Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userLearning from Executions for Semantic Parsing
التعلم من عمليات إعدام التحليل الدلالي
414
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تهدف التحليل الدلالي إلى ترجمة كلام اللغة الطبيعية (NL) على البرامج القابلة للتفسير بالآلة، والتي يمكن تنفيذها مقابل بيئة عالمية حقيقية. منذ فترة طويلة تم الاعتراف بالشروح باهظة الثمن لأزواج برنامج الكلام كعقوبة رئيسية لنشر النماذج العصبية المعاصرة لتطبيقات الحياة الحقيقية. في هذا العمل، نركز على مهمة التعلم شبه الإشراف حيث يتوفر كمية محدودة من البيانات المشروحة مع العديد من الكلمات غير المستقرة غير المسبقة. بناء على الملاحظة التي يجب أن تكون البرامج التي تتوافق مع الكلام NL قابلة للتنفيذ دائما، نقترح تشجيع المحلل المحلل لتوليد برامج قابلة للتنفيذ للكلمات غير المسبقة. نظرا لمسافة البحث الكبير للبرامج القابلة للتنفيذ، والأساليب التقليدية التي تستخدم شعاع البحث عن التقريب، مثل التدريب الذاتي والتدريب الهامشي الأعلى، لا تؤدي كذلك. بدلا من ذلك، نقترح مجموعة من أهداف التدريب الجديدة المستمدة من خلال الاقتراب من مشكلة التعلم من عمليات الإعدام من منظور التنظيم الخلفي. أهدافنا الجديدة تفوق الطرق التقليدية في الليلة الماضية والجيوقي، سد الفجوة بين التعليم شبه الإشرافه والإشراف.
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 major 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.
References used
https://aclanthology.org/
rate research
Read More
The importance of building semantic parsers which can be applied to new domains and generate programs unseen at training has long been acknowledged, and datasets testing out-of-domain performance are becoming increasingly available. However, little o
r no attention has been devoted to learning algorithms or objectives which promote domain generalization, with virtually all existing approaches relying on standard supervised learning. In this work, we use a meta-learning framework which targets zero-shot domain generalization for semantic parsing. We apply a model-agnostic training algorithm that simulates zero-shot parsing by constructing virtual train and test sets from disjoint domains. The learning objective capitalizes on the intuition that gradient steps that improve source-domain performance should also improve target-domain performance, thus encouraging a parser to generalize to unseen target domains. Experimental results on the (English) Spider and Chinese Spider datasets show that the meta-learning objective significantly boosts the performance of a baseline parser.
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 repre
senting 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.
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.
In practical applications of semantic parsing, we often want to rapidly change the behavior of the parser, such as enabling it to handle queries in a new domain, or changing its predictions on certain targeted queries. While we can introduce new trai
ning examples exhibiting the target behavior, a mechanism for enacting such behavior changes without expensive model re-training would be preferable. To this end, we propose ControllAble Semantic Parser via Exemplar Retrieval (CASPER). Given an input query, the parser retrieves related exemplars from a retrieval index, augments them to the query, and then applies a generative seq2seq model to produce an output parse. The exemplars act as a control mechanism over the generic generative model: by manipulating the retrieval index or how the augmented query is constructed, we can manipulate the behavior of the parser. On the MTOP dataset, in addition to achieving state-of-the-art on the standard setup, we show that CASPER can parse queries in a new domain, adapt the prediction toward the specified patterns, or adapt to new semantic schemas without having to further re-train the model.
AM dependency parsing is a method for neural semantic graph parsing that exploits the principle of compositionality. While AM dependency parsers have been shown to be fast and accurate across several graphbanks, they require explicit annotations of t
he compositional tree structures for training. In the past, these were obtained using complex graphbank-specific heuristics written by experts. Here we show how they can instead be trained directly on the graphs with a neural latent-variable model, drastically reducing the amount and complexity of manual heuristics. We demonstrate that our model picks up on several linguistic phenomena on its own and achieves comparable accuracy to supervised training, greatly facilitating the use of AM dependency parsing for new sembanks.
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
