Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userTracing Source Language Interference in Translation with Graph-Isomorphism Measures
تتبع لغة مصدر مصدر في الترجمة مع تدابير الرسم البياني ISOMORPHISM
207
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
استخدمت الأبحاث السابقة ميزات لغوية لإظهار أن الترجمات تظهر آثار التداخل اللغوي المصدر وأن الأشجار البلورية بين اللغات يمكن إعادة بناءها من نتائج الترجمات إلى نفس اللغة. أظهرت الأبحاث الحديثة أن مثيلات الترجمة (التداخل اللغوي المصدر) يمكن اكتشافها في مساحات تضمينها، ومقارنة مساحات الأدوات الخاصة ببيانات اللغة الأصلية مع أماكن التضمين الناتجة عن الترجمات إلى نفس اللغة، باستخدام اختلاف بسيط يستند إلى eigenvector من قياس ISOMORPHIMM. حتى الآن، لا يزال هناك سؤال مفتوح ما إذا كان يمكن إجراء تدابير البديلة البديلة البديلة البديلة نتائج أفضل. في هذه الورقة، نحن (ط) استكشاف مسافة Groomov-Hausdorff، (II) تقديم نسخة طيفية جديدة من الطريقة القائمة على eigenvector، و (III) تقييم جميع النهج مقابل قاعدة بيانات نموذجية لغوية واسعة (URIEL). نظرا لأن المسافات اللغوية الناتجة عن نهج التزييف الطيفي لدينا يمكن أن تتكاثر الأشجار الوراثية على قدم المساواة مع العمل السابق دون الحاجة إلى أي معلومات لغوية واضحة وأن النتائج يمكن تمديدها إلى اللغات غير الهندية الأوروبية. أخيرا، نظهر أن الطرق قوية تحت مجموعة متنوعة من ظروف النمذجة.
Previous research has used linguistic features to show that translations exhibit traces of source language interference and that phylogenetic trees between languages can be reconstructed from the results of translations into the same language. Recent research has shown that instances of translationese (source language interference) can even be detected in embedding spaces, comparing embeddings spaces of original language data with embedding spaces resulting from translations into the same language, using a simple Eigenvector-based divergence from isomorphism measure. To date, it remains an open question whether alternative graph-isomorphism measures can produce better results. In this paper, we (i) explore Gromov-Hausdorff distance, (ii) present a novel spectral version of the Eigenvector-based method, and (iii) evaluate all approaches against a broad linguistic typological database (URIEL). We show that language distances resulting from our spectral isomorphism approaches can reproduce genetic trees on a par with previous work without requiring any explicit linguistic information and that the results can be extended to non-Indo-European languages. Finally, we show that the methods are robust under a variety of modeling conditions.
References used
https://aclanthology.org/
rate research
Read More
Among the factors affecting the movement of water in the soil are soil properties (structure and texture).
The rate of components of soil minerals and organic material has an effect on its bulk density. As the
surface soil has organic matter more t
han subsurface soil in general, the bulk density increases with soil
depth, so the research aims to study the effect of changing soil bulk density with depth on wetting front
advance under a trickle line source. The experimental work included a nine laboratory tests for
monitoring the advancement of the wetting front with time, The water advance and water distribution
measurement are carried out for three cases of the soil profile with the change of bulk density along soil
depth (0.00923,0.00462,0) gm/cm 3/cm: first case with the soil changed bulk density from 1.2 gm/cm 3 at
the soil surface and gradually to 1.8 gm/cm 3 at a maximum depth of the profile, the second case with the
soil changing bulk density from 1.5 gm / cm 3 to 1.8 gm / cm 3, and the third case homogeneous soil with
bulk density 1.2 gm / cm 3, and using three application flow rates 1.3,2.6,3.9 cm 3 / min / cm.
The study showed that with the increase in the change of bulk density along soil depth there is a small
increase in horizontal advance and almost non-existent increase in vertical advance while they are clear
and tangible in diagonal advance. It also showed that the amount of the increase in the vertical advance is
greater than in the horizontal advance and be could be in diagonal advance when increasing the
application flow rate, and all of the horizontal advance, vertical advance and the diagonal advance of the
wetting front increase with the decrease of the application flow rate when applied in the same volume of
water.
Graph-based semantic parsing aims to represent textual meaning through directed graphs. As one of the most promising general-purpose meaning representations, these structures and their parsing have gained a significant interest momentum during recent
years, with several diverse formalisms being proposed. Yet, owing to this very heterogeneity, most of the research effort has focused mainly on solutions specific to a given formalism. In this work, instead, we reframe semantic parsing towards multiple formalisms as Multilingual Neural Machine Translation (MNMT), and propose SGL, a many-to-many seq2seq architecture trained with an MNMT objective. Backed by several experiments, we show that this framework is indeed effective once the learning procedure is enhanced with large parallel corpora coming from Machine Translation: we report competitive performances on AMR and UCCA parsing, especially once paired with pre-trained architectures. Furthermore, we find that models trained under this configuration scale remarkably well to tasks such as cross-lingual AMR parsing: SGL outperforms all its competitors by a large margin without even explicitly seeing non-English to AMR examples at training time and, once these examples are included as well, sets an unprecedented state of the art in this task. We release our code and our models for research purposes at https://github.com/SapienzaNLP/sgl.
Pre-trained models like Bidirectional Encoder Representations from Transformers (BERT), have recently made a big leap forward in Natural Language Processing (NLP) tasks. However, there are still some shortcomings in the Masked Language Modeling (MLM)
task performed by these models. In this paper, we first introduce a multi-graph including different types of relations between words. Then, we propose Multi-Graph augmented BERT (MG-BERT) model that is based on BERT. MG-BERT embeds tokens while taking advantage of a static multi-graph containing global word co-occurrences in the text corpus beside global real-world facts about words in knowledge graphs. The proposed model also employs a dynamic sentence graph to capture local context effectively. Experimental results demonstrate that our model can considerably enhance the performance in the MLM task.
Story generation is a task that aims to automatically generate a meaningful story. This task is challenging because it requires high-level understanding of the semantic meaning of sentences and causality of story events. Naivesequence-to-sequence mod
els generally fail to acquire such knowledge, as it is difficult to guarantee logical correctness in a text generation model without strategic planning. In this study, we focus on planning a sequence of events assisted by event graphs and use the events to guide the generator. Rather than using a sequence-to-sequence model to output a sequence, as in some existing works, we propose to generate an event sequence by walking on an event graph. The event graphs are built automatically based on the corpus. To evaluate the proposed approach, we incorporate human participation, both in event planning and story generation. Based on the largescale human annotation results, our proposed approach has been shown to provide more logically correct event sequences and stories compared with previous approaches.
Dialogue-based relation extraction (RE) aims to extract relation(s) between two arguments that appear in a dialogue. Because dialogues have the characteristics of high personal pronoun occurrences and low information density, and since most relationa
l facts in dialogues are not supported by any single sentence, dialogue-based relation extraction requires a comprehensive understanding of dialogue. In this paper, we propose the TUrn COntext awaRE Graph Convolutional Network (TUCORE-GCN) modeled by paying attention to the way people understand dialogues. In addition, we propose a novel approach which treats the task of emotion recognition in conversations (ERC) as a dialogue-based RE. Experiments on a dialogue-based RE dataset and three ERC datasets demonstrate that our model is very effective in various dialogue-based natural language understanding tasks. In these experiments, TUCORE-GCN outperforms the state-of-the-art models on most of the benchmark datasets. Our code is available at https://github.com/BlackNoodle/TUCORE-GCN.
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
