Reasoning is a key pillar of human cognition and intelligence. In the past decade, we witnessed dramatic gains in natural language processing and unprecedented scaling of large language models. Recent work has characterized the capability of few-shot prompting techniques such as chain of thought to emulate human reasoning in large language models. This hallmark feature of few-shot prompting, combined with ever scaling language models, opened a vista of possibilities to solve various tasks, such as math word problems, code completion, and commonsense reasoning. Chain of thought (CoT) prompting further pushes the performance of models in a few-shot setup, by supplying intermediate steps and urging the model to follow the same process. Despite its compelling performance, the genesis of reasoning capability in these models is less explored. This work initiates the preliminary steps towards a deeper understanding of reasoning mechanisms in large language models. Our work centers around querying the model while controlling for all but one of the components in a prompt: symbols, patterns, and text. We then analyze the performance divergence across the queries. Our results suggest the presence of factual patterns in a prompt is not necessary for the success of CoT. Nonetheless, we empirically show that relying solely on patterns is also insufficient for high quality results. We posit that text imbues patterns with commonsense knowledge and meaning. Our exhaustive empirical analysis provides qualitative examples of the symbiotic relationship between text and patterns. Such systematic understanding of CoT enables us to devise concise chain of thought, dubbed as CCoT, where text and patterns are pruned to only retain their key roles, while delivering on par or slightly higher solve task rate.
In the span of a few months, generative Artificial Intelligence (AI) tools that can generate realistic images or text have taken the Internet by storm, making them one of the technologies with fastest adoption ever. Some of these generative AI tools such as DALL-E, MidJourney, or ChatGPT have gained wide public notoriety. Interestingly, these tools are possible because of the massive amount of data (text and images) available on the Internet. The tools are trained on massive data sets that are scraped from Internet sites. And now, these generative AI tools are creating massive amounts of new data that are being fed into the Internet. Therefore, future versions of generative AI tools will be trained with Internet data that is a mix of original and AI-generated data. As time goes on, a mixture of original data and data generated by different versions of AI tools will populate the Internet. This raises a few intriguing questions: how will future versions of generative AI tools behave when trained on a mixture of real and AI generated data? Will they evolve with the new data sets or degenerate? Will evolution introduce biases in subsequent generations of generative AI tools? In this document, we explore these questions and report some very initial simulation results using a simple image-generation AI tool. These results suggest that the quality of the generated images degrades as more AI-generated data is used for training thus suggesting that generative AI may degenerate. Although these results are preliminary and cannot be generalised without further study, they serve to illustrate the potential issues of the interaction between generative AI and the Internet.
Real-world data contains a vast amount of multimodal information, among which vision and language are the two most representative modalities. Moreover, increasingly heavier models, e.g., Transformers, have attracted the attention of researchers to model compression. However, how to compress multimodal models, especially vison-language Transformers, is still under-explored. This paper proposes the \textbf{U}nified and \textbf{P}r\textbf{o}gressive \textbf{P}runing (UPop) as a universal vison-language Transformer compression framework, which incorporates 1) unifiedly searching multimodal subnets in a continuous optimization space from the original model, which enables automatic assignment of pruning ratios among compressible modalities and structures; 2) progressively searching and retraining the subnet, which maintains convergence between the search and retrain to attain higher compression ratios. Experiments on multiple generative and discriminative vision-language tasks, including Visual Reasoning, Image Caption, Visual Question Answer, Image-Text Retrieval, Text-Image Retrieval, and Image Classification, demonstrate the effectiveness and versatility of the proposed UPop framework.
Voice synthesis has seen significant improvements in the past decade resulting in highly intelligible voices. Further investigations have resulted in models that can produce variable speech, including conditional emotional expression. The problem lies, however, in a focus on phrase-level modifications and prosodic vocal features. Using the CREMA-D dataset we have trained a GAN conditioned on emotion to generate worth lengths for a given input text. These word lengths are relative to neutral speech and can be provided, through speech synthesis markup language (SSML) to a text-to-speech (TTS) system to generate more expressive speech. Additionally, a generative model is also trained using implicit maximum likelihood estimation (IMLE) and a comparative analysis with GANs is included. We were able to achieve better performances on objective measures for neutral speech, and better time alignment for happy speech when compared to an out-of-box model. However, further investigation of subjective evaluation is required.
Clinical factors account only for a small portion, about 10-30%, of the controllable factors that affect an individual's health outcomes. The remaining factors include where a person was born and raised, where he/she pursued their education, what their work and family environment is like, etc. These factors are collectively referred to as Social Determinants of Health (SDoH). The majority of SDoH data is recorded in unstructured clinical notes by physicians and practitioners. Recording SDoH data in a structured manner (in an EHR) could greatly benefit from a dedicated ontology of SDoH terms. Our research focuses on extracting sentences from clinical notes, making use of such an SDoH ontology (called SOHO) to provide appropriate concepts. We utilize recent advancements in Deep Learning to optimize the hyperparameters of a Clinical BioBERT model for SDoH text. A genetic algorithm-based hyperparameter tuning regimen was implemented to identify optimal parameter settings. To implement a complete classifier, we pipelined Clinical BioBERT with two subsequent linear layers and two dropout layers. The output predicts whether a text fragment describes an SDoH issue of the patient. We compared the AdamW, Adafactor, and LAMB optimizers. In our experiments, AdamW outperformed the others in terms of accuracy.
Clinical notes containing valuable patient information are written by different health care providers with various scientific levels and writing styles. It might be helpful for clinicians and researchers to understand what information is essential when dealing with extensive electronic medical records. Entities recognizing and mapping them to standard terminologies is crucial in reducing ambiguity in processing clinical notes. Although named entity recognition and entity linking are critical steps in clinical natural language processing, they can also result in the production of repetitive and low-value concepts. In other hand, all parts of a clinical text do not share the same importance or content in predicting the patient's condition. As a result, it is necessary to identify the section in which each content is recorded and also to identify key concepts to extract meaning from clinical texts. In this study, these challenges have been addressed by using clinical natural language processing techniques. In addition, in order to identify key concepts, a set of popular unsupervised key phrase extraction methods has been verified and evaluated. Considering that most of the clinical concepts are in the form of multi-word expressions and their accurate identification requires the user to specify n-gram range, we have proposed a shortcut method to preserve the structure of the expression based on TF-IDF. In order to evaluate the pre-processing method and select the concepts, we have designed two types of downstream tasks (multiple and binary classification) using the capabilities of transformer-based models. The obtained results show the superiority of proposed method in combination with SciBERT model, also offer an insight into the efficacy of general extracting essential phrase methods for clinical notes.
Image colorization is a well-known problem in computer vision. However, due to the ill-posed nature of the task, image colorization is inherently challenging. Though several attempts have been made by researchers to make the colorization pipeline automatic, these processes often produce unrealistic results due to a lack of conditioning. In this work, we attempt to integrate textual descriptions as an auxiliary condition, along with the grayscale image that is to be colorized, to improve the fidelity of the colorization process. To the best of our knowledge, this is one of the first attempts to incorporate textual conditioning in the colorization pipeline. To do so, we have proposed a novel deep network that takes two inputs (the grayscale image and the respective encoded text description) and tries to predict the relevant color gamut. As the respective textual descriptions contain color information of the objects present in the scene, the text encoding helps to improve the overall quality of the predicted colors. We have evaluated our proposed model using different metrics and found that it outperforms the state-of-the-art colorization algorithms both qualitatively and quantitatively.
The use of BERT, one of the most popular language models, has led to improvements in many Natural Language Processing (NLP) tasks. One such task is Named Entity Recognition (NER) i.e. automatic identification of named entities such as location, person, organization, etc. from a given text. It is also an important base step for many NLP tasks such as information extraction and argumentation mining. Even though there is much research done on NER using BERT and other popular language models, the same is not explored in detail when it comes to Legal NLP or Legal Tech. Legal NLP applies various NLP techniques such as sentence similarity or NER specifically on legal data. There are only a handful of models for NER tasks using BERT language models, however, none of these are aimed at legal documents in German. In this paper, we fine-tune a popular BERT language model trained on German data (German BERT) on a Legal Entity Recognition (LER) dataset. To make sure our model is not overfitting, we performed a stratified 10-fold cross-validation. The results we achieve by fine-tuning German BERT on the LER dataset outperform the BiLSTM-CRF+ model used by the authors of the same LER dataset. Finally, we make the model openly available via HuggingFace.
This paper describes the submission of UZH_CLyp for the SemEval 2023 Task 9 "Multilingual Tweet Intimacy Analysis". We achieved second-best results in all 10 languages according to the official Pearson's correlation regression evaluation measure. Our cross-lingual transfer learning approach explores the benefits of using a Head-First Fine-Tuning method (HeFiT) that first updates only the regression head parameters and then also updates the pre-trained transformer encoder parameters at a reduced learning rate. Additionally, we study the impact of using a small set of automatically generated examples (in our case, from ChatGPT) for low-resource settings where no human-labeled data is available. Our study shows that HeFiT stabilizes training and consistently improves results for pre-trained models that lack domain adaptation to tweets. Our study also shows a noticeable performance increase in cross-lingual learning when synthetic data is used, confirming the usefulness of current text generation systems to improve zero-shot baseline results. Finally, we examine how possible inconsistencies in the annotated data contribute to cross-lingual interference issues.
The global economy is increasingly dependent on knowledge workers to meet the needs of public and private organizations. While there is no single definition of knowledge work, organizations and industry groups still attempt to measure individuals' capability to engage in it. The most comprehensive assessment of capability readiness for professional knowledge workers is the Uniform CPA Examination developed by the American Institute of Certified Public Accountants (AICPA). In this paper, we experimentally evaluate OpenAI's `text-davinci-003` and prior versions of GPT on both a sample Regulation (REG) exam and an assessment of over 200 multiple-choice questions based on the AICPA Blueprints for legal, financial, accounting, technology, and ethical tasks. First, we find that `text-davinci-003` achieves a correct rate of 14.4% on a sample REG exam section, significantly underperforming human capabilities on quantitative reasoning in zero-shot prompts. Second, `text-davinci-003` appears to be approaching human-level performance on the Remembering & Understanding and Application skill levels in the Exam absent calculation. For best prompt and parameters, the model answers 57.6% of questions correctly, significantly better than the 25% guessing rate, and its top two answers are correct 82.1% of the time, indicating strong non-entailment. Finally, we find that recent generations of GPT-3 demonstrate material improvements on this assessment, rising from 30% for `text-davinci-001` to 57% for `text-davinci-003`. These findings strongly suggest that large language models have the potential to transform the quality and efficiency of future knowledge work.