2022-10-25 更新
Multi-Task Pre-Training of Modular Prompt for Few-Shot Learning
Authors:Tianxiang Sun, Zhengfu He, Qin Zhu, Xipeng Qiu, Xuanjing Huang
Prompt tuning is a parameter-efficient approach to adapting pre-trained language models to downstream tasks. Although prompt tuning has been shown to match the performance of full model tuning when training data is sufficient, it tends to struggle in few-shot learning settings. In this paper, we present Multi-task Pre-trained Modular Prompt (MP2) to boost prompt tuning for few-shot learning. MP2 is a set of combinable prompts pre-trained on 38 Chinese tasks. On downstream tasks, the pre-trained prompts are selectively activated and combined, leading to strong compositional generalization to unseen tasks. To bridge the gap between pre-training and fine-tuning, we formulate upstream and downstream tasks into a unified machine reading comprehension task. Extensive experiments under two learning paradigms, i.e., gradient descent and black-box tuning, show that MP2 significantly outperforms prompt tuning, full model tuning, and prior prompt pre-training methods in few-shot settings. In addition, we demonstrate that MP2 can achieve surprisingly fast and strong adaptation to downstream tasks by merely learning 8 parameters to combine the pre-trained modular prompts.
PDF Code and data are publicly available at https://github.com/Hzfinfdu/MPMP
点此查看论文截图
“Covid vaccine is against Covid but Oxford vaccine is made at Oxford!” Semantic Interpretation of Proper Noun Compounds
Authors:Keshav Kolluru, Gabriel Stanovsky, Mausam
Proper noun compounds, e.g., “Covid vaccine”, convey information in a succinct manner (a “Covid vaccine” is a “vaccine that immunizes against the Covid disease”). These are commonly used in short-form domains, such as news headlines, but are largely ignored in information-seeking applications. To address this limitation, we release a new manually annotated dataset, ProNCI, consisting of 22.5K proper noun compounds along with their free-form semantic interpretations. ProNCI is 60 times larger than prior noun compound datasets and also includes non-compositional examples, which have not been previously explored. We experiment with various neural models for automatically generating the semantic interpretations from proper noun compounds, ranging from few-shot prompting to supervised learning, with varying degrees of knowledge about the constituent nouns. We find that adding targeted knowledge, particularly about the common noun, results in performance gains of upto 2.8%. Finally, we integrate our model generated interpretations with an existing Open IE system and observe an 7.5% increase in yield at a precision of 85%. The dataset and code are available at https://github.com/dair-iitd/pronci.
PDF Accepted at EMNLP’22
点此查看论文截图
Discriminative Language Model as Semantic Consistency Scorer for Prompt-based Few-Shot Text Classification
Authors:Zhipeng Xie, Yahe Li
This paper proposes a novel prompt-based finetuning method (called DLM-SCS) for few-shot text classification by utilizing the discriminative language model ELECTRA that is pretrained to distinguish whether a token is original or generated. The underlying idea is that the prompt instantiated with the true label should have higher semantic consistency score than other prompts with false labels. Since a prompt usually consists of several components (or parts), its semantic consistency can be decomposed accordingly. The semantic consistency of each component is then computed by making use of the pretrained ELECTRA model, without introducing extra parameters. Extensive experiments have shown that our model outperforms several state-of-the-art prompt-based few-shot methods.
PDF 21 pages, 3 figures
点此查看论文截图
Feature Extractor Stacking for Cross-domain Few-shot Meta-learning
Authors:Hongyu Wang, Eibe Frank, Bernhard Pfahringer, Michael Mayo, Geoffrey Holmes
Cross-domain few-shot meta-learning (CDFSML) addresses learning problems where knowledge needs to be transferred from several source domains into an instance-scarce target domain with an explicitly different distribution. Recently published CDFSML methods generally construct a “universal model” that combines knowledge of multiple source domains into one backbone feature extractor. This enables efficient inference but necessitates re-computation of the backbone whenever a new source domain is added. Moreover, these methods often derive their universal model from a collection of backbones — normally one for each source domain — where these backbones are constrained to have the same architecture as the universal model. We propose feature extractor stacking (FES), a new CDFSML method for combining information from a collection of backbones that imposes no constraints on the backbones’ architecture and does not require re-computing a universal model when a backbone for a new source domain becomes available. We present the basic FES algorithm, which is inspired by the classic stacking approach to meta-learning, and also introduce two variants: convolutional FES (ConFES) and regularised FES (ReFES). Given a target-domain task, these algorithms fine-tune each backbone independently, use cross-validation to extract meta training data from the support set available for the task, and learn a simple linear meta-classifier from this data. We evaluate our FES methods on the well-known Meta-Dataset benchmark, targeting image classification with convolutional neural networks, and show that they can achieve state-of-the-art performance.
PDF
点此查看论文截图
Model ensemble instead of prompt fusion: a sample-specific knowledge transfer method for few-shot prompt tuning
Authors:Xiangyu Peng, Chen Xing, Prafulla Kumar Choubey, Chien-Sheng Wu, Caiming Xiong
Prompt tuning approaches, which learn task-specific soft prompts for a downstream task conditioning on frozen pre-trained models, have attracted growing interest due to its parameter efficiency. With large language models and sufficient training data, prompt tuning performs comparably to full-model tuning. However, with limited training samples in few-shot settings, prompt tuning fails to match the performance of full-model fine-tuning. In this work, we focus on improving the few-shot performance of prompt tuning by transferring knowledge from soft prompts of source tasks. Recognizing the good generalization capabilities of ensemble methods in low-data regime, we first experiment and show that a simple ensemble of model predictions based on different source prompts, outperforms existing multi-prompt knowledge transfer approaches such as source prompt fusion in the few-shot setting. Motivated by this observation, we further investigate model ensembles and propose Sample-specific Ensemble of Source Models (SESoM). SESoM learns to adjust the contribution of each source model for each target sample separately when ensembling source model outputs. Through this way, SESoM inherits the superior generalization of model ensemble approaches and simultaneously captures the sample-specific competence of each source prompt. We conduct experiments across a diverse set of eight NLP tasks using models of different scales (T5-{base, large, XL}) and find that SESoM consistently outperforms the existing models of the same as well as larger parametric scale by a large margin.
PDF
点此查看论文截图
A Task-aware Dual Similarity Network for Fine-grained Few-shot Learning
Authors:Yan Qi, Han Sun, Ningzhong Liu, Huiyu Zhou
The goal of fine-grained few-shot learning is to recognize sub-categories under the same super-category by learning few labeled samples. Most of the recent approaches adopt a single similarity measure, that is, global or local measure alone. However, for fine-grained images with high intra-class variance and low inter-class variance, exploring global invariant features and discriminative local details is quite essential. In this paper, we propose a Task-aware Dual Similarity Network(TDSNet), which applies global features and local patches to achieve better performance. Specifically, a local feature enhancement module is adopted to activate the features with strong discriminability. Besides, task-aware attention exploits the important patches among the entire task. Finally, both the class prototypes obtained by global features and discriminative local patches are employed for prediction. Extensive experiments on three fine-grained datasets demonstrate that the proposed TDSNet achieves competitive performance by comparing with other state-of-the-art algorithms.
PDF accepted by PRICAI2022, codes: https://github.com/qiyanhero/TDSNet
点此查看论文截图
Language Models of Code are Few-Shot Commonsense Learners
Authors:Aman Madaan, Shuyan Zhou, Uri Alon, Yiming Yang, Graham Neubig
We address the general task of structured commonsense reasoning: given a natural language input, the goal is to generate a graph such as an event — or a reasoning-graph. To employ large language models (LMs) for this task, existing approaches ``serialize’’ the output graph as a flat list of nodes and edges. Although feasible, these serialized graphs strongly deviate from the natural language corpora that LMs were pre-trained on, hindering LMs from generating them correctly. In this paper, we show that when we instead frame structured commonsense reasoning tasks as code generation tasks, pre-trained LMs of code are better structured commonsense reasoners than LMs of natural language, even when the downstream task does not involve source code at all. We demonstrate our approach across three diverse structured commonsense reasoning tasks. In all these natural language tasks, we show that using our approach, a code generation LM (CODEX) outperforms natural-LMs that are fine-tuned on the target task (e.g., T5) and other strong LMs such as GPT-3 in the few-shot setting.
PDF EMNLP 2022
点此查看论文截图
Language Model Pre-Training with Sparse Latent Typing
Authors:Liliang Ren, Zixuan Zhang, Han Wang, Clare R. Voss, Chengxiang Zhai, Heng Ji
Modern large-scale Pre-trained Language Models (PLMs) have achieved tremendous success on a wide range of downstream tasks. However, most of the LM pre-training objectives only focus on text reconstruction, but have not sought to learn latent-level interpretable representations of sentences. In this paper, we manage to push the language models to obtain a deeper understanding of sentences by proposing a new pre-training objective, Sparse Latent Typing, which enables the model to sparsely extract sentence-level keywords with diverse latent types. Experimental results show that our model is able to learn interpretable latent type categories in a self-supervised manner without using any external knowledge. Besides, the language model pre-trained with such an objective also significantly improves Information Extraction related downstream tasks in both supervised and few-shot settings. Our code is publicly available at: https://github.com/renll/SparseLT.
PDF
点此查看论文截图
Code4Struct: Code Generation for Few-Shot Structured Prediction from Natural Language
Authors:Xingyao Wang, Sha Li, Heng Ji
Large Language Model (LLM) trained on the mixture of text and code has demonstrated impressive capability in translating natural language (NL) into structured code. In this work, we propose Code4Struct to leverage such text-to-structure translation capability to tackle structured prediction tasks in NLP. For example, Event Argument Extraction (EAE) aims to convert text into event-argument structures that can be represented as a class object using code. This alignment between structures and code enables us to take advantage of Programming Language (PL) features such as inheritance and type annotation to introduce external knowledge or add constraints with ease. We exploit the analogy between PL and NLP problems, and, as a case study, we use Code4Struct to tackle the EAE task using code generation. We ask a LLM to generate code to instantiate an event class with predicted arguments given a NL sentence. Despite only using 50 training instances for each event type, Code4Struct is comparable to fully-supervised models trained on 4,202 event instances and, when given the same 50-shot data, outperforms current state-of-the-art (SOTA) by 20.8% absolute F1. When prompted with hierarchical event types implemented using inheritance, Code4Struct can predict arguments for low-resource event types using 10-shot training instances from its sibling event type and outperforms zero-shot baseline by 12% absolute F1.
PDF
点此查看论文截图
Simple Questions Generate Named Entity Recognition Datasets
Authors:Hyunjae Kim, Jaehyo Yoo, Seunghyun Yoon, Jinhyuk Lee, Jaewoo Kang
Recent named entity recognition (NER) models often rely on human-annotated datasets, requiring the significant engagement of professional knowledge on the target domain and entities. This research introduces an ask-to-generate approach that automatically generates NER datasets by asking questions in simple natural language to an open-domain question answering system (e.g., “Which disease?”). Despite using fewer in-domain resources, our models, solely trained on the generated datasets, largely outperform strong low-resource models by an average F1 score of 19.5 for six popular NER benchmarks. Furthermore, our models provide competitive performance with rich-resource models that additionally leverage in-domain dictionaries provided by domain experts. In few-shot NER, we outperform the previous best model by an F1 score of 5.2 on three benchmarks and achieve new state-of-the-art performance.
PDF EMNLP 2022. Code and datasets available at https://github.com/dmis-lab/GeNER
点此查看论文截图
Schema-aware Reference as Prompt Improves Data-Efficient Relational Triple and Event Extraction
Authors:Yunzhi Yao, Shengyu Mao, Xiang Chen, Ningyu Zhang, Shumin Deng, Huajun Chen
Information Extraction, which aims to extract structural relational triple or event from unstructured texts, often suffers from data scarcity issues. With the development of pre-trained language models, many prompt-based approaches to data-efficient information extraction have been proposed and achieved impressive performance. However, existing prompt learning methods for information extraction are still susceptible to several potential limitations: (i) semantic gap between natural language and output structure knowledge with pre-defined schema; (ii) representation learning with locally individual instances limits the performance given the insufficient features. In this paper, we propose a novel approach of schema-aware Reference As Prompt (RAP), which dynamically leverage schema and knowledge inherited from global (few-shot) training data for each sample. Specifically, we propose a schema-aware reference store, which unifies symbolic schema and relevant textual instances. Then, we employ a dynamic reference integration module to retrieve pertinent knowledge from the datastore as prompts during training and inference. Experimental results demonstrate that RAP can be plugged into various existing models and outperforms baselines in low-resource settings on four datasets of relational triple extraction and event extraction. In addition, we provide comprehensive empirical ablations and case analysis regarding different types and scales of knowledge in order to better understand the mechanisms of RAP. Code is available in https://github.com/zjunlp/RAP.
PDF Work in progress
点此查看论文截图
Few-shot Learning with Multilingual Language Models
Authors:Xi Victoria Lin, Todor Mihaylov, Mikel Artetxe, Tianlu Wang, Shuohui Chen, Daniel Simig, Myle Ott, Naman Goyal, Shruti Bhosale, Jingfei Du, Ramakanth Pasunuru, Sam Shleifer, Punit Singh Koura, Vishrav Chaudhary, Brian O’Horo, Jeff Wang, Luke Zettlemoyer, Zornitsa Kozareva, Mona Diab, Veselin Stoyanov, Xian Li
Large-scale generative language models such as GPT-3 are competitive few-shot learners. While these models are known to be able to jointly represent many different languages, their training data is dominated by English, potentially limiting their cross-lingual generalization. In this work, we train multilingual generative language models on a corpus covering a diverse set of languages, and study their few- and zero-shot learning capabilities in a wide range of tasks. Our largest model with 7.5 billion parameters sets new state of the art in few-shot learning in more than 20 representative languages, outperforming GPT-3 of comparable size in multilingual commonsense reasoning (with +7.4% absolute accuracy improvement in 0-shot settings and +9.4% in 4-shot settings) and natural language inference (+5.4% in each of 0-shot and 4-shot settings). On the FLORES-101 machine translation benchmark, our model outperforms GPT-3 on 171 out of 182 directions with 32 training examples, while surpassing the official supervised baseline in 45 directions. We conduct an in-depth analysis of different multilingual prompting approaches, showing in particular that strong few-shot learning performance across languages can be achieved via cross-lingual transfer through both templates and demonstration examples. Finally, we evaluate our models in social value tasks such as hate speech detection in five languages and find it has limitations similar to comparable sized GPT-3 models.
PDF Accepted to EMNLP 2022; 34 pages
点此查看论文截图
Contrastive Representation Learning for Gaze Estimation
Authors:Swati Jindal, Roberto Manduchi
Self-supervised learning (SSL) has become prevalent for learning representations in computer vision. Notably, SSL exploits contrastive learning to encourage visual representations to be invariant under various image transformations. The task of gaze estimation, on the other hand, demands not just invariance to various appearances but also equivariance to the geometric transformations. In this work, we propose a simple contrastive representation learning framework for gaze estimation, named Gaze Contrastive Learning (GazeCLR). GazeCLR exploits multi-view data to promote equivariance and relies on selected data augmentation techniques that do not alter gaze directions for invariance learning. Our experiments demonstrate the effectiveness of GazeCLR for several settings of the gaze estimation task. Particularly, our results show that GazeCLR improves the performance of cross-domain gaze estimation and yields as high as 17.2% relative improvement. Moreover, the GazeCLR framework is competitive with state-of-the-art representation learning methods for few-shot evaluation. The code and pre-trained models are available at https://github.com/jswati31/gazeclr.
PDF Accepted at NeurIPS 2022 Gaze Meets ML Workshop (Spotlight)
点此查看论文截图
That’s the Wrong Lung! Evaluating and Improving the Interpretability of Unsupervised Multimodal Encoders for Medical Data
Authors:Denis Jered McInerney, Geoffrey Young, Jan-Willem van de Meent, Byron C. Wallace
Pretraining multimodal models on Electronic Health Records (EHRs) provides a means of learning representations that can transfer to downstream tasks with minimal supervision. Recent multimodal models induce soft local alignments between image regions and sentences. This is of particular interest in the medical domain, where alignments might highlight regions in an image relevant to specific phenomena described in free-text. While past work has suggested that attention “heatmaps” can be interpreted in this manner, there has been little evaluation of such alignments. We compare alignments from a state-of-the-art multimodal (image and text) model for EHR with human annotations that link image regions to sentences. Our main finding is that the text has an often weak or unintuitive influence on attention; alignments do not consistently reflect basic anatomical information. Moreover, synthetic modifications — such as substituting “left” for “right” — do not substantially influence highlights. Simple techniques such as allowing the model to opt out of attending to the image and few-shot finetuning show promise in terms of their ability to improve alignments with very little or no supervision. We make our code and checkpoints open-source.
PDF
点此查看论文截图
An Empirical Revisiting of Linguistic Knowledge Fusion in Language Understanding Tasks
Authors:Changlong Yu, Tianyi Xiao, Lingpeng Kong, Yangqiu Song, Wilfred Ng
Though linguistic knowledge emerges during large-scale language model pretraining, recent work attempt to explicitly incorporate human-defined linguistic priors into task-specific fine-tuning. Infusing language models with syntactic or semantic knowledge from parsers has shown improvements on many language understanding tasks. To further investigate the effectiveness of structural linguistic priors, we conduct empirical study of replacing parsed graphs or trees with trivial ones (rarely carrying linguistic knowledge e.g., balanced tree) for tasks in the GLUE benchmark. Encoding with trivial graphs achieves competitive or even better performance in fully-supervised and few-shot settings. It reveals that the gains might not be significantly attributed to explicit linguistic priors but rather to more feature interactions brought by fusion layers. Hence we call for attention to using trivial graphs as necessary baselines to design advanced knowledge fusion methods in the future.
PDF EMNLP 2022 Main Conference
点此查看论文截图