Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDeriving Contextualised Semantic Features from BERT (and Other Transformer Model) Embeddings
اشتقاق الميزات الدلالية السياقية من Bert (وغيرها من طراز المحولات)
133
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
وضعت النماذج المستندة إلى بنية المحولات، مثل بيرت، خطوة حاسمة إلى الأمام في مجال معالجة اللغة الطبيعية. الأهم من ذلك، فإنها تسمح بإنشاء Adgeddings Word التي تلتقط معلومات دهالية مهمة حول الكلمات في السياق. ومع ذلك، ككيانات واحدة، من الصعب تفسير هذه الأشرطة وتفسير النماذج المستخدمة لإنشاءها بأنها غير مبتمة. اقترح الموثق والزملاء مساحة تضمين بديهية حيث يعتمد كل بعدا على واحدة من 65 من الميزات الدلالية الأساسية. لسوء الحظ، توجد المساحة فقط لمجموعة بيانات صغيرة من 535 كلمة، مما يحد من استخداماتها. العمل السابق (UTSUMI، 2018، 2020؛ Turton et al.، 2020)، أظهر أن ميزات الموثق يمكن استخلاصها من المدينات الثابتة واستقلاعها بنجاح لمفردات جديدة كبيرة. اتخاذ الخطوة التالية، توضح هذه الورقة أن ميزات الموثق يمكن أن تستمد من مساحة تضمين بيرت. هذا يوفر شيئين؛ (1) قيم ميزة الدلالية المستمدة من Adgeddings Word السياقي و (2) رؤى في كيفية تمثيل الميزات الدلالية عبر طبقات مختلفة من نموذج Bert.
Models based on the transformer architecture, such as BERT, have marked a crucial step forward in the field of Natural Language Processing. Importantly, they allow the creation of word embeddings that capture important semantic information about words in context. However, as single entities, these embeddings are difficult to interpret and the models used to create them have been described as opaque. Binder and colleagues proposed an intuitive embedding space where each dimension is based on one of 65 core semantic features. Unfortunately, the space only exists for a small data-set of 535 words, limiting its uses. Previous work (Utsumi, 2018, 2020; Turton et al., 2020) has shown that Binder features can be derived from static embeddings and successfully extrapolated to a large new vocabulary. Taking the next step, this paper demonstrates that Binder features can be derived from the BERT embedding space. This provides two things; (1) semantic feature values derived from contextualised word embeddings and (2) insights into how semantic features are represented across the different layers of the BERT model.
References used
https://aclanthology.org/
rate research
Read More
One of the long-standing challenges in lexical semantics consists in learning representations of words which reflect their semantic properties. The remarkable success of word embeddings for this purpose suggests that high-quality representations can
be obtained by summarizing the sentence contexts of word mentions. In this paper, we propose a method for learning word representations that follows this basic strategy, but differs from standard word embeddings in two important ways. First, we take advantage of contextualized language models (CLMs) rather than bags of word vectors to encode contexts. Second, rather than learning a word vector directly, we use a topic model to partition the contexts in which words appear, and then learn different topic-specific vectors for each word. Finally, we use a task-specific supervision signal to make a soft selection of the resulting vectors. We show that this simple strategy leads to high-quality word vectors, which are more predictive of semantic properties than word embeddings and existing CLM-based strategies.
In this paper, we introduce the first corpus specifying negative entities within sentences. We discuss indicators for their presence, namely particular verbs, but also the linguistic conditions when their prediction should be suppressed. We further s
how that a fine-tuned Bert-based baseline model outperforms an over-generating rule-based approach which is not aware of these further restrictions. If a perfect filter were applied, both would be on par.
Relative position embedding (RPE) is a successful method to explicitly and efficaciously encode position information into Transformer models. In this paper, we investigate the potential problems in Shaw-RPE and XL-RPE, which are the most representati
ve and prevalent RPEs, and propose two novel RPEs called Low-level Fine-grained High-level Coarse-grained (LFHC) RPE and Gaussian Cumulative Distribution Function (GCDF) RPE. LFHC-RPE is an improvement of Shaw-RPE, which enhances the perception ability at medium and long relative positions. GCDF-RPE utilizes the excellent properties of the Gaussian function to amend the prior encoding mechanism in XL-RPE. Experimental results on nine authoritative datasets demonstrate the effectiveness of our methods empirically. Furthermore, GCDF-RPE achieves the best overall performance among five different RPEs.
هذه المقالة تحوي ترجمة وتلخيص وتوضيح للمذكور في الورقة البحثية المذكور اسمها أعلاه والموجودة في https://annals-csis.org/Volume_8/pliks/221.pdf , والتي تقوم باستخراج المعلومات الدلالية المهمة الموجودة في الوثائق والملفات والأوراق البحثية .
Sarcasm detection and sentiment analysis are important tasks in Natural Language Understanding. Sarcasm is a type of expression where the sentiment polarity is flipped by an interfering factor. In this study, we exploited this relationship to enhance
both tasks by proposing a multi-task learning approach using a combination of static and contextualised embeddings. Our proposed system achieved the best result in the sarcasm detection subtask.
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
