Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userComparing Span Extraction Methods for Semantic Role Labeling
مقارنة أساليب استخراج Span للحصول على وضع العلامات الدلالية
441
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
في هذا العمل، قارننا تجريبيا أساليب استخراج الفصول لمهمة الدور الدلالي (SRL).في حين أن التقدم الأخير الذي يشتمل على تمثيلات محكومة مدربة مسبقا في الترميز العصبية قد حسن بشكل كبير أداء SRL F1 بشأن المعايير الشعبية، فإن التكاليف المهمة وفوائد فك التشفير المنظم في هذه النماذج أصبحت أقل وضوحا.مع تجارب واسعة النطاق على مجموعات بيانات Propbank SRL، نجد أن طرق فك التشفير أكثر تنظيما تفوق العلامات الحيوية عند استخدام Asceddings ثابت (نوع الكلمات) عبر جميع الإعدادات التجريبية.ومع ذلك، عند استخدامها جنبا إلى جنب مع تمثيلات الكلمات السياقية المدربة مسبقا، يتم تقلص الفوائد.نقوم أيضا بتجربة الإعدادات عبر النوع والإعدادات عبر اللغات والعثور على اتجاهات مماثلة.ونحن نؤدي كذلك إلى مقارنات السرعة وتوفير التحليل حول مفاضات الكفاءة الدقة بين أساليب فك التشفير المختلفة.
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.
References used
https://aclanthology.org/
rate research
Read More
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.
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 mak
es 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.
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
Multilingual and cross-lingual Semantic Role Labeling (SRL) have recently garnered increasing attention as multilingual text representation techniques have become more effective and widely available. While recent work has attained growing success, re
sults on gold multilingual benchmarks are still not easily comparable across languages, making it difficult to grasp where we stand. For example, in CoNLL-2009, the standard benchmark for multilingual SRL, language-to-language comparisons are affected by the fact that each language has its own dataset which differs from the others in size, domains, sets of labels and annotation guidelines. In this paper, we address this issue and propose UniteD-SRL, a new benchmark for multilingual and cross-lingual, span- and dependency-based SRL. UniteD-SRL provides expert-curated parallel annotations using a common predicate-argument structure inventory, allowing direct comparisons across languages and encouraging studies on cross-lingual transfer in SRL. We release UniteD-SRL v1.0 at https://github.com/SapienzaNLP/united-srl.
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
