Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDoes BERT Understand Idioms? A Probing-Based Empirical Study of BERT Encodings of Idioms
هل بيرت فهم التعريفات؟دراسة تجريبية تستند إلى ترميزات برت التعبيريات
337
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
فهم التعابير مهم في NLP.في هذه الورقة، ندرس إلى أي مدى يمكن لطراز بيرت المدرب مسبقا أن يرمز معنى التعبير العناقوي المحتمل (فطيرة) في سياق معين.نحن نستفيد من بعض البيانات الموجودة وأداء مهام التحقيق: تصنيف استخدام فطيرة وتحديد صياغة الصيغة.تشير نتائج التجريب الخاصة بنا إلى أن بيرت بالفعل يمكن أن تفصل السماحات الحرفية والاعتينية من فطيرة بدقة عالية.كما أنه قادر أيضا على تشفير المعنى الاصطلاح للكتبة إلى حد ما.
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 probing 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.
References used
https://aclanthology.org/
rate research
Read More
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.
Natural conversations are filled with disfluencies. This study investigates if and how BERT understands disfluency with three experiments: (1) a behavioural study using a downstream task, (2) an analysis of sentence embeddings and (3) an analysis of
the attention mechanism on disfluency. The behavioural study shows that without fine-tuning on disfluent data, BERT does not suffer significant performance loss when presented disfluent compared to fluent inputs (exp1). Analysis on sentence embeddings of disfluent and fluent sentence pairs reveals that the deeper the layer, the more similar their representation (exp2). This indicates that deep layers of BERT become relatively invariant to disfluency. We pinpoint attention as a potential mechanism that could explain this phenomenon (exp3). Overall, the study suggests that BERT has knowledge of disfluency structure. We emphasise the potential of using BERT to understand natural utterances without disfluency removal.
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 re
actions 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.
Abstract Pre-trained Transformer-based models have achieved state-of-the-art performance for various Natural Language Processing (NLP) tasks. However, these models often have billions of parameters, and thus are too resource- hungry and computation-i
ntensive to suit low- capability devices or applications with strict latency requirements. One potential remedy for this is model compression, which has attracted considerable research attention. Here, we summarize the research in compressing Transformers, focusing on the especially popular BERT model. In particular, we survey the state of the art in compression for BERT, we clarify the current best practices for compressing large-scale Transformer models, and we provide insights into the workings of various methods. Our categorization and analysis also shed light on promising future research directions for achieving lightweight, accurate, and generic NLP models.
Due to the development of deep learning, the natural language processing tasks have made great progresses by leveraging the bidirectional encoder representations from Transformers (BERT). The goal of information retrieval is to search the most releva
nt results for the user's query from a large set of documents. Although BERT-based retrieval models have shown excellent results in many studies, these models usually suffer from the need for large amounts of computations and/or additional storage spaces. In view of the flaws, a BERT-based Siamese-structured retrieval model (BESS) is proposed in this paper. BESS not only inherits the merits of pre-trained language models, but also can generate extra information to compensate the original query automatically. Besides, the reinforcement learning strategy is introduced to make the model more robust. Accordingly, we evaluate BESS on three public-available corpora, and the experimental results demonstrate the efficiency of the proposed retrieval model.
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
