinese-MNER data can easily lead to the over-fitting problem while training. With the aim of dealing with the above problems, we put forward a BERT-BiLSTM-CRF model by integrating the part-of-speech (POS) tagging features and a Regularization method (BBCPR) for Chinese-MNER. In BBCPR, we first leverage a POS fusion layer to incorporate external syntax knowledge. Next, we design a novel REgularization mothod with Adversarial training and Dropout (READ) to improve the model robustness. Specifically, READ focuses on reducing the difference between the predictions of two sub-models through minimizing the bidirectional KL divergence between the adversarial output and original output distributions for the same sample. Comprehensive evaluations on two public data sets, namely, cMedQANER and cEHRNER from the Chinese Biomedical Language Understanding Evaluation benchmark (ChineseBLUE), demonstrate the superiority of our proposal in Chinese-MNER. In addition, ablation study shows that READ can effectively improve the model performance. Our proposal does well in exploring the technical terms and identifying the word boundary.

Document classification has a broad application in the field of sentiment classification, document ranking and topic labeling, etc. Previous neural network-based work has mainly focused on investigating a so-called forward implication, i.e., the preceding text segments are taken as the context of the following text segments when generating the text representation. Such a scenario typically ignores the fact that the semantics of a document are a product of the mutual implication of all text segments in a document. Thus, in this paper, we introduce a concept of interaction and propose a text representation model with Self-interaction Attention Mechanism (TextSAM) for document classification. In particular, we design three aggregated strategies to integrate the interaction into a hierarchical architecture for document classification, i.e., averaging the interaction, maximizing the interaction and adding one more attention layer on the interaction, which leads to three models, i.e., TextSAMAVE, TextSAMMAX and TextSAMATT, respectively. Our comprehensive experimental results on two public datasets, i.e., Yelp 2016 and Amazon Reviews (Electronics), show that our proposals can significantly outperform the state-of-the-art neural-based baselines for document classification, presenting a general improvement in terms of accuracy ranging from 5.97% to 14.05% against the best baseline. Furthermore, we find that our proposals with a self-interaction attention mechanism can obviously alleviate the impact brought by the increase of sentence number as the relative improvement of our proposals against the baselines are enlarged when the sentence number increases.