Tzuf Paz-Argaman - Academia.edu (original) (raw)

Uploads

Papers by Tzuf Paz-Argaman

Findings of the Association for Computational Linguistics: EMNLP 2020, 2020

We study the problem of recognizing visual entities from the textual descriptions of their classe... more We study the problem of recognizing visual entities from the textual descriptions of their classes. Specifically, given birds' images with free-text descriptions of their species, we learn to classify images of previously-unseen species based on specie descriptions. This setup has been studied in the vision community under the name zero-shot learning from text, focusing on learning to transfer knowledge about visual aspects of birds from seen classes to previously-unseen ones. Here, we suggest focusing on the textual description and distilling from the description the most relevant information to effectively match visual features to the parts of the text that discuss them. Specifically, (1) we propose to leverage the similarity between species, reflected in the similarity between text descriptions of the species. (2) we derive visual summaries of the texts, i.e., extractive summaries that focus on the visual features that tend to be reflected in images. We propose a simple attention-based model augmented with the similarity and visual summaries components. Our empirical results consistently and significantly outperform the state-of-the-art on the largest benchmarks for text-based zero-shot learning, illustrating the critical importance of texts for zero-shot image-recognition.

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), 2019

Following navigation instructions in natural language requires a composition of language, action,... more Following navigation instructions in natural language requires a composition of language, action, and knowledge of the environment. Knowledge of the environment may be provided via visual sensors or as a symbolic world representation referred to as a map. Here we introduce the Realistic Urban Navigation (RUN) task, aimed at interpreting navigation instructions based on a real, dense, urban map. Using Amazon Mechanical Turk, we collected a dataset of 2515 instructions aligned with actual routes over three regions of Manhattan. We propose a strong baseline for the task and empirically investigate which aspects of the neural architecture are important for the RUN success. Our results empirically show that entity abstraction, attention over words and worlds, and a constantly updating world-state, significantly contribute to task accuracy.

Findings of the Association for Computational Linguistics: ACL 2023

The task of textual geolocation-retrieving the coordinates of a place based on a free-form langua... more The task of textual geolocation-retrieving the coordinates of a place based on a free-form language description-calls for not only grounding but also natural language understanding and geospatial reasoning. Even though there are quite a few datasets in English used for geolocation, they are currently based on open-source data (Wikipedia and Twitter), where the location of the described place is mostly implicit, such that the location retrieval resolution is limited. Furthermore, there are no datasets available for addressing the problem of textual geolocation in morphologically rich and resourcepoor languages, such as Hebrew. In this paper, we present the Hebrew Geo-Location (HeGeL) corpus, designed to collect literal place descriptions and analyze lingual geospatial reasoning. We crowdsourced 5,649 literal Hebrew place descriptions of various place types in three cities in Israel. Qualitative and empirical analysis show that the data exhibits abundant use of geospatial reasoning and requires a novel environmental representation. 1

Findings of the Association for Computational Linguistics: EMNLP 2020, 2020

We study the problem of recognizing visual entities from the textual descriptions of their classe... more We study the problem of recognizing visual entities from the textual descriptions of their classes. Specifically, given birds' images with free-text descriptions of their species, we learn to classify images of previously-unseen species based on specie descriptions. This setup has been studied in the vision community under the name zero-shot learning from text, focusing on learning to transfer knowledge about visual aspects of birds from seen classes to previously-unseen ones. Here, we suggest focusing on the textual description and distilling from the description the most relevant information to effectively match visual features to the parts of the text that discuss them. Specifically, (1) we propose to leverage the similarity between species, reflected in the similarity between text descriptions of the species. (2) we derive visual summaries of the texts, i.e., extractive summaries that focus on the visual features that tend to be reflected in images. We propose a simple attention-based model augmented with the similarity and visual summaries components. Our empirical results consistently and significantly outperform the state-of-the-art on the largest benchmarks for text-based zero-shot learning, illustrating the critical importance of texts for zero-shot image-recognition.

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), 2019

Following navigation instructions in natural language requires a composition of language, action,... more Following navigation instructions in natural language requires a composition of language, action, and knowledge of the environment. Knowledge of the environment may be provided via visual sensors or as a symbolic world representation referred to as a map. Here we introduce the Realistic Urban Navigation (RUN) task, aimed at interpreting navigation instructions based on a real, dense, urban map. Using Amazon Mechanical Turk, we collected a dataset of 2515 instructions aligned with actual routes over three regions of Manhattan. We propose a strong baseline for the task and empirically investigate which aspects of the neural architecture are important for the RUN success. Our results empirically show that entity abstraction, attention over words and worlds, and a constantly updating world-state, significantly contribute to task accuracy.

Findings of the Association for Computational Linguistics: ACL 2023

The task of textual geolocation-retrieving the coordinates of a place based on a free-form langua... more The task of textual geolocation-retrieving the coordinates of a place based on a free-form language description-calls for not only grounding but also natural language understanding and geospatial reasoning. Even though there are quite a few datasets in English used for geolocation, they are currently based on open-source data (Wikipedia and Twitter), where the location of the described place is mostly implicit, such that the location retrieval resolution is limited. Furthermore, there are no datasets available for addressing the problem of textual geolocation in morphologically rich and resourcepoor languages, such as Hebrew. In this paper, we present the Hebrew Geo-Location (HeGeL) corpus, designed to collect literal place descriptions and analyze lingual geospatial reasoning. We crowdsourced 5,649 literal Hebrew place descriptions of various place types in three cities in Israel. Qualitative and empirical analysis show that the data exhibits abundant use of geospatial reasoning and requires a novel environmental representation. 1