Analyzing The Language of Visual Tokens

• URL: http://arxiv.org/abs/2411.05001v1
• Date: Thu, 07 Nov 2024 18:59:28 GMT
• Title: Analyzing The Language of Visual Tokens
• Authors: David M. Chan, Rodolfo Corona, Joonyong Park, Cheol Jun Cho, Yutong Bai, Trevor Darrell,
• Abstract summary: We take a natural-language-centric approach to analyzing discrete visual languages. We show that higher token innovation drives greater entropy and lower compression, with tokens predominantly representing object parts. We also show that visual languages lack cohesive grammatical structures, leading to higher perplexity and weaker hierarchical organization compared to natural languages.
• Score: 48.62180485759458
• License:
• Abstract: With the introduction of transformer-based models for vision and language tasks, such as LLaVA and Chameleon, there has been renewed interest in the discrete tokenized representation of images. These models often treat image patches as discrete tokens, analogous to words in natural language, learning joint alignments between visual and human languages. However, little is known about the statistical behavior of these visual languages - whether they follow similar frequency distributions, grammatical structures, or topologies as natural languages. In this paper, we take a natural-language-centric approach to analyzing discrete visual languages and uncover striking similarities and fundamental differences. We demonstrate that, although visual languages adhere to Zipfian distributions, higher token innovation drives greater entropy and lower compression, with tokens predominantly representing object parts, indicating intermediate granularity. We also show that visual languages lack cohesive grammatical structures, leading to higher perplexity and weaker hierarchical organization compared to natural languages. Finally, we demonstrate that, while vision models align more closely with natural languages than other models, this alignment remains significantly weaker than the cohesion found within natural languages. Through these experiments, we demonstrate how understanding the statistical properties of discrete visual languages can inform the design of more effective computer vision models.

Related papers

• MulCogBench: A Multi-modal Cognitive Benchmark Dataset for Evaluating Chinese and English Computational Language Models [44.74364661212373]
  This paper proposes MulCogBench, a cognitive benchmark dataset collected from native Chinese and English participants. It encompasses a variety of cognitive data, including subjective semantic ratings, eye-tracking, functional magnetic resonance imaging (fMRI) and magnetoencephalography (MEG) Results show that language models share significant similarities with human cognitive data and the similarity patterns are modulated by the data modality and stimuli complexity.
  arXiv  Detail & Related papers  (2024-03-02T07:49:57Z)
• Transparency Helps Reveal When Language Models Learn Meaning [71.96920839263457]
  Our systematic experiments with synthetic data reveal that, with languages where all expressions have context-independent denotations, both autoregressive and masked language models learn to emulate semantic relations between expressions. Turning to natural language, our experiments with a specific phenomenon -- referential opacity -- add to the growing body of evidence that current language models do not well-represent natural language semantics.
  arXiv  Detail & Related papers  (2022-10-14T02:35:19Z)
• Linking Emergent and Natural Languages via Corpus Transfer [98.98724497178247]
  We propose a novel way to establish a link by corpus transfer between emergent languages and natural languages. Our approach showcases non-trivial transfer benefits for two different tasks -- language modeling and image captioning. We also introduce a novel metric to predict the transferability of an emergent language by translating emergent messages to natural language captions grounded on the same images.
  arXiv  Detail & Related papers  (2022-03-24T21:24:54Z)
• Oracle Linguistic Graphs Complement a Pretrained Transformer Language Model: A Cross-formalism Comparison [13.31232311913236]
  We examine the extent to which, in principle, linguistic graph representations can complement and improve neural language modeling. We find that, overall, semantic constituency structures are most useful to language modeling performance.
  arXiv  Detail & Related papers  (2021-12-15T04:29:02Z)
• Controlled Evaluation of Grammatical Knowledge in Mandarin Chinese Language Models [22.57309958548928]
  We investigate whether structural supervision improves language models' ability to learn grammatical dependencies in typologically different languages. We train LSTMs, Recurrent Neural Network Grammars, Transformer language models, and generative parsing models on datasets of different sizes. We find suggestive evidence that structural supervision helps with representing syntactic state across intervening content and improves performance in low-data settings.
  arXiv  Detail & Related papers  (2021-09-22T22:11:30Z)
• Discovering Representation Sprachbund For Multilingual Pre-Training [139.05668687865688]
  We generate language representation from multilingual pre-trained models and conduct linguistic analysis. We cluster all the target languages into multiple groups and name each group as a representation sprachbund. Experiments are conducted on cross-lingual benchmarks and significant improvements are achieved compared to strong baselines.
  arXiv  Detail & Related papers  (2021-09-01T09:32:06Z)
• Vokenization: Improving Language Understanding with Contextualized, Visual-Grounded Supervision [110.66085917826648]
  We develop a technique that extrapolates multimodal alignments to language-only data by contextually mapping language tokens to their related images. "vokenization" is trained on relatively small image captioning datasets and we then apply it to generate vokens for large language corpora. Trained with these contextually generated vokens, our visually-supervised language models show consistent improvements over self-supervised alternatives on multiple pure-language tasks.
  arXiv  Detail & Related papers  (2020-10-14T02:11:51Z)
• Bridging Linguistic Typology and Multilingual Machine Translation with Multi-View Language Representations [83.27475281544868]
  We use singular vector canonical correlation analysis to study what kind of information is induced from each source. We observe that our representations embed typology and strengthen correlations with language relationships. We then take advantage of our multi-view language vector space for multilingual machine translation, where we achieve competitive overall translation accuracy.
  arXiv  Detail & Related papers  (2020-04-30T16:25:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.