Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userEffectiveness of Pre-training for Few-shot Intent Classification
فعالية التدريب المسبق لتصنيف عدد قليل من الطلقات
385
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تحقق هذه الورقة في فعالية التدريب المسبق لتصنيف قلة الطابع القليلة.في حين أن النماذج الحالية عادة ما تكون هناك مزيد من النماذج اللغوية السابقة لما قبل التدريب مثل Bert على كمية شاسعة من Corpus غير المسبق، فإننا نجد أنها فعالة للغاية وكفاءة ببساطة Brite Tune Bert مع مجموعة صغيرة من الكلام المسمى من مجموعات البيانات العامة.على وجه التحديد، تقوم Brtt Tuning Berting ذات الصقل مع ما يقرب من 1000 من البيانات المسمى نموذجا مدربا مسبقا - Intentbert، والذي يمكن أن يتجاوز بسهولة أداء النماذج المدربة مسبقا الحالية للحصول على تصنيف قلة الطابع على النطاقات الجديدة مع دلائل مختلفة للغاية.تؤكد فعالية Intentbert المرتفعة من جدوى وعملية الكشف عن القلة القليلة، وتقترح قدرة تعميمها العالية عبر المجالات المختلفة أن مهام تصنيف النوايا قد تشارك هيكل أساسي مماثل، والتي يمكن تعلمها بكفاءة من مجموعة صغيرة من البيانات المسمى.يمكن العثور على شفرة المصدر في https://github.com/hdzhang-code/intentbert.
This paper investigates the effectiveness of pre-training for few-shot intent classification. While existing paradigms commonly further pre-train language models such as BERT on a vast amount of unlabeled corpus, we find it highly effective and efficient to simply fine-tune BERT with a small set of labeled utterances from public datasets. Specifically, fine-tuning BERT with roughly 1,000 labeled data yields a pre-trained model -- IntentBERT, which can easily surpass the performance of existing pre-trained models for few-shot intent classification on novel domains with very different semantics. The high effectiveness of IntentBERT confirms the feasibility and practicality of few-shot intent detection, and its high generalization ability across different domains suggests that intent classification tasks may share a similar underlying structure, which can be efficiently learned from a small set of labeled data. The source code can be found at https://github.com/hdzhang-code/IntentBERT.
References used
https://aclanthology.org/
rate research
Read More
Intent classification (IC) and slot filling (SF) are critical building blocks in task-oriented dialogue systems. These two tasks are closely-related and can flourish each other. Since only a few utterances can be utilized for identifying fast-emergin
g new intents and slots, data scarcity issue often occurs when implementing IC and SF. However, few IC/SF models perform well when the number of training samples per class is quite small. In this paper, we propose a novel explicit-joint and supervised-contrastive learning framework for few-shot intent classification and slot filling. Its highlights are as follows. (i) The model extracts intent and slot representations via bidirectional interactions, and extends prototypical network to achieve explicit-joint learning, which guarantees that IC and SF tasks can mutually reinforce each other. (ii) The model integrates with supervised contrastive learning, which ensures that samples from same class are pulled together and samples from different classes are pushed apart. In addition, the model follows a not common but practical way to construct the episode, which gets rid of the traditional setting with fixed way and shot, and allows for unbalanced datasets. Extensive experiments on three public datasets show that our model can achieve promising performance.
Natural Language Processing (NLP) is increasingly relying on general end-to-end systems that need to handle many different linguistic phenomena and nuances. For example, a Natural Language Inference (NLI) system has to recognize sentiment, handle num
bers, perform coreference, etc. Our solutions to complex problems are still far from perfect, so it is important to create systems that can learn to correct mistakes quickly, incrementally, and with little training data. In this work, we propose a continual few-shot learning (CFL) task, in which a system is challenged with a difficult phenomenon and asked to learn to correct mistakes with only a few (10 to 15) training examples. To this end, we first create benchmarks based on previously annotated data: two NLI (ANLI and SNLI) and one sentiment analysis (IMDB) datasets. Next, we present various baselines from diverse paradigms (e.g., memory-aware synapses and Prototypical networks) and compare them on few-shot learning and continual few-shot learning setups. Our contributions are in creating a benchmark suite and evaluation protocol for continual few-shot learning on the text classification tasks, and making several interesting observations on the behavior of similarity-based methods. We hope that our work serves as a useful starting point for future work on this important topic.
Few-shot learning arises in important practical scenarios, such as when a natural language understanding system needs to learn new semantic labels for an emerging, resource-scarce domain. In this paper, we explore retrieval-based methods for intent c
lassification and slot filling tasks in few-shot settings. Retrieval-based methods make predictions based on labeled examples in the retrieval index that are similar to the input, and thus can adapt to new domains simply by changing the index without having to retrain the model. However, it is non-trivial to apply such methods on tasks with a complex label space like slot filling. To this end, we propose a span-level retrieval method that learns similar contextualized representations for spans with the same label via a novel batch-softmax objective. At inference time, we use the labels of the retrieved spans to construct the final structure with the highest aggregated score. Our method outperforms previous systems in various few-shot settings on the CLINC and SNIPS benchmarks.
In this work, we focus on a more challenging few-shot intent detection scenario where many intents are fine-grained and semantically similar. We present a simple yet effective few-shot intent detection schema via contrastive pre-training and fine-tun
ing. Specifically, we first conduct self-supervised contrastive pre-training on collected intent datasets, which implicitly learns to discriminate semantically similar utterances without using any labels. We then perform few-shot intent detection together with supervised contrastive learning, which explicitly pulls utterances from the same intent closer and pushes utterances across different intents farther. Experimental results show that our proposed method achieves state-of-the-art performance on three challenging intent detection datasets under 5-shot and 10-shot settings.
Meta learning aims to optimize the model's capability to generalize to new tasks and domains. Lacking a data-efficient way to create meta training tasks has prevented the application of meta-learning to the real-world few shot learning scenarios. Rec
ent studies have proposed unsupervised approaches to create meta-training tasks from unlabeled data for free, e.g., the SMLMT method (Bansal et al., 2020a) constructs unsupervised multi-class classification tasks from the unlabeled text by randomly masking words in the sentence and let the meta learner choose which word to fill in the blank. This study proposes a semi-supervised meta-learning approach that incorporates both the representation power of large pre-trained language models and the generalization capability of prototypical networks enhanced by SMLMT. The semi-supervised meta training approach avoids overfitting prototypical networks on a small number of labeled training examples and quickly learns cross-domain task-specific representation only from a few supporting examples. By incorporating SMLMT with prototypical networks, the meta learner generalizes better to unseen domains and gains higher accuracy on out-of-scope examples without the heavy lifting of pre-training. We observe significant improvement in few-shot generalization after training only a few epochs on the intent classification tasks evaluated in a multi-domain setting.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
