Search Results for author: Miloš Stanojević

Found 12 papers, 4 papers with code

Modeling Incremental Language Comprehension in the Brain with Combinatory Categorial Grammar

no code implementations NAACL (CMCL) 2021 Miloš Stanojević, Shohini Bhattasali, Donald Dunagan, Luca Campanelli, Mark Steedman, Jonathan Brennan, John Hale

Hierarchical sentence structure plays a role in word-by-word human sentence comprehension, but it remains unclear how best to characterize this structure and unknown how exactly it would be recognized in a step-by-step process model.

Sentence

A Root of a Problem: Optimizing Single-Root Dependency Parsing

1 code implementation EMNLP 2021 Miloš Stanojević, Shay B. Cohen

We describe two approaches to single-root dependency parsing that yield significant speed ups in such parsing.

Dependency Parsing

Formal Basis of a Language Universal

no code implementations CL (ACL) 2021 Miloš Stanojević, Mark Steedman

Abstract Steedman (2020) proposes as a formal universal of natural language grammar that grammatical permutations of the kind that have given rise to transformational rules are limited to a class known to mathematicians and computer scientists as the “separable” permutations.

Machine Translation

Computing All Quantifier Scopes with CCG

1 code implementation IWCS (ACL) 2021 Miloš Stanojević, Mark Steedman

We present a method for computing all quantifer scopes that can be extracted from a single CCG derivation.

Multipath parsing in the brain

no code implementations31 Jan 2024 Berta Franzluebbers, Donald Dunagan, Miloš Stanojević, Jan Buys, John T. Hale

Humans understand sentences word-by-word, in the order that they hear them.

SynJax: Structured Probability Distributions for JAX

3 code implementations7 Aug 2023 Miloš Stanojević, Laurent Sartran

The development of deep learning software libraries enabled significant progress in the field by allowing users to focus on modeling, while letting the library to take care of the tedious and time-consuming task of optimizing execution for modern hardware accelerators.

Unbiased and Efficient Sampling of Dependency Trees

no code implementations25 May 2022 Miloš Stanojević

However, the majority of dependency treebanks require that every valid dependency tree has a single edge coming out of the ROOT node, a constraint that is not part of the definition of spanning trees.

valid

Transformer Grammars: Augmenting Transformer Language Models with Syntactic Inductive Biases at Scale

no code implementations1 Mar 2022 Laurent Sartran, Samuel Barrett, Adhiguna Kuncoro, Miloš Stanojević, Phil Blunsom, Chris Dyer

We find that TGs outperform various strong baselines on sentence-level language modeling perplexity, as well as on multiple syntax-sensitive language modeling evaluation metrics.

Inductive Bias Language Modelling +1

Modality and Negation in Event Extraction

1 code implementation ACL (CASE) 2021 Sander Bijl de Vroe, Liane Guillou, Miloš Stanojević, Nick McKenna, Mark Steedman

Language provides speakers with a rich system of modality for expressing thoughts about events, without being committed to their actual occurrence.

Event Extraction Fact Checking +3

Removing Biases from Trainable MT Metrics by Using Self-Training

no code implementations10 Aug 2015 Miloš Stanojević

Our solution is more general: (1) it does not address only the recall bias but also all other biases that might be present in the data and (2) it does not require any knowledge of the types of features used which is useful in cases when manual tuning of metric's weights is not possible.

Domain Adaptation Machine Translation +1

Cannot find the paper you are looking for? You can Submit a new open access paper.