paper-with-me

Papers

How Can BERT Help Lexical Semantics Tasks?

2019-11-07 · Yile Wang, Leyang Cui, Yue Zhang

Contextualized embeddings such as BERT can serve as strong input representations to NLP tasks, outperforming their static embeddings counterparts such as skip-gram, CBOW and GloVe. However, such embeddings are dynamic, calculated according to a sentence-level context, which limits their use in lexical semantics tasks. We address this issue by making use of dynamic embeddings as word representations in training static embeddings, thereby leveraging their strong representation power for disambiguating context information. Results show that this method leads to improvements over traditional static embeddings on a range of lexical semantics tasks, obtaining the best reported results on seven datasets.

📄 PDF Abstract BibTeX arXiv:1911.02929

Code (0)

등록된 구현이 없습니다.

Tasks

SentenceWord Embeddings

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
GloVe GloVe Embeddings are a type of word embedding that encode the co-occurrence probability ratio between two words as vector differences. GloVe uses a weighted least squares…
Residual Connection 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Weight Decay 설명 없음
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

Compositional and Lexical Semantics in RoBERTa, BERT and DistilBERT: A Case Study on CoQA

2020-09-17 · EMNLP 2020 11 · Ieva Staliūnaitė, Ignacio Iacobacci

Many NLP tasks have benefited from transferring knowledge from contextualized word embeddings, however the picture of what type of knowledge is transferred is incomplete. This paper studies the types of linguistic phenom…

Conversational Question AnsweringNegationQuestion AnsweringSemantic Role Labeling+1

HurtBERT: Incorporating Lexical Features with BERT for the Detection of Abusive Language

2020-11-01 · EMNLP (ALW) 2020 11 · Anna Koufakou, Endang Wahyu Pamungkas, Valerio Basile, Viviana Patti

The detection of abusive or offensive remarks in social texts has received significant attention in research. In several related shared tasks, BERT has been shown to be the state-of-the-art. In this paper, we propose to …

Abusive LanguageSentence

Measuring Context-Word Biases in Lexical Semantic Datasets

2021-12-13 · Qianchu Liu, Diana McCarthy, Anna Korhonen

State-of-the-art pretrained contextualized models (PCM) eg. BERT use tasks such as WiC and WSD to evaluate their word-in-context representations. This inherently assumes that performance in these tasks reflect how well a…

Retrieval

Fantastic Semantics and Where to Find Them: Investigating Which Layers of Generative LLMs Reflect Lexical Semantics

2024-03-03 · Zhu Liu, Cunliang Kong, Ying Liu, Maosong Sun

Large language models have achieved remarkable success in general language understanding tasks. However, as a family of generative methods with the objective of next token prediction, the semantic evolution with the dept…

Language ModelingLanguage Modelling

Probing Pretrained Language Models for Lexical Semantics

2020-10-12 · EMNLP 2020 11 · Ivan Vulić, Edoardo Maria Ponti, Robert Litschko, Goran Glavaš 외

The success of large pretrained language models (LMs) such as BERT and RoBERTa has sparked interest in probing their representations, in order to unveil what types of knowledge they implicitly capture. While prior resear…

World Knowledge