paper-with-me

홈 › Papers

Charagram: Embedding Words and Sentences via Character n-grams

2016-07-10 · EMNLP 2016 11 · John Wieting, Mohit Bansal, Kevin Gimpel, Karen Livescu

We present Charagram embeddings, a simple approach for learning character-based compositional models to embed textual sequences. A word or sentence is represented using a character n-gram count vector, followed by a single nonlinear transformation to yield a low-dimensional embedding. We use three tasks for evaluation: word similarity, sentence similarity, and part-of-speech tagging. We demonstrate that Charagram embeddings outperform more complex architectures based on character-level recurrent and convolutional neural networks, achieving new state-of-the-art performance on several similarity tasks.

📄 PDF Abstract BibTeX arXiv:1607.02789

Code (0)

등록된 구현이 없습니다.

Tasks

Part-Of-Speech TaggingSentenceSentence SimilarityWord Similarity

Similar Papers 제목 키워드 기반

Segmentation-free Compositional $n$-gram Embedding

2018-09-04 · NAACL 2019 6 · Geewook Kim, Kazuki Fukui, Hidetoshi Shimodaira

We propose a new type of representation learning method that models words, phrases and sentences seamlessly. Our method does not depend on word segmentation and any human-annotated resources (e.g., word dictionaries), ye…

Representation LearningSegmentationWord Embeddings

Fast and Accurate Transformer-based Translation with Character-Level Encoding and Subword-Level Decoding

2021-11-16 · ACL ARR November 2021 11 · Anonymous

The Transformer translation model is fast to train and achieves state-of-the-art results for various translation tasks. However, unknown input words at test time remain a challenge for the Transformer, especially when …

DecoderTranslation

Convolutional Neural Network for Universal Sentence Embeddings

2018-08-01 · COLING 2018 8 · Xiaoqi Jiao, Fang Wang, Dan Feng

This paper proposes a simple CNN model for creating general-purpose sentence embeddings that can transfer easily across domains and can also act as effective initialization for downstream tasks. Recently, averaging the e…

Semantic Textual SimilaritySentenceSentence EmbeddingsTransfer Learning+1

Word-like character n-gram embedding

2018-11-01 · WS 2018 11 · Geewook Kim, Kazuki Fukui, Hidetoshi Shimodaira

We propose a new word embedding method called \textit{word-like character} n\textit{-gram embedding}, which learns distributed representations of words by embedding word-like character n-grams. Our method is an extension…

SegmentationWord Embeddings

Addressing Low-Resource Scenarios with Character-aware Embeddings

2018-06-01 · WS 2018 6 · Sean Papay, Sebastian Pad{\'o}, Ngoc Thang Vu

Most modern approaches to computing word embeddings assume the availability of text corpora with billions of words. In this paper, we explore a setup where only corpora with millions of words are available, and many word…

Morphological AnalysisWord Embeddings