# Language Features Matter: Effective Language Representations for Vision-Language Tasks

arXiv: https://arxiv.org/abs/1908.06327 · HTML: https://mlsanity.com/paper/1908.06327/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Aug 2019.

## Built on by (most cited first, 4 of 4)

- [TEACHTEXT: CrossModal Generalized Distillation for Text-Video Retrieval](https://mlsanity.com/paper/2104.08271/) (2021)
- [Sign Language Video Retrieval with Free-Form Textual Queries](https://mlsanity.com/paper/2201.02495/) (2022)
- [Telling the What while Pointing to the Where: Multimodal Queries for Image Retrieval](https://mlsanity.com/paper/2102.04980/) (2021)
- [Learning Zero-Shot Multifaceted Visually Grounded Word Embeddings via Multi-Task Training](https://mlsanity.com/paper/2104.07500/) (2021)

## Abstract (arXiv)

Shouldn't language and vision features be treated equally in vision-language (VL) tasks? Many VL approaches treat the language component as an afterthought, using simple language models that are either built upon fixed word embeddings trained on text-only data or are learned from scratch. We believe that language features deserve more attention, and conduct experiments which compare different word embeddings, language models, and embedding augmentation steps on five common VL tasks: image-sentence retrieval, image captioning, visual question answering, phrase grounding, and text-to-clip retrieval. Our experiments provide some striking results; an average embedding language model outperforms an LSTM on retrieval-style tasks; state-of-the-art representations such as BERT perform relatively poorly on vision-language tasks. From this comprehensive set of experiments we propose a set of best practices for incorporating the language component of VL tasks. To further elevate language features, we also show that knowledge in vision-language problems can be transferred across tasks to gain performance with multi-task training. This multi-task training is applied to a new Graph Oriented Vision-Language Embedding (GrOVLE), which we adapt from Word2Vec using WordNet and an original visual-language graph built from Visual Genome, providing a ready-to-use vision-language embedding: http://ai.bu.edu/grovle.