Results 1 to 10 of about 138,423 (180)

Combining computational linguistics with sentence embedding to create a zero-shot NLIDB

Array
Accessing relational databases using natural language is a challenging task, with existing methods often suffering from poor domain generalization and high computational costs. In this study, we propose a novel approach that eliminates the training phase while offering high adaptability across domains. Our method combines structured linguistic rules, a
Mauro Castelli
exaly   +3 more sources

Zero-shot Cross-Linguistic Learning of Event Semantics

Proceedings of the 15th International Conference on Natural Language Generation, 2022
Typologically diverse languages offer systems of lexical and grammatical aspect that allow speakers to focus on facets of event structure in ways that comport with the specific communicative setting and discourse constraints they face. In this paper, we look specifically at captions of images across Arabic, Chinese, Farsi, German, Russian, and Turkish ...
Malihe Alikhani, Thomas Kober 0001, Bashar Alhafni, Yue Chen, Mert Inan, Elizabeth Nielsen, Shahab Raji, Mark Steedman, Matthew Stone   +8 more
openaire   +4 more sources

Gaussian Visual-Linguistic Embedding for Zero-Shot Recognition [PDF]

Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, 2016
An exciting outcome of research at the intersection of language and vision is that of zeroshot learning (ZSL). ZSL promises to scale visual recognition by borrowing distributed semantic models learned from linguistic corpora and turning them into visual recognition models.
Tanmoy Mukherjee, Timothy M. Hospedales
openaire   +2 more sources

Inflectional zero morphology – Linguistic myth or neurocognitive reality?

Frontiers in Psychology, 2022
Knowledge of language, its structure and grammar are an essential part of our education and daily activities. Despite the importance of language in our lives, linguistic theories that explain how the language system operates are often disconnected from our knowledge of the brain’s neurocognitive mechanisms underpinning the linguistic function.
Maria Alekseeva, Andriy Myachykov, Andriy Myachykov, Yury Shtyrov   +3 more
openaire   +4 more sources

Linguistically-Enriched and Context-AwareZero-shot Slot Filling [PDF]

Proceedings of the Web Conference 2021, 2021
Slot filling is identifying contiguous spans of words in an utterance that correspond to certain parameters (i.e., slots) of a user request/query. Slot filling is one of the most important challenges in modern task-oriented dialog systems. Supervised learning approaches have proven effective at tackling this challenge, but they need a significant ...
A. B. Siddique 0001, Fuad T. Jamour, Vagelis Hristidis   +2 more
openaire   +2 more sources

Faster Zero-shot Multi-modal Entity Linking via Visual-Linguistic Representation [PDF]

Data Intelligence, 2022
Abstract Multi-modal entity linking plays a crucial role in a wide range of knowledge-based modal-fusion tasks, i.e., multi-modal retrieval and multi-modal event extraction. We introduce the new ZEro-shot Multi-modal Entity Linking (ZEMEL) task, the format is similar to multi-modal entity linking, but multi-modal mentions are linked to ...
Qiushuo Zheng, Hao Wen 0005, Meng Wang 0009, Guilin Qi, Chaoyu Bai   +4 more
openaire   +1 more source

ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models

CoRR, 2023
Preprint.
Kesen, İlker, Pedrotti, Andrea, Dogan, Mustafa, Cafagna, Michele, Acikgoz, Emre Can, Parcalabescu, Letitia, Calixto, Iacer, Frank, Anette, Gatt, Albert, Erdem, Aykut, Erdem, Erkut   +10 more
openaire   +5 more sources

PERFORMING ANAPHORA IN MODERN GREEK: A NEO-GRICEAN PRAGMATIC ANALYSIS [PDF]

, 2013
The paper addresses the problem of interpreting anaphoric NPs in Modern Greek. It includes a proposal of a novel analysis based on the systematic interaction of the neo- Gricean pragmatic principles of communication, which provides a neat and elegant ...
Anagnostopoulou, Anagnostopoulou, Arlenga, Arlenga, Arlenga, Arlenga, Blackwell, Blackwell, Blackwell, Blackwell, Blackwell, Blackwell, Blackwell, Blackwell, Cambridge, Cambridge, Cambridge, Cambridge, Chiou, Chiou, Culy, Culy, Culy, Culy, Dowty, Dowty, Fox, Fox, Frey, Frey, Grice, Grice, Grice, Grice, Grice, Grice, Grodzinsky, Grodzinsky, Haspelmath, Haspelmath, Holton, Holton, Horn, Horn, Huang, Huang, Huang, Huang, Huang, Huang, Huang, Huang, Iatridou, Iatridou, Iatridou, Iatridou, Iatridou, Iatridou, Joseph, Joseph, Karamanis, Karamanis, Kempson, Kempson, Kempson, Kempson, Kempson, Kempson, Kempson, Kempson, Kiparsky, Kiparsky, Koopman, Koopman, Kordoni, Kordoni, Lapata, Lapata, Levinson, Levinson, Levinson, Levinson, Levinson, Levinson, Mackridge, Mackridge, Michael Chiou, Miltsakaki, Miltsakaki, Philippaki, Philippaki, Philippaki, Philippaki, Praeger, Praeger, Reinhart, Reinhart, Reinhart, Reinhart, Runner, Runner, Sells, Sells, Susumu, Susumu, Terzi, Terzi, Valiouli, Valiouli, Varlokosta, Varlokosta, Varlokosta, Varlokosta, Varlokosta, Varlokosta, Zribi, Zribi, Zribi, Zribi   +118 more
core   +2 more sources

Automatic linguistic analysis for language teachers [PDF]

Proceedings of the 19th international conference on Computational linguistics -, 2002
This paper presents the Natural Language Processing-based linguistic analysis tool that we have developed for Japanese as a Second Language teachers. This program, Zero Detector (ZD), aims to promote effective instruction of zero anaphora, on the basis of a hypothesis about ideal conditions for second language acquisition, by making invisible zeros ...
Mitsuko Yamura-Takei, Miho Fujiwara, Makoto Yoshie, Teruaki Aizawa   +3 more
openaire   +2 more sources

Exploring Linguistic Similarity and Zero-Shot Learning for Multilingual Translation of Dravidian Languages

CoRR, 2023
Current research in zero-shot translation is plagued by several issues such as high compute requirements, increased training time and off target translations. Proposed remedies often come at the cost of additional data or compute requirements. Pivot based neural machine translation is preferred over a single-encoder model for most settings despite the ...
Danish Mohammed Ebadulla, Rahul Raman, S. Natarajan, Hridhay Kiran Shetty, Ashish Harish Shenoy   +4 more
openaire   +2 more sources