Large pre-trained language models (LMs) such as GPT-3 have acquired a surprising ability to perform zero-shot learning. For example, to classify sentiment without any training examples, we can "prompt" the LM with the review and the label description "Does the user like this movie?", and ask whether the next word is "yes" or "no". However, the next word prediction training objective is still misaligned with the target zero-shot learning objective. To address this weakness, we propose meta-tuning, which directly optimizes the zero-shot learning objective by fine-tuning pre-trained language models on a collection of datasets. We focus on classification tasks, and construct the meta-dataset by aggregating 43 existing datasets and annotating 441 label descriptions in a question-answering (QA) format. When evaluated on unseen tasks, meta-tuned models outperform a same-sized QA model and the previous SOTA zero-shot learning system based on natural language inference. Additionally, increasing parameter count from 220M to 770M improves AUC-ROC scores by 6.3%, and we forecast that even larger models would perform better. Therefore, measuring zero-shot learning performance on language models out-of-the-box might underestimate their true potential, and community-wide efforts on aggregating datasets and unifying their formats can help build models that answer prompts better.
Diabetica: Adapting Large Language Model to Enhance Multiple Medical Tasks in Diabetes Care and Management
Qing Yuan Research Institute, SEIEE, Shanghai Jiao Tong University（上海交通大学电子信息与电气工程学院清源研究院）；Zhongshan Hospital, Fudan University（复旦大学附属中山医院）；Qingpu Branch of Zhongshan Hospital, Affiliated to Fudan University（复旦大学附属中山医院青浦分院）
New York University（纽约大学）；EleutherAI；Microsoft Azure AI（微软Azure人工智能部门）
Fine-tuning large language models for different tasks can be costly and inefficient, and even methods that reduce the number of tuned parameters still require full gradient-based optimization. We propose HyperTuning, a novel approach to model adaptation that uses a hypermodel to generate task-specific parameters for a fixed downstream model. We demonstrate a simple setup for hypertuning with HyperT5, a T5-based hypermodel that produces soft prefixes or LoRA parameters for a frozen T5 model from few-shot examples. We train HyperT5 in two stages: first, hyperpretraining with a modified condition…
Prompt tuning (PT) is an effective approach to adapting pre-trained language models to downstream tasks. Without a good initialization, prompt tuning doesn't perform well under few-shot settings. So pre-trained prompt tuning (PPT) is proposed to initialize prompts by leveraging pre-training data. We propose MetaPT (Meta-learned Prompt Tuning) to further improve PPT's initialization by considering latent structure within the pre-training data. Specifically, we introduce the structure by first clustering pre-training data into different auxiliary tasks with unsupervised methods. Then we use thes…
Don't Erase, Inform! Detecting and Contextualizing Harmful Language in Cultural Heritage Collections
National Technical University of Athens（希腊国家技术大学）；DFF - Deutsches Filminstitut & Filmmuseum（德国电影学院及电影博物馆）；Europeana Foundation（欧洲ana基金会）；Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）
The performance of automatic speech recognition systems can be improved by adapting an acoustic model to compensate for the mismatch between training and testing conditions, for example by adapting to unseen speakers. The success of speaker adaptation methods relies on selecting weights that are suitable for adaptation and using good adaptation schedules to update these weights in order not to overfit to the adaptation data. In this paper we investigate a principled way of adapting all the weights of the acoustic model using a meta-learning. We show that the meta-learner can learn to perform s…
Albeit the universal representational power of pre-trained language models, adapting them onto a specific NLP task still requires a considerably large amount of labeled data. Effective task fine-tuning meets challenges when only a few labeled examples are present for the task. In this paper, we aim to the address of the problem of few shot task learning by exploiting and transferring from a different task which admits a related but disparate label space. Specifically, we devise a label transfer network (LTN) to transform the labels from source task to the target task of interest for training. …
Booz Allen Hamilton（博思艾伦咨询公司）；British Library（大英图书馆）；EleutherAI；Hugging Face；Inria（法国国家信息与自动化研究所）；University of Washington（华盛顿大学）；University of Western Australia（西澳大利亚大学）；University of the Basque Country（巴斯克大学）；KFUPM（法赫德国王石油矿产大学）
In recent years, large-scale data collection efforts have prioritized the amount of data collected in order to improve the modeling capabilities of large language models. This prioritization, however, has resulted in concerns with respect to the rights of data subjects represented in data collections, particularly when considering the difficulty in interrogating these collections due to insufficient documentation and tools for analysis. Mindful of these pitfalls, we present our methodology for a documentation-first, human-centered data collection project as part of the BigScience initiative. W…
Natural language understanding (NLU) has made massive progress driven by large benchmarks, but benchmarks often leave a long tail of infrequent phenomena underrepresented. We reflect on the question: have transfer learning methods sufficiently addressed the poor performance of benchmark-trained models on the long tail? We conceptualize the long tail using macro-level dimensions (e.g., underrepresented genres, topics, etc.), and perform a qualitative meta-analysis of 100 representative papers on transfer learning research for NLU. Our analysis asks three questions: (i) Which long tail dimension…
University of Cambridge（剑桥大学）；University of California, Merced（加利福尼亚大学默塞德分校）
Natural language processing techniques are increasingly applied to identify social trends and predict behavior based on large text collections. Existing methods typically rely on surface lexical and syntactic information. Yet, research in psychology shows that patterns of human conceptualisation, such as metaphorical framing, are reliable predictors of human expectations and decisions. In this paper, we present a method to learn patterns of metaphorical framing from large text collections, using statistical techniques. We apply the method to data in three different languages and evaluate the i…
Off-the-shelf natural language processing software performs poorly when parsing patent claims owing to their use of irregular language relative to the corpora built from news articles and the web typically utilized to train this software. Stopping short of the extensive and expensive process of accumulating a large enough dataset to completely retrain parsers for patent claims, a method of adapting existing natural language processing software towards patent claims via forced part of speech tag correction is proposed. An Amazon Mechanical Turk collection campaign organized to generate a public…
Recent works suggest that transformer models are capable of multi-tasking on diverse NLP tasks and adapting to new tasks efficiently. However, the potential of these multi-task models may be limited as they use the same set of parameters for all tasks. In contrast, humans tackle tasks in a more flexible way, by making proper presumptions on what skills and knowledge are relevant and executing only the necessary computations. Inspired by this, we propose to use task-level mixture-of-expert models, which has a collection of transformer layers (i.e., experts) and a router component that chooses f…
École polytechnique fédérale de Lausanne (EPFL)（洛桑联邦理工学院）；Tsinghua University（清华大学）；Hangzhou Dianzi University（杭州电子科技大学）
Natural language generation (NLG) is an essential component of task-oriented dialogue systems. Despite the recent success of neural approaches for NLG, they are typically developed for particular domains with rich annotated training examples. In this paper, we study NLG in a low-resource setting to generate sentences in new scenarios with handful training examples. We formulate the problem from a meta-learning perspective, and propose a generalized optimization-based approach (Meta-NLG) based on the well-recognized model-agnostic meta-learning (MAML) algorithm. Meta-NLG defines a set of meta t…
Neural Language Models (NLM), when trained and evaluated with context spanning multiple utterances, have been shown to consistently outperform both conventional n-gram language models and NLMs that use limited context. In this paper, we investigate various techniques to incorporate turn based context history into both recurrent (LSTM) and Transformer-XL based NLMs. For recurrent based NLMs, we explore context carry over mechanism and feature based augmentation, where we incorporate other forms of contextual information such as bot response and system dialogue acts as classified by a Natural La…
