Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userImproved Latent Tree Induction with Distant Supervision via Span Constraints
تحسين تحريض الأشجار الكامنة مع الإشراف البعيد عبر قيود Span
397
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
لأكثر من ثلاثين عاما، قام الباحثون بتطوير وتحليل طرق لتحريض الأشجار الكامنة كهدوث لنهج التحليل النحوي غير المقترح. ومع ذلك، لا تزال الأنظمة الحديثة لا تؤدي بشكل جيد بما فيه الكفاية مقارنة بنظيراتهم الخاضعة للإشراف للحصول على أي استخدام عملي باسم التعليق الهيكلية للنص. في هذا العمل، نقدم تقنية تستخدم إشراف بعيد في شكل قيود سبعة (أي عبارة قوية) لتحسين الأداء في تحليل الدوائر الانتخابية غير المزدوجة. باستخدام عدد قليل نسبيا من قيود الأمان، يمكننا تحسين الإخراج بشكل كبير من Diora، وهو نظام تحليل غير مناسب بالفعل منافسة. بالمقارنة مع التعليق التوضيحي في شجرة التحليل الكامل، يمكن الحصول على قيود Span مع الحد الأدنى من الجهد، كما هو الحال مع معجم مشتق من ويكيبيديا، للعثور على مباريات نصية دقيقة. تجاربنا تظهر قيود الأمان على أساس الكيانات على تحسين تحليل الدوائر الانتخابية على بنك WSJ Penn TreeBank الإنجليزية بأكثر من 5 F1. علاوة على ذلك، تمتد طريقنا إلى أي مجال يتم فيه تحقيق قيود سبعة بسهولة، وكدراسة حالة نوضح فعاليتها من خلال تحليل النص الطبي الطبيعي من مجموعة بيانات الحرفية.
For over thirty years, researchers have developed and analyzed methods for latent tree induction as an approach for unsupervised syntactic parsing. Nonetheless, modern systems still do not perform well enough compared to their supervised counterparts to have any practical use as structural annotation of text. In this work, we present a technique that uses distant supervision in the form of span constraints (i.e. phrase bracketing) to improve performance in unsupervised constituency parsing. Using a relatively small number of span constraints we can substantially improve the output from DIORA, an already competitive unsupervised parsing system. Compared with full parse tree annotation, span constraints can be acquired with minimal effort, such as with a lexicon derived from Wikipedia, to find exact text matches. Our experiments show span constraints based on entities improves constituency parsing on English WSJ Penn Treebank by more than 5 F1. Furthermore, our method extends to any domain where span constraints are easily attainable, and as a case study we demonstrate its effectiveness by parsing biomedical text from the CRAFT dataset.
References used
https://aclanthology.org/
rate research
Read More
We present ReasonBert, a pre-training method that augments language models with the ability to reason over long-range relations and multiple, possibly hybrid contexts. Unlike existing pre-training methods that only harvest learning signals from local
contexts of naturally occurring texts, we propose a generalized notion of distant supervision to automatically connect multiple pieces of text and tables to create pre-training examples that require long-range reasoning. Different types of reasoning are simulated, including intersecting multiple pieces of evidence, bridging from one piece of evidence to another, and detecting unanswerable cases. We conduct a comprehensive evaluation on a variety of extractive question answering datasets ranging from single-hop to multi-hop and from text-only to table-only to hybrid that require various reasoning capabilities and show that ReasonBert achieves remarkable improvement over an array of strong baselines. Few-shot experiments further demonstrate that our pre-training method substantially improves sample efficiency.
In implicit discourse relation classification, we want to predict the relation between adjacent sentences in the absence of any overt discourse connectives. This is challenging even for humans, leading to shortage of annotated data, a fact that makes
the task even more difficult for supervised machine learning approaches. In the current study, we perform implicit discourse relation classification without relying on any labeled implicit relation. We sidestep the lack of data through explicitation of implicit relations to reduce the task to two sub-problems: language modeling and explicit discourse relation classification, a much easier problem. Our experimental results show that this method can even marginally outperform the state-of-the-art, in spite of being much simpler than alternative models of comparable performance. Moreover, we show that the achieved performance is robust across domains as suggested by the zero-shot experiments on a completely different domain. This indicates that recent advances in language modeling have made language models sufficiently good at capturing inter-sentence relations without the help of explicit discourse markers.
Scientific literature analysis needs fine-grained named entity recognition (NER) to provide a wide range of information for scientific discovery. For example, chemistry research needs to study dozens to hundreds of distinct, fine-grained entity types
, making consistent and accurate annotation difficult even for crowds of domain experts. On the other hand, domain-specific ontologies and knowledge bases (KBs) can be easily accessed, constructed, or integrated, which makes distant supervision realistic for fine-grained chemistry NER. In distant supervision, training labels are generated by matching mentions in a document with the concepts in the knowledge bases (KBs). However, this kind of KB-matching suffers from two major challenges: incomplete annotation and noisy annotation. We propose ChemNER, an ontology-guided, distantly-supervised method for fine-grained chemistry NER to tackle these challenges. It leverages the chemistry type ontology structure to generate distant labels with novel methods of flexible KB-matching and ontology-guided multi-type disambiguation. It significantly improves the distant label generation for the subsequent sequence labeling model training. We also provide an expert-labeled, chemistry NER dataset with 62 fine-grained chemistry types (e.g., chemical compounds and chemical reactions). Experimental results show that ChemNER is highly effective, outperforming substantially the state-of-the-art NER methods (with .25 absolute F1 score improvement).
This study was made at ALASSAD Hospital-TISHREEN University in-LATTAKIA
at the Department of Obestetrics and Gynecology in the period between 1/1/2013 and
1/1/2014. The number of patients the study was 190.Including140 cases have been holding
memb
rane stripping and 50 cases without membrane stripping.
According to Bishop –Scoring index we have estimated the uterine cervix in patients,
then a Membrane- Stripping was made.
Rate of response was 79.28% in cases of membrane stripping "then 54%in cases "
without membrane striping ". In most cases of response ,we need to do the membrane
stripping twice.Top of response was obtained when Bishop –Scoring index was between 4-
6 (Moderate ripening of the cervix).
Rate of Vaginal Delivery was 87.85% in cases of membrane stripping and 76%
without membrane stripping.
The complications were limited in the study group included:
1-Infection( 0.58%).
2-Bleeding 0.58%.
3-PROM 1.16%.
It means that Membrane Stripping was somehow safe.
State-of-the-art deep neural networks require large-scale labeled training data that is often expensive to obtain or not available for many tasks. Weak supervision in the form of domain-specific rules has been shown to be useful in such settings to a
utomatically generate weakly labeled training data. However, learning with weak rules is challenging due to their inherent heuristic and noisy nature. An additional challenge is rule coverage and overlap, where prior work on weak supervision only considers instances that are covered by weak rules, thus leaving valuable unlabeled data behind. In this work, we develop a weak supervision framework (ASTRA) that leverages all the available data for a given task. To this end, we leverage task-specific unlabeled data through self-training with a model (student) that considers contextualized representations and predicts pseudo-labels for instances that may not be covered by weak rules. We further develop a rule attention network (teacher) that learns how to aggregate student pseudo-labels with weak rule labels, conditioned on their fidelity and the underlying context of an instance. Finally, we construct a semi-supervised learning objective for end-to-end training with unlabeled data, domain-specific rules, and a small amount of labeled data. Extensive experiments on six benchmark datasets for text classification demonstrate the effectiveness of our approach with significant improvements over state-of-the-art baselines.
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
