Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userMilaNLP @ WASSA: Does BERT Feel Sad When You Cry?
Milanlp @ Wassa: هل بيرت تشعر بالحزن عندما تبكي؟
187
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تصف الورقة تقديم فريق Milanlp (جامعة Bocconi، ميلان) في مهمة Wassa 2021 المشتركة بشأن الكشف عن التعاطف والتصنيف العاطفي.نحن نركز على المسار 2 - تصنيف العاطفة - التي تتكون من التنبؤ بمشاعر ردود الفعل على القصص الإخبارية الإنجليزية على مستوى المقال.نختبر نماذج مختلفة تعتمد على أطر متعددة ومتعددة الإدخال.كان الهدف هو استغلال أفضل جميع المعلومات المرتبطة المقدمة في مجموعة البيانات.نجد، على الرغم من أن التعاطف باعتباره المهمة المساعدة في التعلم متعدد المهام والسمات الديموغرافية حيث يوفر مدخلات إضافية أداء أسوأ فيما يتعلق بتعلم المهمة الفردية.في حين أن النتيجة تنافسية من حيث المنافسة، فإن نتائجنا تشير إلى أن العاطفة والتعاطف غير مرتبطة مهام مرتبطة - على الأقل لغرض التنبؤ.
The paper describes the MilaNLP team's submission (Bocconi University, Milan) in the WASSA 2021 Shared Task on Empathy Detection and Emotion Classification. We focus on Track 2 - Emotion Classification - which consists of predicting the emotion of reactions to English news stories at the essay-level. We test different models based on multi-task and multi-input frameworks. The goal was to better exploit all the correlated information given in the data set. We find, though, that empathy as an auxiliary task in multi-task learning and demographic attributes as additional input provide worse performance with respect to single-task learning. While the result is competitive in terms of the competition, our results suggest that emotion and empathy are not related tasks - at least for the purpose of prediction.
References used
https://aclanthology.org/
rate research
Read More
Understanding idioms is important in NLP. In this paper, we study to what extent pre-trained BERT model can encode the meaning of a potentially idiomatic expression (PIE) in a certain context. We make use of a few existing datasets and perform two pr
obing tasks: PIE usage classification and idiom paraphrase identification. Our experiment results suggest that BERT indeed can separate the literal and idiomatic usages of a PIE with high accuracy. It is also able to encode the idiomatic meaning of a PIE to some extent.
People convey their intention and attitude through linguistic styles of the text that they write. In this study, we investigate lexicon usages across styles throughout two lenses: human perception and machine word importance, since words differ in th
e strength of the stylistic cues that they provide. To collect labels of human perception, we curate a new dataset, Hummingbird, on top of benchmarking style datasets. We have crowd workers highlight the representative words in the text that makes them think the text has the following styles: politeness, sentiment, offensiveness, and five emotion types. We then compare these human word labels with word importance derived from a popular fine-tuned style classifier like BERT. Our results show that the BERT often finds content words not relevant to the target style as important words used in style prediction, but humans do not perceive the same way even though for some styles (e.g., positive sentiment and joy) human- and machine-identified words share significant overlap for some styles.
This paper describes our contribution to the WASSA 2021 shared task on Empathy Prediction and Emotion Classification. The broad goal of this task was to model an empathy score, a distress score and the overall level of emotion of an essay written in
response to a newspaper article associated with harm to someone. We have used the ELECTRA model abundantly and also advanced deep learning approaches like multi-task learning. Additionally, we also leveraged standard machine learning techniques like ensembling. Our system achieves a Pearson Correlation Coefficient of 0.533 on sub-task I and a macro F1 score of 0.5528 on sub-task II. We ranked 1st in Emotion Classification sub-task and 3rd in Empathy Prediction sub-task.
In machine reading comprehension tasks, a model must extract an answer from the available context given a question and a passage. Recently, transformer-based pre-trained language models have achieved state-of-the-art performance in several natural la
nguage processing tasks. However, it is unclear whether such performance reflects true language understanding. In this paper, we propose adversarial examples to probe an Arabic pre-trained language model (AraBERT), leading to a significant performance drop over four Arabic machine reading comprehension datasets. We present a layer-wise analysis for the transformer's hidden states to offer insights into how AraBERT reasons to derive an answer. The experiments indicate that AraBERT relies on superficial cues and keyword matching rather than text understanding. Furthermore, hidden state visualization demonstrates that prediction errors can be recognized from vector representations in earlier layers.
Learning fine-grained distinctions between vocabulary items is a key challenge in learning a new language. For example, the noun wall'' has different lexical manifestations in Spanish -- pared'' refers to an indoor wall while muro'' refers to an outs
ide wall. However, this variety of lexical distinction may not be obvious to non-native learners unless the distinction is explained in such a way. In this work, we present a method for automatically identifying fine-grained lexical distinctions, and extracting rules explaining these distinctions in a human- and machine-readable format. We confirm the quality of these extracted rules in a language learning setup for two languages, Spanish and Greek, where we use the rules to teach non-native speakers when to translate a given ambiguous word into its different possible translations.
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
