Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userTuning Deep Active Learning for Semantic Role Labeling
ضبط التعلم النشط العميق لوضع العلامات الدلالية
327
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تم عرض التعلم النشط للحد من متطلبات التوضيحية للعديد من مهام معالجة اللغة الطبيعية، بما في ذلك وضع العلامات الدلالية (SRL).تنطوي SRL على وسيطة وسيطة تمتد من أجل المحتمل أن يحتمل أن يتسرب المتعددة في جملة، مما يجعل من الصعب تجميع القرارات العديدة في درجة واحدة لتحديد حالات جديدة للتعليق.في هذه الورقة، نطبق طريقتين للحصول على درجات تجميع عبر المسندات المتعددة من أجل اختيار جمل الاستعلام مع طريقتين تقدير اليقين النموذجي: استخدام مخرجات الشبكة العصبية واستخدام التعلم النشط في Bayesian في التسرب عن طريق الخلاف.قارنا هذه الأساليب بثلاثة أسماطية سلبية --- اختيار الجملة العشوائية، تحديد المستندات العشوائية بالكامل، واختيار الجمل مع معظم المتوقع --- وتحليل تأثير هذه الاستراتيجيات لديها على منحنى التعلم فيما يتعلق بتخفيض عدد المشروحالجمل والمسند لتحقيق الأداء العالي.
Active learning has been shown to reduce annotation requirements for numerous natural language processing tasks, including semantic role labeling (SRL). SRL involves labeling argument spans for potentially multiple predicates in a sentence, which makes it challenging to aggregate the numerous decisions into a single score for determining new instances to annotate. In this paper, we apply two ways of aggregating scores across multiple predicates in order to choose query sentences with two methods of estimating model certainty: using the neural network's outputs and using dropout-based Bayesian Active Learning by Disagreement. We compare these methods with three passive baselines --- random sentence selection, random whole-document selection, and selecting sentences with the most predicates --- and analyse the effect these strategies have on the learning curve with respect to reducing the number of annotated sentences and predicates to achieve high performance.
References used
https://aclanthology.org/
rate research
Read More
In this work, we empirically compare span extraction methods for the task of semantic role labeling (SRL). While recent progress incorporating pre-trained contextualized representations into neural encoders has greatly improved SRL F1 performance on
popular benchmarks, the potential costs and benefits of structured decoding in these models have become less clear. With extensive experiments on PropBank SRL datasets, we find that more structured decoding methods outperform BIO-tagging when using static (word type) embeddings across all experimental settings. However, when used in conjunction with pre-trained contextualized word representations, the benefits are diminished. We also experiment in cross-genre and cross-lingual settings and find similar trends. We further perform speed comparisons and provide analysis on the accuracy-efficiency trade-offs among different decoding methods.
Large-scale language models such as ELMo and BERT have pushed the horizon of what is possible in semantic role labeling (SRL), solving the out-of-vocabulary problem and enabling end-to-end systems, but they have also introduced significant biases. We
evaluate three SRL parsers on very simple transitive sentences with verbs usually associated with animate subjects and objects, such as, Mary babysat Tom'': a state-of-the-art parser based on BERT, an older parser based on GloVe, and an even older parser from before the days of word embeddings. When arguments are word forms predominantly used as person names, aligning with common sense expectations of animacy, the BERT-based parser is unsurprisingly superior; yet, with abstract or random nouns, the opposite picture emerges. We refer to this as common sense bias'' and present a challenge dataset for evaluating the extent to which parsers are sensitive to such a bias. Our code and challenge dataset are available here: github.com/coastalcph/comte
While FrameNet is widely regarded as a rich resource of semantics in natural language processing, a major criticism concerns its lack of coverage and the relative paucity of its labeled data compared to other commonly used lexical resources such as P
ropBank and VerbNet. This paper reports on a pilot study to address these gaps. We propose a data augmentation approach, which uses existing frame-specific annotation to automatically annotate other lexical units of the same frame which are unannotated. Our rule-based approach defines the notion of a **sister lexical unit** and generates frame-specific augmented data for training. We present experiments on frame-semantic role labeling which demonstrate the importance of this data augmentation: we obtain a large improvement to prior results on frame identification and argument identification for FrameNet, utilizing both full-text and lexicographic annotations under FrameNet. Our findings on data augmentation highlight the value of automatic resource creation for improved models in frame-semantic parsing.
Although recent developments in neural architectures and pre-trained representations have greatly increased state-of-the-art model performance on fully-supervised semantic role labeling (SRL), the task remains challenging for languages where supervis
ed SRL training data are not abundant. Cross-lingual learning can improve performance in this setting by transferring knowledge from high-resource languages to low-resource ones. Moreover, we hypothesize that annotations of syntactic dependencies can be leveraged to further facilitate cross-lingual transfer. In this work, we perform an empirical exploration of the helpfulness of syntactic supervision for crosslingual SRL within a simple multitask learning scheme. With comprehensive evaluations across ten languages (in addition to English) and three SRL benchmark datasets, including both dependency- and span-based SRL, we show the effectiveness of syntactic supervision in low-resource scenarios.
High-quality arguments are an essential part of decision-making. Automatically predicting the quality of an argument is a complex task that recently got much attention in argument mining. However, the annotation effort for this task is exceptionally
high. Therefore, we test uncertainty-based active learning (AL) methods on two popular argument-strength data sets to estimate whether sample-efficient learning can be enabled. Our extensive empirical evaluation shows that uncertainty-based acquisition functions can not surpass the accuracy reached with the random acquisition on these data sets.
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
