paper-with-me

홈 › Papers

Some of Them Can be Guessed! Exploring the Effect of Linguistic Context in Predicting Quantifiers

2018-06-01 · ACL 2018 7 · Sandro Pezzelle, Shane Steinert-Threlkeld, Raffaela Bernardi, Jakub Szymanik

We study the role of linguistic context in predicting quantifiers (few', all'). We collect crowdsourced data from human participants and test various models in a local (single-sentence) and a global context (multi-sentence) condition. Models significantly out-perform humans in the former setting and are only slightly better in the latter. While human performance improves with more linguistic context (especially on proportional quantifiers), model performance suffers. Models are very effective in exploiting lexical and morpho-syntactic patterns; humans are better at genuinely understanding the meaning of the (global) context.

📄 PDF Abstract BibTeX arXiv:1806.00354

Code (1)

sandropezzelle/fill-in-the-quant 공식 구현

Tasks

Sentence

Similar Papers 제목 키워드 기반

Boosting Resource-Constrained Federated Learning Systems with Guessed Updates

2021-10-21 · Mohamed Yassine Boukhari, Akash Dhasade, Anne-Marie Kermarrec, Rafael Pires 외

Federated learning (FL) enables a set of client devices to collaboratively train a model without sharing raw data. This process, though, operates under the constrained computation and communication resources of edge devi…

Federated Learning

Self-training a Constituency Parser using n-gram Trees

2014-05-01 · LREC 2014 5 · Arda {\c{C}}elebi, Arzucan {\"O}zg{\"u}r

In this study, we tackle the problem of self-training a feature-rich discriminative constituency parser. We approach the self-training problem with the assumption that while the full sentence parse tree produced by a par…

Constituency ParsingSentence

Multiple regression techniques for modeling dates of first performances of Shakespeare-era plays

2021-04-13 · Pablo Moscato, Hugh Craig, Gabriel Egan, Mohammad Nazmul Haque 외

The date of the first performance of a play of Shakespeare's time must usually be guessed with reference to multiple indirect external sources, or to some aspect of the content or style of the play. Identifying these dat…

Continued fractionregression

Unsupervised Domain Adaptive Re-Identification: Theory and Practice

2018-07-30 · Liangchen Song, Cheng Wang, Lefei Zhang, Bo Du 외

We study the problem of unsupervised domain adaptive re-identification (re-ID) which is an active topic in computer vision but lacks a theoretical foundation. We first extend existing unsupervised domain adaptive classif…

General ClassificationUnsupervised Domain Adaptation

A (Psycho-)Linguistically Motivated Scheme for Annotating and Exploring Emotions in a Genre-Diverse Corpus

2022-06-01 · LREC 2022 6 · Aline Etienne, Delphine Battistelli, Gwénolé Lecorvé

This paper presents a scheme for emotion annotation and its manual application on a genre-diverse corpus of texts written in French. The methodology introduced here emphasizes the necessity of clarifying the main concept…