Search Results for author: Staffan Larsson

Found 17 papers, 1 papers with code

Bayesian Classification and Inference in a Probabilistic Type Theory with Records

no code implementations ACL (NALOMA, IWCS) 2021 Staffan Larsson, Robin Cooper

We propose a probabilistic account of semantic inference and classification formulated in terms of probabilistic type theory with records, building on Cooper et.

Classification Vocal Bursts Type Prediction

Discrete and Probabilistic Classifier-based Semantics

no code implementations PaM 2020 Staffan Larsson

We present a formal semantics (a version of Type Theory with Records) which places classifiers of perceptual information at the core of semantics.

Classification

Semantic Classification and Learning Using a Linear Tranformation Model in a Probabilistic Type Theory with Records

no code implementations ReInAct 2021 Staffan Larsson, Jean-Philippe Bernardy

Starting from an existing account of semantic classification and learning from interaction formulated in a Probabilistic Type Theory with Records, encompassing Bayesian inference and learning with a frequentist flavour, we observe some problems with this account and provide an alternative account of classification learning that addresses the observed problems.

Bayesian Inference Classification

In Search of Meaning and Its Representations for Computational Linguistics

no code implementations CLASP 2022 Simon Dobnik, Robin Cooper, Adam Ek, Bill Noble, Staffan Larsson, Nikolai Ilinykh, Vladislav Maraev, Vidya Somashekarappa

In this paper we examine different meaning representations that are commonly used in different natural language applications today and discuss their limits, both in terms of the aspects of the natural language meaning they are modelling and in terms of the aspects of the application for which they are used.

Evaluating N-best Calibration of Natural Language Understanding for Dialogue Systems

1 code implementation SIGDIAL (ACL) 2022 Ranim Khojah, Alexander Berman, Staffan Larsson

A Natural Language Understanding (NLU) component can be used in a dialogue system to perform intent classification, returning an N-best list of hypotheses with corresponding confidence estimates.

Classification intent-classification +2

Topic and genre in dialogue

no code implementations6 Dec 2023 Amandine Decker, Ellen Breitholtz, Christine Howes, Staffan Larsson

In this paper we argue that topic plays a fundamental role in conversations, and that the concept is needed in addition to that of genre to define interactions.

We went to look for meaning and all we got were these lousy representations: aspects of meaning representation for computational semantics

no code implementations10 Sep 2021 Simon Dobnik, Robin Cooper, Adam Ek, Bill Noble, Staffan Larsson, Nikolai Ilinykh, Vladislav Maraev, Vidya Somashekarappa

In this paper we examine different meaning representations that are commonly used in different natural language applications today and discuss their limits, both in terms of the aspects of the natural language meaning they are modelling and in terms of the aspects of the application for which they are used.

Distribution is not enough: going Firther

no code implementations WS 2019 Andy L{\"u}cking, Robin Cooper, Staffan Larsson, Jonathan Ginzburg

Much work in contemporary computational semantics follows the distributional hypothesis (DH), which is understood as an approach to semantics according to which the meaning of a word is a function of its distribution over contexts which is represented as vectors (word embeddings) within a multi-dimensional semantic space.

Word Embeddings

User-initiated Sub-dialogues in State-of-the-art Dialogue Systems

no code implementations WS 2017 Staffan Larsson

We test state of the art dialogue systems for their behaviour in response to user-initiated sub-dialogues, i. e. interactions where a system question is responded to with a question or request from the user, who thus initiates a sub-dialogue.

Dialogue Management Spoken Dialogue Systems

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