Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSkoltechNLP at SemEval-2021 Task 2: Generating Cross-Lingual Training Data for the Word-in-Context Task
Skoltechnlp في مهمة Semeval-2021: إنشاء بيانات تدريبية عبر اللغات لمهمة Word-in السياق
138
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
في هذه الورقة، نقدم نظاما لحل مهمة الغموض في السياق عبر اللغات واللغات متعددة اللغات. قدم منظمو المهام بيانات أحادية الأونلينغ بعدة لغات، ولكن لم تتوفر بيانات تدريبية عبر اللغات. لمعالجة عدم وجود بيانات تدريبية عبر اللغات المقدمة رسميا، قررنا توليد هذه البيانات بأنفسنا. نحن نصف نهج بسيط ولكنه فعال يعتمد على الترجمة الآلية والترجمة الخلفية للوحدات المعجمية إلى اللغة الأصلية المستخدمة في سياق هذه المهمة المشتركة. في تجاربنا، استخدمنا نظاما عصبا يعتمد على نموذج لغة XLM-R، وهو نموذج لغة ملثم مقره محول مسبقا، كناسما أساسيا. نظهر فعالية النهج المقترح لأنه يسمح بتحسين أداء هذا النموذج الأساسي القوي العصبي القوي. بالإضافة إلى ذلك، في هذه الدراسة، نقدم أنواعا متعددة من المصنف المستند إلى XLM-R، وتجربة طرق مختلفة لخلط المعلومات من الأحداث الأولى والثانية للكلمة المستهدفة في عينتين.
In this paper, we present a system for the solution of the cross-lingual and multilingual word-in-context disambiguation task. Task organizers provided monolingual data in several languages, but no cross-lingual training data were available. To address the lack of the officially provided cross-lingual training data, we decided to generate such data ourselves. We describe a simple yet effective approach based on machine translation and back translation of the lexical units to the original language used in the context of this shared task. In our experiments, we used a neural system based on the XLM-R, a pre-trained transformer-based masked language model, as a baseline. We show the effectiveness of the proposed approach as it allows to substantially improve the performance of this strong neural baseline model. In addition, in this study, we present multiple types of the XLM-R based classifier, experimenting with various ways of mixing information from the first and second occurrences of the target word in two samples.
References used
https://aclanthology.org/
rate research
Read More
This paper presents a word-in-context disambiguation system. The task focuses on capturing the polysemous nature of words in a multilingual and cross-lingual setting, without considering a strict inventory of word meanings. The system applies Natural
Language Processing algorithms on datasets from SemEval 2021 Task 2, being able to identify the meaning of words for the languages Arabic, Chinese, English, French and Russian, without making use of any additional mono- or multilingual resources.
In this paper, we introduce the first SemEval task on Multilingual and Cross-Lingual Word-in-Context disambiguation (MCL-WiC). This task allows the largely under-investigated inherent ability of systems to discriminate between word senses within and
across languages to be evaluated, dropping the requirement of a fixed sense inventory. Framed as a binary classification, our task is divided into two parts. In the multilingual sub-task, participating systems are required to determine whether two target words, each occurring in a different context within the same language, express the same meaning or not. Instead, in the cross-lingual part, systems are asked to perform the task in a cross-lingual scenario, in which the two target words and their corresponding contexts are provided in two different languages. We illustrate our task, as well as the construction of our manually-created dataset including five languages, namely Arabic, Chinese, English, French and Russian, and the results of the participating systems. Datasets and results are available at: https://github.com/SapienzaNLP/mcl-wic.
We experiment with XLM RoBERTa for Word in Context Disambiguation in the Multi Lingual and Cross Lingual setting so as to develop a single model having knowledge about both settings. We solve the problem as a binary classification problem and also ex
periment with data augmentation and adversarial training techniques. In addition, we also experiment with a 2-stage training technique. Our approaches prove to be beneficial for better performance and robustness.
In this paper, we introduce our system that we participated with at the multilingual and cross-lingual word-in-context disambiguation SemEval 2021 shared task. In our experiments, we investigated the possibility of using an all-words fine-grained wor
d sense disambiguation system trained purely on sense-annotated data in English and draw predictions on the semantic equivalence of words in context based on the similarity of the ranked lists of the (English) WordNet synsets returned for the target words decisions had to be made for. We overcame the multi,-and cross-lingual aspects of the shared task by applying a multilingual transformer for encoding the texts written in either Arabic, English, French, Russian and Chinese. While our results lag behind top scoring submissions, it has the benefit that it not only provides a binary flag whether two words in their context have the same meaning, but also provides a more tangible output in the form of a ranked list of (English) WordNet synsets irrespective of the language of the input texts. As our framework is designed to be as generic as possible, it can be applied as a baseline for basically any language (supported by the multilingual transformed architecture employed) even in the absence of any additional form of language specific training data.
In this work, we present our approach for solving the SemEval 2021 Task 2: Multilingual and Cross-lingual Word-in-Context Disambiguation (MCL-WiC). The task is a sentence pair classification problem where the goal is to detect whether a given word co
mmon to both the sentences evokes the same meaning. We submit systems for both the settings - Multilingual (the pair's sentences belong to the same language) and Cross-Lingual (the pair's sentences belong to different languages). The training data is provided only in English. Consequently, we employ cross-lingual transfer techniques. Our approach employs fine-tuning pre-trained transformer-based language models, like ELECTRA and ALBERT, for the English task and XLM-R for all other tasks. To improve these systems' performance, we propose adding a signal to the word to be disambiguated and augmenting our data by sentence pair reversal. We further augment the dataset provided to us with WiC, XL-WiC and SemCor 3.0. Using ensembles, we achieve strong performance in the Multilingual task, placing first in the EN-EN and FR-FR sub-tasks. For the Cross-Lingual setting, we employed translate-test methods and a zero-shot method, using our multilingual models, with the latter performing slightly better.
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
