paper-with-me

Papers

Retrofitting Contextualized Word Embeddings with Paraphrases

2019-09-12 · IJCNLP 2019 11 · Weijia Shi, Muhao Chen, Pei Zhou, Kai-Wei Chang

Contextualized word embedding models, such as ELMo, generate meaningful representations of words and their context. These models have been shown to have a great impact on downstream applications. However, in many cases, the contextualized embedding of a word changes drastically when the context is paraphrased. As a result, the downstream model is not robust to paraphrasing and other linguistic variations. To enhance the stability of contextualized word embedding models, we propose an approach to retrofitting contextualized embedding models with paraphrase contexts. Our method learns an orthogonal transformation on the input space, which seeks to minimize the variance of word representations on paraphrased contexts. Experiments show that the retrofitted model significantly outperforms the original ELMo on various sentence classification and language inference tasks.

📄 PDF Abstract BibTeX arXiv:1909.09700

Code (0)

등록된 구현이 없습니다.

Tasks

SentenceSentence ClassificationWord Embeddings

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
BiLSTM A Bidirectional LSTM, or biLSTM, is a sequence processing model that consists of two LSTMs: one taking the input in a forward direction, and the other in a backwards…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
ELMo Embeddings from Language Models, or ELMo, is a type of deep contextualized word representation that models both (1) complex characteristics of word use (e.g., syntax and…

Similar Papers 제목 키워드 기반

Using Paraphrases to Study Properties of Contextual Embeddings

2022-07-12 · NAACL 2022 7 · Laura Burdick, Jonathan K. Kummerfeld, Rada Mihalcea

We use paraphrases as a unique source of data to analyze contextualized embeddings, with a particular focus on BERT. Because paraphrases naturally encode consistent word and phrase semantics, they provide a unique lens f…

Using Context-to-Vector with Graph Retrofitting to Improve Word Embeddings

2022-10-30 · ACL 2022 5 · Jiangbin Zheng, Yile Wang, Ge Wang, Jun Xia 외

Although contextualized embeddings generated from large-scale pre-trained models perform well in many tasks, traditional static embeddings (e.g., Skip-gram, Word2Vec) still play an important role in low-resource and ligh…

Word EmbeddingsWord Similarity

Integrating Lexical Knowledge in Word Embeddings using Sprinkling and Retrofitting

2019-12-14 · ICON 2019 12 · Aakash Srinivasan, Harshavardhan Kamarthi, Devi Ganesan, Sutanu Chakraborti

Neural network based word embeddings, such as Word2Vec and GloVe, are purely data driven in that they capture the distributional information about words from the training corpus. Past works have attempted to improve thes…

Word Embeddings

Word Sense Induction using Knowledge Embeddings

2018-10-23 · Anonymous

Word Embeddings are able to capture lexico-semantic information but remain flawed in their inability to assign unique representations to different senses of a polysemous words. They also fail to include information from …

Word EmbeddingsWord Sense Induction

Exploring Fine-Tuned Embeddings that Model Intensifiers for Emotion Analysis

2019-04-05 · WS 2019 6 · Laura Bostan, Roman Klinger

Adjective phrases like "a little bit surprised", "completely shocked", or "not stunned at all" are not handled properly by currently published state-of-the-art emotion classification and intensity prediction systems whic…

Emotion ClassificationEmotion RecognitionGeneral ClassificationWord Embeddings