Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userOn the Relation between Syntactic Divergence and Zero-Shot Performance
فيما يتعلق بالعلاقة بين الاختلاف النحوي والأداء الصفر
164
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
نستكشف الصلة بين المدى الذي يتم فيه الحفاظ على العلاقات النحوية في الترجمة وسهولة إنشاء شجرة تحليل بشكل صحيح في إعداد طلقة صفرية. في حين أن العمل السابق يشير إلى مثل هذه العلاقة، إلا أنه يميل إلى التركيز على مستوى الكلي وليس على مستوى الحواف الفردية --- فجوة نهدف إلى معالجتها. كحالة اختبار، نقوم بنقل التبعيات العالمية (UD) من الإنجليزية إلى مجموعة متنوعة من اللغات وإجراء مجموعتين من التجارب. في واحد، نقوم بتحليل الأداء الصفر بالرصاص بناء على مدى الحفاظ على حواف مصدر اللغة الإنجليزية في الترجمة. في مكان آخر، نطبق ثلاث تحولات بدوائية بمرحلة مغلفة إلى UD، مما يخلق المزيد من الإصدارات المستقرة عبر الأغراض، وتقييم إمتصاصها الصفرية بالرصاص. من أجل مقارنة أداء التحليل عبر مخططات مختلفة، نقوم بإجراء تقييم خارجي على المهمة المصب المتمثلة في استخراج العلاقات عبر اللغات المتبادلة باستخدام مجموعة فرعية من المعيار الإنجليزي القياسي المترجم إلى الروسية والكورية. في كلتا المجموعتين من التجارب، تشير نتائجنا إلى علاقة قوية بين الاستقرار عبر اللغات وأداء تحليل اللقطة الصفرية.
We explore the link between the extent to which syntactic relations are preserved in translation and the ease of correctly constructing a parse tree in a zero-shot setting. While previous work suggests such a relation, it tends to focus on the macro level and not on the level of individual edges---a gap we aim to address. As a test case, we take the transfer of Universal Dependencies (UD) parsing from English to a diverse set of languages and conduct two sets of experiments. In one, we analyze zero-shot performance based on the extent to which English source edges are preserved in translation. In another, we apply three linguistically motivated transformations to UD, creating more cross-lingually stable versions of it, and assess their zero-shot parsability. In order to compare parsing performance across different schemes, we perform extrinsic evaluation on the downstream task of cross-lingual relation extraction (RE) using a subset of a standard English RE benchmark translated to Russian and Korean. In both sets of experiments, our results suggest a strong relation between cross-lingual stability and zero-shot parsing performance.
References used
https://aclanthology.org/
rate research
Read More
Developing mechanisms that flexibly adapt dialog systems to unseen tasks and domains is a major challenge in dialog research. Neural models implicitly memorize task-specific dialog policies from the training data. We posit that this implicit memoriza
tion has precluded zero-shot transfer learning. To this end, we leverage the schema-guided paradigm, wherein the task-specific dialog policy is explicitly provided to the model. We introduce the Schema Attention Model (SAM) and improved schema representations for the STAR corpus. SAM obtains significant improvement in zero-shot settings, with a +22 F1 score improvement over prior work. These results validate the feasibility of zero-shot generalizability in dialog. Ablation experiments are also presented to demonstrate the efficacy of SAM.
Pretrained transformer-based encoders such as BERT have been demonstrated to achieve state-of-the-art performance on numerous NLP tasks. Despite their success, BERT style encoders are large in size and have high latency during inference (especially o
n CPU machines) which make them unappealing for many online applications. Recently introduced compression and distillation methods have provided effective ways to alleviate this shortcoming. However, the focus of these works has been mainly on monolingual encoders. Motivated by recent successes in zero-shot cross-lingual transfer learning using multilingual pretrained encoders such as mBERT, we evaluate the effectiveness of Knowledge Distillation (KD) both during pretraining stage and during fine-tuning stage on multilingual BERT models. We demonstrate that in contradiction to the previous observation in the case of monolingual distillation, in multilingual settings, distillation during pretraining is more effective than distillation during fine-tuning for zero-shot transfer learning. Moreover, we observe that distillation during fine-tuning may hurt zero-shot cross-lingual performance. Finally, we demonstrate that distilling a larger model (BERT Large) results in the strongest distilled model that performs best both on the source language as well as target languages in zero-shot settings.
Zero-shot cross-domain dialogue state tracking (DST) enables us to handle unseen domains without the expense of collecting in-domain data. In this paper, we propose a slot descriptions enhanced generative approach for zero-shot cross-domain DST. Spec
ifically, our model first encodes a dialogue context and a slot with a pre-trained self-attentive encoder, and generates slot value in auto-regressive manner. In addition, we incorporate Slot Type Informed Descriptions that capture the shared information of different slots to facilitates the cross-domain knowledge transfer. Experimental results on MultiWOZ shows that our model significantly improve existing state-of-the-art results in zero-shot cross-domain setting.
Coupled with the availability of large scale datasets, deep learning architectures have enabled rapid progress on the Question Answering task. However, most of those datasets are in English, and the performances of state-of-the-art multilingual model
s are significantly lower when evaluated on non-English data. Due to high data collection costs, it is not realistic to obtain annotated data for each language one desires to support. We propose a method to improve the Cross-lingual Question Answering performance without requiring additional annotated data, leveraging Question Generation models to produce synthetic samples in a cross-lingual fashion. We show that the proposed method allows to significantly outperform the baselines trained on English data only. We report a new state-of-the-art on four datasets: MLQA, XQuAD, SQuAD-it and PIAF (fr).
This study aims at studying the phonetic or syllable changes that
occur on the last sound of a word when this sound is a consonant or a
vowel.
The study is also concerned with exploring the relation between the
last sound of the word and the firs
t sound of the next word. An example
on that is when the last sound changes into a sound similar to the sound
of the following word, wherein both sounds are assimilated.
The study shows that if the last sound is a vowel, caused for
instance by the vocal; then, changes do not happen, where in such case
the vocal separates the end of the word from the beginning of the next
word. This emphasizes the importance of vocals in separating the speech
and avoiding misconception.
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
