Výsledky vyhledávání

Report

Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of Reference Under Ambiguities

Autor: Zhang, Zheyuan, Hu, Fengyuan, Lee, Jayjun, Shi, Freda, Kordjamshidi, Parisa, Chai, Joyce, Ma, Ziqiao

Spatial expressions in situated communication can be ambiguous, as their meanings vary depending on the frames of reference (FoR) adopted by speakers and listeners. While spatial language understanding and reasoning by vision-language models (VLMs) h

Externí odkaz: http://arxiv.org/abs/2410.17385

Zobrazit plný text záznamu

Report

Gated Slot Attention for Efficient Linear-Time Sequence Modeling

Autor: Zhang, Yu, Yang, Songlin, Zhu, Ruijie, Zhang, Yue, Cui, Leyang, Wang, Yiqiao, Wang, Bolun, Shi, Freda, Wang, Bailin, Bi, Wei, Zhou, Peng, Fu, Guohong

Linear attention Transformers and their gated variants, celebrated for enabling parallel training and efficient recurrent inference, still fall short in recall-intensive tasks compared to traditional Transformers and demand significant resources for

Externí odkaz: http://arxiv.org/abs/2409.07146

Zobrazit plný text záznamu

Report

LogogramNLP: Comparing Visual and Textual Representations of Ancient Logographic Writing Systems for NLP

Autor: Chen, Danlu, Shi, Freda, Agarwal, Aditi, Myerston, Jacobo, Berg-Kirkpatrick, Taylor

Publikováno v: ACL 2024, long paper

Standard natural language processing (NLP) pipelines operate on symbolic representations of language, which typically consist of sequences of discrete tokens. However, creating an analogous representation for ancient logographic writing systems is an

Externí odkaz: http://arxiv.org/abs/2408.04628

Zobrazit plný text záznamu

Report

Learning Language Structures through Grounding

Autor: Shi, Freda

Language is highly structured, with syntactic and semantic structures, to some extent, agreed upon by speakers of the same language. With implicit or explicit awareness of such structures, humans can learn and use language efficiently and generalize

Externí odkaz: http://arxiv.org/abs/2406.09662

Zobrazit plný text záznamu

Report

Structured Tree Alignment for Evaluation of (Speech) Constituency Parsing

Autor: Shi, Freda, Gimpel, Kevin, Livescu, Karen

We present the structured average intersection-over-union ratio (STRUCT-IOU), a similarity metric between constituency parse trees motivated by the problem of evaluating speech parsers. STRUCT-IOU enables comparison between a constituency parse tree

Externí odkaz: http://arxiv.org/abs/2402.13433

Zobrazit plný text záznamu