Search Results - "Kuhlmann, Marco"

Tractable Parsing for CCGs of Bounded Degree by Schiffer, Lena Katharina, Kuhlmann, Marco, Satta, Giorgio

“…Unlike other mildly context-sensitive formalisms, Combinatory Categorial Grammar (CCG) cannot be parsed in polynomial time when the size of the grammar is…”
Get full text

On the Complexity of CCG Parsing by Kuhlmann, Marco, Satta, Giorgio, Jonsson, Peter

“…We study the parsing complexity of Combinatory Categorial Grammar (CCG) in the formalism of Vijay-Shanker and Weir ( ). As our main result, we prove that any…”
Get full text

Finite-state methods and mathematics of language, introduction to the special issue by Kuhlmann, Marco, Wurm, Christian

Get full text

The tree-generative capacity of combinatory categorial grammars by Kuhlmann, Marco, Maletti, Andreas, Schiffer, Lena Katharina

“…The generative capacity of combinatory categorial grammars (CCGs) as generators of tree languages is investigated. It is demonstrated that the tree languages…”
Get full text

Balanced Product of Calibrated Experts for Long-Tailed Recognition by Aimar, Emanuel Sanchez, Jonnarth, Arvi, Felsberg, Michael, Kuhlmann, Marco

“…Many real-world recognition problems are characterized by long-tailed label distributions. These distributions make representation learning highly challenging…”
Get full text

Numerical simulation of carbon monoxide emissions from spark ignition engines by Raggi, Marco Valério Kuhlmann, Sodré, José Ricardo

“…This work describes a numerical model for calculation of carbon monoxide (CO) emissions from spark ignition engines. The model calculates CO concentration from…”
Get full text

Is cognitive impairment associated with reduced syntactic complexity in writing? Evidence from automated text analysis by Sand Aronsson, Fredrik, Kuhlmann, Marco, Jelic, Vesna, Östberg, Per

“…Background: Written language impairments are common in Alzheimer's disease and reduced syntactic complexity in written discourse has been observed decades…”
Get full text

Parsing to Noncrossing Dependency Graphs by Kuhlmann, Marco, Jonsson, Peter

“…We study the generalization of maximum spanning tree dependency parsing to maximum acyclic subgraphs. Because the underlying optimization problem is…”
Get full text

Properties and Challenges of LLM-Generated Explanations by Kunz, Jenny, Kuhlmann, Marco

“…The self-rationalising capabilities of large language models (LLMs) have been explored in restricted settings, using task/specific data sets. However, current…”
Get full text

A New Parsing Algorithm for Combinatory Categorial Grammar by Kuhlmann, Marco, Satta, Giorgio

“…We present a polynomial-time parsing algorithm for CCG, based on a new decomposition of derivations into small, shareable parts. Our algorithm has the same…”
Get full text

Efficient Parsing for Head-Split Dependency Trees by Satta, Giorgio, Kuhlmann, Marco

“…Head splitting techniques have been successfully exploited to improve the asymptotic runtime of parsing algorithms for projective dependency trees, under the…”
Get full text

NL2Plan: Robust LLM-Driven Planning from Minimal Text Descriptions by Gestrin, Elliot, Kuhlmann, Marco, Seipp, Jendrik

“…Today's classical planners are powerful, but modeling input tasks in formats such as PDDL is tedious and error-prone. In contrast, planning with Large Language…”
Get full text

How Reliable Are Automatic Evaluation Methods for Instruction-Tuned LLMs? by Doostmohammadi, Ehsan, Holmström, Oskar, Kuhlmann, Marco

“…Work on instruction-tuned Large Language Models (LLMs) has used automatic methods based on text overlap and LLM judgments as cost-effective alternatives to…”
Get full text

Fact Recall, Heuristics or Pure Guesswork? Precise Interpretations of Language Models for Fact Completion by Saynova, Denitsa, Hagström, Lovisa, Johansson, Moa, Johansson, Richard, Kuhlmann, Marco

“…Previous interpretations of language models (LMs) miss important distinctions in how these models process factual information. For example, given the query…”
Get full text

Surface-Based Retrieval Reduces Perplexity of Retrieval-Augmented Language Models by Doostmohammadi, Ehsan, Norlund, Tobias, Kuhlmann, Marco, Johansson, Richard

“…Augmenting language models with a retrieval mechanism has been shown to significantly improve their performance while keeping the number of parameters low…”
Get full text

Tabulation of Noncrossing Acyclic Digraphs by Kuhlmann, Marco

“…I present an algorithm that, given a number $n \geq 1$, computes a compact representation of the set of all noncrossing acyclic digraphs with $n$ nodes. This…”
Get full text

On the Generalization Ability of Retrieval-Enhanced Transformers by Norlund, Tobias, Doostmohammadi, Ehsan, Johansson, Richard, Kuhlmann, Marco

“…Recent work on the Retrieval-Enhanced Transformer (RETRO) model has shown that off-loading memory from trainable weights to a retrieval database can…”
Get full text

Balanced Product of Calibrated Experts for Long-Tailed Recognition by Aimar, Emanuel Sanchez, Jonnarth, Arvi, Felsberg, Michael, Kuhlmann, Marco

“…Many real-world recognition problems are characterized by long-tailed label distributions. These distributions make representation learning highly challenging…”
Get full text

Flexible Distribution Alignment: Towards Long-tailed Semi-supervised Learning with Proper Calibration by Aimar, Emanuel Sanchez, Helgesen, Nathaniel, Xu, Yonghao, Kuhlmann, Marco, Felsberg, Michael

“…Long-tailed semi-supervised learning (LTSSL) represents a practical scenario for semi-supervised applications, challenged by skewed labeled distributions that…”
Get full text

Maximum Pagenumber-k Subgraph is NP-Complete by Jonsson, Peter, Kuhlmann, Marco

“…Given a graph $G$ with a total order defined on its vertices, the Maximum Pagenumber-$k$ Subgraph Problem asks for a maximum subgraph $G'$ of $G$ such that…”
Get full text