Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userFew-Shot Novel Concept Learning for Semantic Parsing
عدد قليل من الرواية مفهوم التعلم لتحليل الدلالي
214
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
البشر قادرون على تعلم مفاهيم جديدة من أمثلة قليلة جدا؛ في المقابل، تحتاج خوارزميات التعلم في الآلة الحديثة عادة الآلاف من الأمثلة للقيام بذلك. في هذه الورقة، نقترح خوارزمية لتعلم مفاهيم جديدة من خلال تمثيلها كبرامج بشأن المفاهيم القائمة. وبهذه الطريقة، تعتبر مشكلة التعلم المفهوم بشكل طبيعي مشكلة تخليق برنامجا وتخصصت خوارزميةنا من بعض الأمثلة لتوليف برنامج يمثل مفهوم الرواية. بالإضافة إلى ذلك، نقوم بإجراء تحليل نظري لنهجنا للقضية التي يكون فيها البرنامج الذي يحدد مفهوم الرواية على تلك الموجودة خالية من السياق. نظهر أنه بالنظر إلى المحلل المحلل القائم على النحو المستفاد وقاعدة الإنتاج الجديدة، يمكننا زيادة المحلل بمحلل مع قاعدة الإنتاج بطريقة تعميم. نقيم نهجنا من خلال مفاهيم التعلم في مجال التحليل الدلالي الممتد إلى إعداد تعلم مفهوم الرواية القليلة، مما يظهر أن نهجنا يتفوق بشكل كبير على المحللين الدلالي العصبي المنتهي.
Humans are capable of learning novel concepts from very few examples; in contrast, state-of-the-art machine learning algorithms typically need thousands of examples to do so. In this paper, we propose an algorithm for learning novel concepts by representing them as programs over existing concepts. This way the concept learning problem is naturally a program synthesis problem and our algorithm learns from a few examples to synthesize a program representing the novel concept. In addition, we perform a theoretical analysis of our approach for the case where the program defining the novel concept over existing ones is context-free. We show that given a learned grammar-based parser and a novel production rule, we can augment the parser with the production rule in a way that provably generalizes. We evaluate our approach by learning concepts in the semantic parsing domain extended to the few-shot novel concept learning setting, showing that our approach significantly outperforms end-to-end neural semantic parsers.
References used
https://aclanthology.org/
rate research
Read More
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.
The ability to continuously expand knowledge over time and utilize it to rapidly generalize to new tasks is a key feature of human linguistic intelligence. Existing models that pursue rapid generalization to new tasks (e.g., few-shot learning methods
), however, are mostly trained in a single shot on fixed datasets, unable to dynamically expand their knowledge; while continual learning algorithms are not specifically designed for rapid generalization. We present a new learning setup, Continual Learning of Few-Shot Learners (CLIF), to address challenges of both learning settings in a unified setup. CLIF assumes a model learns from a sequence of diverse NLP tasks arriving sequentially, accumulating knowledge for improved generalization to new tasks, while also retaining performance on the tasks learned earlier. We examine how the generalization ability is affected in the continual learning setup, evaluate a number of continual learning algorithms, and propose a novel regularized adapter generation approach. We find that catastrophic forgetting affects generalization ability to a lesser degree than performance on seen tasks; while continual learning algorithms can still bring considerable benefit to the generalization ability.
Semantic parsing aims at translating natural language (NL) utterances onto machine-interpretable programs, which can be executed against a real-world environment. The expensive annotation of utterance-program pairs has long been acknowledged as a maj
or bottleneck for the deployment of contemporary neural models to real-life applications. In this work, we focus on the task of semi-supervised learning where a limited amount of annotated data is available together with many unlabeled NL utterances. Based on the observation that programs which correspond to NL utterances should always be executable, we propose to encourage a parser to generate executable programs for unlabeled utterances. Due to the large search space of executable programs, conventional methods that use beam-search for approximation, such as self-training and top-k marginal likelihood training, do not perform as well. Instead, we propose a set of new training objectives that are derived by approaching the problem of learning from executions from the posterior regularization perspective. Our new objectives outperform conventional methods on Overnight and GeoQuery, bridging the gap between semi-supervised and supervised learning.
Synthesizing data for semantic parsing has gained increasing attention recently. However, most methods require handcrafted (high-precision) rules in their generative process, hindering the exploration of diverse unseen data. In this work, we propose
a generative model which features a (non-neural) PCFG that models the composition of programs (e.g., SQL), and a BART-based translation model that maps a program to an utterance. Due to the simplicity of PCFG and pre-trained BART, our generative model can be efficiently learned from existing data at hand. Moreover, explicitly modeling compositions using PCFG leads to better exploration of unseen programs, thus generate more diverse data. We evaluate our method in both in-domain and out-of-domain settings of text-to-SQL parsing on the standard benchmarks of GeoQuery and Spider, respectively. Our empirical results show that the synthesized data generated from our model can substantially help a semantic parser achieve better compositional and domain generalization.
Meta-learning has recently been proposed to learn models and algorithms that can generalize from a handful of examples. However, applications to structured prediction and textual tasks pose challenges for meta-learning algorithms. In this paper, we a
pply two meta-learning algorithms, Prototypical Networks and Reptile, to few-shot Named Entity Recognition (NER), including a method for incorporating language model pre-training and Conditional Random Fields (CRF). We propose a task generation scheme for converting classical NER datasets into the few-shot setting, for both training and evaluation. Using three public datasets, we show these meta-learning algorithms outperform a reasonable fine-tuned BERT baseline. In addition, we propose a novel combination of Prototypical Networks and Reptile.
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
