paper-with-me

Papers

Combining Language and Vision with a Multimodal Skip-gram Model

2015-01-12 · HLT 2015 5 · Angeliki Lazaridou, Nghia The Pham, Marco Baroni

We extend the SKIP-GRAM model of Mikolov et al. (2013a) by taking visual information into account. Like SKIP-GRAM, our multimodal models (MMSKIP-GRAM) build vector-based word representations by learning to predict linguistic contexts in text corpora. However, for a restricted set of words, the models are also exposed to visual representations of the objects they denote (extracted from natural images), and must predict linguistic and visual features jointly. The MMSKIP-GRAM models achieve good performance on a variety of semantic benchmarks. Moreover, since they propagate visual information to all words, we use them to improve image labeling and retrieval in the zero-shot setup, where the test concepts are never seen during model training. Finally, the MMSKIP-GRAM models discover intriguing visual properties of abstract words, paving the way to realistic implementations of embodied theories of meaning.

📄 PDF Abstract BibTeX arXiv:1501.02598

Code (0)

등록된 구현이 없습니다.

Tasks

Retrieval

Similar Papers 제목 키워드 기반

Skip-gram Language Modeling Using Sparse Non-negative Matrix Probability Estimation

2014-12-03 · Noam Shazeer, Joris Pelemans, Ciprian Chelba

We present a novel family of language model (LM) estimation techniques named Sparse Non-negative Matrix (SNM) estimation. A first set of experiments empirically evaluating it on the One Billion Word Benchmark shows that …

Language ModelingLanguage Modelling

SubGram: Extending Skip-gram Word Representation with Substrings

2018-06-18 · Tom Kocmi, Ondřej Bojar

Skip-gram (word2vec) is a recent method for creating vector representations of words ("distributed word representations") using a neural network. The representation gained popularity in various areas of natural language …

PolyUCOMP: Combining Semantic Vectors with Skip bigrams for Semantic Textual Similarity

2012-07-01 · SEMEVAL 2012 7 · Jian Xu, Qin Lu, Zhengzhong Liu
Question AnsweringSemantic Textual SimilarityText Summarization

Skip-Vision: Efficient and Scalable Acceleration of Vision-Language Models via Adaptive Token Skipping

2025-03-26 · Weili Zeng, Ziyuan Huang, Kaixiang Ji, Yichao Yan

Transformer-based models have driven significant advancements in Multimodal Large Language Models (MLLMs), yet their computational costs surge drastically when scaling resolution, training data, and model parameters. A k…

A Probabilistic Model for Joint Learning of Word Embeddings from Texts and Images

2018-10-01 · EMNLP 2018 10 · Melissa Ailem, Bo-Wen Zhang, Aurelien Bellet, Pascal Denis 외

Several recent studies have shown the benefits of combining language and perception to infer word embeddings. These multimodal approaches either simply combine pre-trained textual and visual representations (e.g. feature…

Coreference ResolutionImage ClassificationQuestion AnsweringRetrieval+3