paper-with-me

Papers

Comparatives, Quantifiers, Proportions: A Multi-Task Model for the Learning of Quantities from Vision

2018-04-13 · NAACL 2018 6 · Sandro Pezzelle, Ionut-Teodor Sorodoc, Raffaella Bernardi

The present work investigates whether different quantification mechanisms (set comparison, vague quantification, and proportional estimation) can be jointly learned from visual scenes by a multi-task computational model. The motivation is that, in humans, these processes underlie the same cognitive, non-symbolic ability, which allows an automatic estimation and comparison of set magnitudes. We show that when information about lower-complexity tasks is available, the higher-level proportional task becomes more accurate than when performed in isolation. Moreover, the multi-task model is able to generalize to unseen combinations of target/non-target objects. Consistently with behavioral evidence showing the interference of absolute number in the proportional task, the multi-task model no longer works when asked to provide the number of target objects in the scene.

📄 PDF Abstract BibTeX arXiv:1804.05018

Code (1)

sandropezzelle/multitask-quant 공식 구현 tf

Similar Papers 제목 키워드 기반

Logical Inferences with Comparatives and Generalized Quantifiers

2020-05-16 · ACL 2020 6 · Izumi Haruta, Koji Mineshima, Daisuke Bekki

Comparative constructions pose a challenge in Natural Language Inference (NLI), which is the task of determining whether a text entails a hypothesis. Comparatives are structurally complex in that they interact with other…

Automated Theorem ProvingNatural Language Inference

Implementing a Logical Inference System for Japanese Comparatives

2025-09-17 · Yosuke Mikami, Daiki Matsuoka, Hitomi Yanaka arxiv

Natural Language Inference (NLI) involving comparatives is challenging because it requires understanding quantities and comparative relations expressed by sentences. While some approaches leverage Large Language Models (…

Natural Language Inference

Be Precise or Fuzzy: Learning the Meaning of Cardinals and Quantifiers from Vision

2017-02-17 · EACL 2017 4 · Sandro Pezzelle, Marco Marelli, Raffaella Bernardi

People can refer to quantities in a visual scene by using either exact cardinals (e.g. one, two, three) or natural language quantifiers (e.g. few, most, all). In humans, these two processes underlie fairly different cogn…

Pay Attention to Those Sets! Learning Quantification from Images

2017-04-10 · Ionut Sorodoc, Sandro Pezzelle, Aurélie Herbelot, Mariella Dimiccoli 외

Major advances have recently been made in merging language and vision representations. But most tasks considered so far have confined themselves to the processing of objects and lexicalised relations amongst objects (con…

Pragmatic Reasoning Unlocks Quantifier Semantics for Foundation Models

2023-11-08 · Yiyuan Li, Rakesh R. Menon, Sayan Ghosh, Shashank Srivastava

Generalized quantifiers (e.g., few, most) are used to indicate the proportions predicates are satisfied (for example, some apples are red). One way to interpret quantifier semantics is to explicitly bind these satisfacti…

Natural Language Inference