Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSemantic Alignment with Calibrated Similarity for Multilingual Sentence Embedding
المحاذاة الدلالية مع التشابه المعايرة لضمان الجملة متعددة اللغات
344
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
قياس درجة التشابه بين زوج من الجمل بلغات مختلفة هو المطلوبة الأساسية لأساليب تضمين الجملة متعددة اللغات. يتكون التنبؤ بدرجة التشابه من مهمتين فرعيتين، وهو تقييم التغلب غير المباشر واسترجاع الجملة متعددة اللغات. ومع ذلك، فإن الأساليب التقليدية قد تناولت أساسا واحدة فقط من المهام الفرعية، وبالتالي أظهرت عروضا متحيزا. في هذه الورقة، نقترح طريقة جديدة وطريقة قوية لتضمين الجملة متعددة اللغات، مما يدل على تحسين الأداء على كلا المهام الفرعية، وبالتالي مما يؤدي إلى تنبؤات قوية لدرجات التشابه متعددة اللغات. تتكون الطريقة المقترحة من جزأين: لتعلم التشابه الدلالي من الجمل في اللغة المحورية، ثم تمديد الهيكل الدلالي المستفاد لغات مختلفة. لمحاذاة الهياكل الدلالية عبر لغات مختلفة، نقدم شبكة مدرس وطالب. تقطير شبكة المعلم معرفة اللغة المحورية لغات مختلفة من شبكة الطلاب. أثناء التقطير، يتم تحديث معلمات شبكة المعلم مع المتوسط البطيء المتحرك. جنبا إلى جنب مع التقطير وتحديث المعلمة، يمكن محاذاة الهيكل الدلالي لشبكة الطالب مباشرة عبر لغات مختلفة مع الحفاظ على القدرة على قياس التشابه الدلالي. وبالتالي، فإن طريقة التدريب متعددة اللغات تدفع تحسين الأداء في تقييم التشابه متعدد اللغات. يحقق النموذج المقترح أداء الحديث في تقييم التشابه متعدد اللغات لعام 2017 بالإضافة إلى مهام فرعية، التي تمتد التقييم المتشابهات لأول مرة 2017 و Tatoeba متعددة اللغات متعددة اللغات في 14 لغة.
Measuring the similarity score between a pair of sentences in different languages is the essential requisite for multilingual sentence embedding methods. Predicting the similarity score consists of two sub-tasks, which are monolingual similarity evaluation and multilingual sentence retrieval. However, conventional methods have mainly tackled only one of the sub-tasks and therefore showed biased performances. In this paper, we suggest a novel and strong method for multilingual sentence embedding, which shows performance improvement on both sub-tasks, consequently resulting in robust predictions of multilingual similarity scores. The suggested method consists of two parts: to learn semantic similarity of sentences in the pivot language and then to extend the learned semantic structure to different languages. To align semantic structures across different languages, we introduce a teacher-student network. The teacher network distills the knowledge of the pivot language to different languages of the student network. During the distillation, the parameters of the teacher network are updated with the slow-moving average. Together with the distillation and the parameter updating, the semantic structure of the student network can be directly aligned across different languages while preserving the ability to measure the semantic similarity. Thus, the multilingual training method drives performance improvement on multilingual similarity evaluation. The suggested model achieves the state-of-the-art performance on extended STS 2017 multilingual similarity evaluation as well as two sub-tasks, which are extended STS 2017 monolingual similarity evaluation and Tatoeba multilingual retrieval in 14 languages.
References used
https://aclanthology.org/
rate research
Read More
Document alignment techniques based on multilingual sentence representations have recently shown state of the art results. However, these techniques rely on unsupervised distance measurement techniques, which cannot be fined-tuned to the task at hand
. In this paper, instead of these unsupervised distance measurement techniques, we employ Metric Learning to derive task-specific distance measurements. These measurements are supervised, meaning that the distance measurement metric is trained using a parallel dataset. Using a dataset belonging to English, Sinhala, and Tamil, which belong to three different language families, we show that these task-specific supervised distance learning metrics outperform their unsupervised counterparts, for document alignment.
We propose a method to distill a language-agnostic meaning embedding from a multilingual sentence encoder. By removing language-specific information from the original embedding, we retrieve an embedding that fully represents the sentence's meaning. T
he proposed method relies only on parallel corpora without any human annotations. Our meaning embedding allows efficient cross-lingual sentence similarity estimation by simple cosine similarity calculation. Experimental results on both quality estimation of machine translation and cross-lingual semantic textual similarity tasks reveal that our method consistently outperforms the strong baselines using the original multilingual embedding. Our method consistently improves the performance of any pre-trained multilingual sentence encoder, even in low-resource language pairs where only tens of thousands of parallel sentence pairs are available.
Pre-trained cross-lingual encoders such as mBERT (Devlin et al., 2019) and XLM-R (Conneau et al., 2020) have proven impressively effective at enabling transfer-learning of NLP systems from high-resource languages to low-resource languages. This succe
ss comes despite the fact that there is no explicit objective to align the contextual embeddings of words/sentences with similar meanings across languages together in the same space. In this paper, we present a new method for learning multilingual encoders, AMBER (Aligned Multilingual Bidirectional EncodeR). AMBER is trained on additional parallel data using two explicit alignment objectives that align the multilingual representations at different granularities. We conduct experiments on zero-shot cross-lingual transfer learning for different tasks including sequence tagging, sentence retrieval and sentence classification. Experimental results on the tasks in the XTREME benchmark (Hu et al., 2020) show that AMBER obtains gains of up to 1.1 average F1 score on sequence tagging and up to 27.3 average accuracy on retrieval over the XLM-R-large model which has 3.2x the parameters of AMBER. Our code and models are available at http://github.com/junjiehu/amber.
The evaluation of question answering models compares ground-truth annotations with model predictions. However, as of today, this comparison is mostly lexical-based and therefore misses out on answers that have no lexical overlap but are still semanti
cally similar, thus treating correct answers as false. This underestimation of the true performance of models hinders user acceptance in applications and complicates a fair comparison of different models. Therefore, there is a need for an evaluation metric that is based on semantics instead of pure string similarity. In this short paper, we present SAS, a cross-encoder-based metric for the estimation of semantic answer similarity, and compare it to seven existing metrics. To this end, we create an English and a German three-way annotated evaluation dataset containing pairs of answers along with human judgment of their semantic similarity, which we release along with an implementation of the SAS metric and the experiments. We find that semantic similarity metrics based on recent transformer models correlate much better with human judgment than traditional lexical similarity metrics on our two newly created datasets and one dataset from related work.
Semantic textual similarity (STS) systems estimate the degree of the meaning similarity between two sentences. Cross-lingual STS systems estimate the degree of the meaning similarity between two sentences, each in a different language. State-of-the-a
rt algorithms usually employ a strongly supervised, resource-rich approach difficult to use for poorly-resourced languages. However, any approach needs to have evaluation data to confirm the results. In order to simplify the evaluation process for poorly-resourced languages (in terms of STS evaluation datasets), we present new datasets for cross-lingual and monolingual STS for languages without this evaluation data. We also present the results of several state-of-the-art methods on these data which can be used as a baseline for further research. We believe that this article will not only extend the current STS research to other languages, but will also encourage competition on this new evaluation data.
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
