Training robot policies in the real world can be unsafe, costly, and difficult to scale. Simulation serves as an inexpensive and potentially limitless source of training data, but suffers from the semantics and physics disparity between simulated and...
We consider the problem of translating high-level textual descriptions to formal representations in technical documentation as part of an effort to model the meaning of such documentation. We focus specifically on the problem of learning translationa...
[CVPR2024] SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution (⭐ 616)
Does the grammatical gender of a language interfere when measuring the semantic gender information captured by its word embeddings? A number of anomalous gender bias measurements in the embeddings of gendered languages suggest this possibility. We de...
How does the input segmentation of pretrained language models (PLMs) affect their interpretations of complex words? We present the first study investigating this question, taking BERT as the example PLM and focusing on its semantic representations of...
This paper reports on Qwant Research contribution to tasks 2 and 3 of the DEFT 2019's challenge, focusing on French clinical cases analysis. Task 2 is a task on semantic similarity between clinical cases and discussions. For this task, we propose an...
Multimodal large-scale datasets for outdoor scenes are mostly designed for urban driving problems. The scenes are highly structured and semantically different from scenarios seen in nature-centered scenes such as gardens or parks. To promote machine...
A simple CSS for styling semantic HTML. (⭐ 2)
Points: 7 | Comments: 2 | Author: kemar
We extend the 0-approximation of sensing actions and incomplete information in [Son and Baral 2000] to action theories with static causal laws and prove its soundness with respect to the possible world semantics. We also show that the conditional p...
First-order logic (FOL) can represent the logical entailment semantics of natural language (NL) sentences, but determining natural language entailment using FOL remains a challenge. To address this, we propose the Entailment-Preserving FOL representa...
Capturing semantic relations between sentences, such as entailment, is a long-standing challenge for computational semantics. Logic-based models analyse entailment in terms of possible worlds (interpretations, or situations) where a premise P entails...
Verbs form the backbone of language, providing the structure and meaning to sentences. Yet, their intricate semantic nuances pose a longstanding challenge. Understanding verb relations through the concept of lexical entailment is crucial for comprehe...
linguistic semantics, a downward entailing (DE) propositional operator is one that constrains the meaning of an expression to a lower number or degree than
Natural Language Inference is fundamental to many Natural Language Processing applications such as semantic search and question answering. The task of NLI has gained significant attention in the recent times due to the release of fairly large scale, challenging datasets. Present…
The Shape Calculus is a bio-inspired calculus for describing 3D shapes moving in a space. A shape forms a 3D process when combined with a behaviour. Behaviours are specified with a timed CCS-like process algebra using a notion of channel that models...
Due to the limited scale and quality of video-text training corpus, most vision-language foundation models employ image-text datasets for pretraining and primarily focus on modeling visually semantic representations while disregarding temporal semant...
? Drop-in semantic styling library in pure CSS. Highly customizable and perfect for simple websites and prototyping web apps! (⭐ 1934)
C is an unsafe language. Researchers have been developing tools to port C to safer languages such as Rust, Checked C, or Go. Existing tools, however, resort to preprocessing the source file first, then porting the resulting code, leaving barely recog...
With the increasing use of conversational AI systems, there is growing concern over privacy leaks, especially when users share sensitive personal data in interactions with Large Language Models (LLMs). Conversations shared with these models may conta...
Can we train a system that, on any new input, either says "don't know" or makes a prediction that is guaranteed to be correct? We answer the question in the affirmative provided our model family is well-specified. Specifically, we introduce the unani...
Semantic conflicts arise when a developer introduces changes to a codebase that unintentionally affect the behavior of changes integrated in parallel by other developers. Traditional merge tools are unable to detect such conflicts, so complementary t...
The assignment of weights to attacks in a classical Argumentation Framework allows to compute semantics by taking into account the different importance of each argument. We represent a Weighted Argumentation Framework by a non-binary matrix, and we c...
The article proposes a formal semantics of happiness and sadness modalities in imperfect information setting. It shows that these modalities are not definable through each other and gives a sound and complete axiomatization of their properties....
This is the text of my speech at the Logica Universalis webinar, which took place on May 11, 2022. I discuss two ways to implement a semantic approach to nonmonotonic consequence relations in an arbitrary propositional language. For one particular...
Language-specified mobile manipulation tasks in novel environments simultaneously face challenges interacting with a scene which is only partially observed, grounding semantic information from language instructions to the partially observed scene, an...
In recent years, large language models (LLMs) have had great success in tasks such as casual conversation, contributing to significant advancements in domains like virtual assistance. However, they often generate responses that are not aligned with h...
Unsupervised panoptic segmentation aims to partition an image into semantically meaningful regions and distinct object instances without training on manually annotated data. In contrast to prior work on unsupervised panoptic scene understanding, we e...
Logic programming is a declarative programming paradigm. Programming language Prolog makes logic programming possible, at least to a substantial extent. However the Prolog debugger works solely in terms of the operational semantics. So it is incompat...
questions and commands. For example, inquisitive semantics is a framework that treats questions as inquisitive propositions, which encode information
This paper explores how natural-language descriptions of formal languages can be compared to their formal representations and how semantic differences can be explained. This is motivated from educational scenarios where learners describe a formal lan...
Landsat imagery is an unparalleled freely available data source that allows reconstructing horizontal and vertical urban form. This paper addresses the challenge of using Landsat data, particularly its 30m spatial resolution, for monitoring three-dim...
Purpose: We propose a 2.5D deep learning neural network (DLNN) to automatically classify thigh muscle into 11 classes and evaluate its classification accuracy over 2D and 3D DLNN when trained with limited datasets. Enables operator invariant quantita...
Figures in scientific publications contain important information and results, and alt text is needed for blind and low vision readers to engage with their content. We conduct a study to characterize the semantic content of alt text in HCI publication...
We present a formal model of Checked C, a dialect of C that aims to enforce spatial memory safety. Our model pays particular attention to the semantics of dynamically sized, potentially null-terminated arrays. We formalize this model in Coq, and prov...
[NAACL 2021] Reading and Acting while Blindfolded: The Need for Semantics in Text Game Agents (⭐ 11)
Semantic maps allow a robot to reason about its surroundings to fulfill tasks such as navigating known environments, finding specific objects, and exploring unmapped areas. Traditional mapping approaches provide accurate geometric representations but...
The four-valued semantics of Belnap--Dunn logic, consisting of the truth values True, False, Neither, and Both, gives rise to several non-classical logics depending on which feature of propositions we wish to preserve: truth, non-falsity, or exact tr...
Audio-text relevance learning refers to learning the shared semantic properties of audio samples and textual descriptions. The standard approach uses binary relevances derived from pairs of audio samples and their human-provided captions, categorizin...
Do unsupervised methods for learning rich, contextualized token representations obviate the need for explicit modeling of linguistic structure in neural network models for semantic role labeling (SRL)? We address this question by incorporating the ma...