OpenAI has released the Chat Generative Pre-trained Transformer (ChatGPT) and revolutionized the approach in artificial intelligence to human-model interaction. The first contact with the chatbot ...reveals its ability to provide detailed and precise answers in various areas. Several publications on ChatGPT evaluation test its effectiveness on well-known natural language processing (NLP) tasks. However, the existing studies are mostly non-automated and tested on a very limited scale. In this work, we examined ChatGPT’s capabilities on 25 diverse analytical NLP tasks, most of them subjective even to humans, such as sentiment analysis, emotion recognition, offensiveness, and stance detection. In contrast, the other tasks require more objective reasoning like word sense disambiguation, linguistic acceptability, and question answering. We also evaluated GPT-4 model on five selected subsets of NLP tasks. We automated ChatGPT and GPT-4 prompting process and analyzed more than 49k responses. Our comparison of its results with available State-of-the-Art (SOTA) solutions showed that the average loss in quality of the ChatGPT model was about 25% for zero-shot and few-shot evaluation. For GPT-4 model, a loss for semantic tasks is significantly lower than for ChatGPT. We showed that the more difficult the task (lower SOTA performance), the higher the ChatGPT loss. It especially refers to pragmatic NLP problems like emotion recognition. We also tested the ability to personalize ChatGPT responses for selected subjective tasks via Random Contextual Few-Shot Personalization, and we obtained significantly better user-based predictions. Additional qualitative analysis revealed a ChatGPT bias, most likely due to the rules imposed on human trainers by OpenAI. Our results provide the basis for a fundamental discussion of whether the high quality of recent predictive NLP models can indicate a tool’s usefulness to society and how the learning and validation procedures for such systems should be established.
•The results of ChatGPT and GPT-4 evaluation on 25 tasks using 48k+ prompts.•Context-awareness and personalization are valuable capabilities of ChatGPT.•ChatGPT and GPT-4 are always worse compared to SOTA methods from 4% to over 70%.•ChatGPT loss tends to be higher for more difficult reasoning problems.•ChatGPT can boost AI development and change our daily lives.
Analysis of subjective texts like offensive content or hate speech is a great challenge, especially regarding annotation process. Most of current annotation procedures are aimed at achieving a high ...level of agreement in order to generate a high quality reference source. However, the annotation guidelines for subjective content may restrict the annotators’ freedom of decision making. Motivated by a moderate annotation agreement in offensive content datasets, we hypothesize that personalized approaches to offensive content identification should be in place. Thus, we propose two novel perspectives of perception: group-based and individual. Using demographics of annotators as well as embeddings of their previous decisions (annotated texts), we are able to train multimodal models (including transformer-based) adjusted to personal or community profiles. Based on the agreement of individuals and groups, we experimentally showed that annotator group agreeability strongly correlates with offensive content recognition quality. The proposed personalized approaches enabled us to create models adaptable to personal user beliefs rather than to agreed offensiveness understanding. Overall, our individualized approaches to offensive content classification outperform classic data-centric methods that generalize offensiveness perception and it refers to all six tested models. Additionally, we developed requirements for annotation procedures, personalization and content processing to make the solutions human-centered.
•A list of requirements for new human-centered content analyses.•3 perspectives for subjective content perception that affect annotation procedures.•New methods for offensive content recognition that respect full personalization.•Reasoning process based on personal behavior implementing human-centered approaches.•Multimodal transformer-based human-centered data representations.•Combining text, metadata, annotator demographics, and annotator behavior.•Evidence that human-centered classification approaches outperform classic methods.
Some tasks in content processing, e.g., natural language processing (NLP), like hate or offensive speech and emotional or funny text detection, are subjective by nature. Each human may perceive some ...content individually. The existing reasoning methods commonly rely on agreed output values, the same for all recipients. We propose fundamentally different — personalized solutions applicable to any subjective NLP task. Our five new deep learning models take into account not only the textual content but also the opinions and beliefs of a given person. They differ in their approaches to learning Human Bias (HuBi) and fusion with content (text) representation. The experiments were carried out on 14 tasks related to offensive, emotional, and humorous texts. Our personalized HuBi methods radically outperformed the generalized ones for all NLP problems. Personalization also has a greater impact on reasoning quality than commonly explored pre-trained and fine-tuned language models. We discovered a high correlation between human bias calculated using our dedicated formula and that learned by the model. Multi-task solutions achieved better outcomes than single-task architectures. Human and word embeddings also provided additional insights.
•Human-centered neural architectures suitable for subjective NLP problems are introduced.•Personalized NLP requires dedicated validation procedures.•Personalized methods revealed their superiority over generalized approaches for 14 tasks related to hate speech, emotions and humor.•Language models, multi-tasking and fine-tuning have less impact than personalization.•There is correlation between formula-based human bias and bias learned by the neural model.
Many tasks in natural language processing like offensive, toxic, or emotional text classification are subjective by nature. Humans tend to perceive textual content in their own individual way. ...Existing methods commonly rely on the agreed output values, the same for all consumers. Here, we propose personalized solutions to subjective tasks. Our four new deep learning models take into account not only the content but also the specificity of a given human. The models represent different approaches to learning the representation and processing data about text readers. The experiments were carried out on four datasets: Wikipedia discussion texts labelled with attack, aggression, and toxicity, as well as opinions annotated with ten numerical emotional categories. Emotional data was considered as multivariate regression (multitask), whereas Wikipedia data as independent classifications. All our models based on human biases and their representations significantly improve the prediction quality in subjective tasks evaluated from the individual's perspective.
Data annotated by humans is a source of knowledge by describing the peculiarities of the problem and therefore fueling the decision process of the trained model. Unfortunately, the annotation process ...for subjective natural language processing (NLP) problems like offensiveness or emotion detection is often very expensive and time-consuming. One of the inevitable risks is to spend some of the funds and annotator effort on annotations that do not provide any additional knowledge about the specific task. To minimize these costs, we propose a new model-based approach that allows the selection of tasks annotated individually for each text in a multi-task scenario. The experiments carried out on three datasets, dozens of NLP tasks, and thousands of annotations show that our method allows up to 40% reduction in the number of annotations with negligible loss of knowledge. The results also emphasize the need to collect a diverse amount of data required to efficiently train a model, depending on the subjectivity of the annotation task. We also focused on measuring the relation between subjective tasks by evaluating the model in single-task and multi-task scenarios. Moreover, for some datasets, training only on the labels predicted by our model improved the efficiency of task selection as a self-supervised learning regularization technique.
Data annotated by humans is a source of knowledge by describing the peculiarities of the problem and therefore fueling the decision process of the trained model. Unfortunately, the annotation process ...for subjective natural language processing (NLP) problems like offensiveness or emotion detection is often very expensive and time-consuming. One of the inevitable risks is to spend some of the funds and annotator effort on annotations that do not provide any additional knowledge about the specific task. To minimize these costs, we propose a new model-based approach that allows the selection of tasks annotated individually for each text in a multi-task scenario. The experiments carried out on three datasets, dozens of NLP tasks, and thousands of annotations show that our method allows up to 40% reduction in the number of annotations with negligible loss of knowledge. The results also emphasize the need to collect a diverse amount of data required to efficiently train a model, depending on the subjectivity of the annotation task. We also focused on measuring the relation between subjective tasks by evaluating the model in single-task and multi-task scenarios. Moreover, for some datasets, training only on the labels predicted by our model improved the efficiency of task selection as a self-supervised learning regularization technique.
Multitask Personalized Recognition of Emotions Evoked by Textual Content Milkowski, Piotr; Saganowski, Stanislaw; Gruza, Marcin ...
2022 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops),
2022-March-21
Conference Proceeding
In this paper, we present the studies on personalized emotion recognition in text perception in the multitask setting. We analyze the performance of the joint learning of the model within groups of ...similar tasks (sub-multitask approach) and for all tasks learned together (full multitask) versus the classical approach based on separate models dedicated to each individual task (single-task). Additionally, we use our novel personalized deep learning architectures capable of recognizing emotions from the user's perspective through the calculated Human Bias and learned vector representation of the user. These methods are combined with state-of-the-art linguistic models based on transformers to represent the textual content. The results show a significant gain in emotion recognition quality in both sub-multitask and multitask scenarios. In each setup, personalization yields a significant quality gain, which is essential from the perspective of AI systems responding to the emotions of a specific user.
As humans, we experience a wide range of feelings and reactions. One of these is laughter, often related to a personal sense of humor and the perception of funny content. Due to its subjective ...nature, recognizing humor in NLP is a very challenging task. Here, we present a new approach to the task of predicting humor in the text by applying the idea of a personalized approach. It takes into account both the text and the context of the content receiver. For that purpose, we proposed four Deep-SHEEP learning models that take advantage of user preference information differently. The experiments were conducted on four datasets: Cockamamie, HUMOR, Jester, and Humicroedit. The results have shown that the application of an innovative personalized approach and user-centric perspective significantly improves performance compared to generalized methods. Moreover, even for random text embeddings, our personalized methods outperform the generalized ones in the subjective humor modeling task. We also argue that the user-related data reflecting an individual sense of humor has similar importance as the evaluated text itself. Different types of humor were investigated as well.
Despite impressive advancements in multilingual corpora collection and model training, developing large-scale deployments of multilingual models still presents a significant challenge. This is ...particularly true for language tasks that are culture-dependent. One such example is the area of multilingual sentiment analysis, where affective markers can be subtle and deeply ensconced in culture. This work presents the most extensive open massively multilingual corpus of datasets for training sentiment models. The corpus consists of 79 manually selected datasets from over 350 datasets reported in the scientific literature based on strict quality criteria. The corpus covers 27 languages representing 6 language families. Datasets can be queried using several linguistic and functional features. In addition, we present a multi-faceted sentiment classification benchmark summarizing hundreds of experiments conducted on different base models, training objectives, dataset collections, and fine-tuning strategies.
Models are increasing in size and complexity in the hunt for SOTA. But what if those 2\% increase in performance does not make a difference in a production use case? Maybe benefits from a smaller, ...faster model outweigh those slight performance gains. Also, equally good performance across languages in multilingual tasks is more important than SOTA results on a single one. We present the biggest, unified, multilingual collection of sentiment analysis datasets. We use these to assess 11 models and 80 high-quality sentiment datasets (out of 342 raw datasets collected) in 27 languages and included results on the internally annotated datasets. We deeply evaluate multiple setups, including fine-tuning transformer-based models for measuring performance. We compare results in numerous dimensions addressing the imbalance in both languages coverage and dataset sizes. Finally, we present some best practices for working with such a massive collection of datasets and models from a multilingual perspective.