With the advancements of artificial intelligence technology, ChatGPT, a new practice of artificial intelligence, holds immense potential across multiple fields. Its user-friendly human-machine interface, rapid response capabilities, and delivery of high-quality answers have attracted considerable attention and widespread usage. Regarded by many as a groundbreaking advancement in AI, ChatGPT represents a new milestone in the field. However, as with any technological evolution, the emergence of ChatGPT brings not only benefits, but also inevitable security risks and ethical issues. This paper provides specific information about ChatGPT, including its technology, limitations, ethical issues, governance paths and future directions. Specifically, we firstly offered a thorough exploration of the technical implementation details of GPT series models. Next, we provided an intricate analysis elucidating the reasons for limitations and scrutinized the consequential impacts, such as malicious misuse, privacy violation, and so on. Finally, we explore diverse governance paths to mitigate the impacts of ChatGPT and present future directions. This review aims to equip users with crucial knowledge, facilitating well-informed decision-making, effectively handling of potential challenges in employing ChatGPT, and staying abreast with the rapidly evolving landscape of this technology.
21 July 2023 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Aspect-based sentiment analysis (ABSA), an extensively researched area in the field of natural language processing (NLP), predicts the sentiment expressed in a text relative to the corresponding aspect. Unfortunately, most languages lack sufficient annotation resources; thus, an increasing number of recent researchers have focused on cross-lingual aspect-based sentiment analysis (XABSA). However, most recent studies focus only on cross-lingual data alignment instead of model alignment. Therefore, we propose a novel framework, CL-XABSA: contrastive learning for cross-lingual aspect-based sentiment analysis. Based on contrastive learning, we close the distance between samples with the same label in different semantic spaces, achieving convergence of semantic spaces of different languages. Specifically, we design two contrastive objectives, token-level contrastive learning of token embeddings (TL-CTE) and sentiment-level contrastive learning of token embeddings (SL-CTE), to unify the semantic space of source and target languages. Since CL-XABSA can receive datasets in multiple languages during training, it can be further extended to multilingual aspect-based sentiment analysis (MABSA). To further improve the model performance, we perform knowledge distillation with target-language unlabeled data. In the distillation XABSA task, we further explore the effectiveness of different data (source dataset, translated dataset, and code-switched dataset). The results demonstrate that the proposed method has a certain improvement in the three XABSA tasks, distillation XABSA and MABSA. The source code of this paper is publicly available at https://github.com/GKLMIP/CL-XABSA .
19 November 2021 in Applied Artificial Intelligence
With the rapid development of social networks, more and more people express their emotions and opinions via online videos. However, most of the current research on multimodal sentiment analysis cannot do well with effective emotional fusion in multimodal data. To deal with the problem, we propose a multi-tensor fusion network with cross-modal modeling for multimodal sentiment analysis. In this study, the multimodal feature extraction with cross-modal modeling is utilized to obtain the relationship of emotional information between multiple modalities. Moreover, the multi-tensor fusion network is used to model the interaction of multiple pairs of bimodal and realize the emotional prediction of multimodal features. The proposed approach performs well in regression and different dimensions of classification experiments on the two public datasets CMU-MOSI and CMU-MOSEI.
Automatic text summarisation (ATS) (therein two main approaches–abstractive summarisation and extractive summarisation are involved) is an automatic procedure for extracting critical information from the text using a specific algorithm or method. Due to the scarcity of corpus, abstractive summarisation achieves poor performance for low-resource language ATS tasks. That’s why it is common for researchers to apply extractive summarisation to low-resource language instead of using abstractive summarisation. As an emerging branch of extraction-based summarisation, methods based on feature analysis quantitate the significance of information by calculating utility scores of each sentence in the article. In this study, we propose a simple but effective extractive method based on the Light Gradient Boosting Machine regression model for Indonesian documents. Four features are extracted, namely PositionScore, TitleScore, the semantic representation similarity between the sentence and the title of document, the semantic representation similarity between the sentence and sentence’s cluster center. We define a formula for calculating the sentence score as the objective function of the linear regression. Considering the characteristics of Indonesian, we use Indonesian lemmatisation technology to improve the calculation of sentence score. The results show that our method is more applicable.
1 March 2023 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Named Entity Recognition (NER) is fundamental to multiple downstream natural language processing (NLP) tasks, but most advanced NER methods heavily rely on massive labeled data with high cost. In this paper, we explore the effectiveness of self-training for low-resource NER. It is one of the semi-supervised approaches to reduce the reliance on manual annotation. However, random pseudo sample selection in standard self-training framework may cause serious error propagation, especially for token-level tasks. To that end, this paper focuses on pseudo sample selection and proposes a new self-training framework with double selectors, namely auxiliary judge task and entropy-based confidence measurement. Specifically, the auxiliary judge task is proposed to filter out the pseudo samples with wrong predictions. The entropy-based confidence measurement is introduced to select pseudo samples with high quality. In addition, to make full use of all pseudo samples, we propose a cumulative function based on the idea of curriculum learning to prompt the model to learn from easy samples to hard ones. Samples with low quality are filtered out through the double selectors, which is more conducive to the training of student models. Experimental results on five NER benchmark datasets from different languages indicate the effectiveness of the proposed framework over several advanced baselines.
Named entity recognition (NER) is a key component of many natural language processing (NLP) applications. The majority of advanced research, however, has not been widely applied to low-resource languages represented by Malay due to the data-hungry problem. In this paper, we present a system for building a Malay NER dataset (MS-NER) of 20,146 sentences through labelled datasets of homologous languages and iterative optimisation. Additionally, we propose a Multi-Task framework, namely MTBR, to integrate boundary information more effectively for NER. Specifically, boundary detection is treated as an auxiliary task and an enhanced Bidirectional Revision module with a gated ignoring mechanism is proposed to undertake conditional label transfer. This can reduce error propagation by the auxiliary task. We conduct extensive experiments on Malay, Indonesian, and English. Experimental results show that MTBR could achieve competitive performance and tends to outperform multiple baselines. The constructed dataset and model would be made available to the public as a new, reliable benchmark for Malay NER.