natural-language-processing-2

Language Acquisition

3260 papers • 126 benchmarks • 313 datasets

Language acquisition refers to tasks related to the learning of a second language.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in language-acquisition-2

Trend

Dataset

Best Model

Actions

SLAM 2018

Libraries

i

Use these libraries to find language-acquisition-2 models and implementations

jilljenn/ktm

2 papers 129

Datasets

BLiMP

Duolingo SLAM Shared Task

Duolingo Spaced Repetition Data

New Brown Corpus

NLI-PT

Subtasks

Grounded language learning

Most implemented papers

Semantic Speech Retrieval With a Visually Grounded Model of Untranscribed Speech

Karen Livescu, Gregory Shakhnarovich, H. Kamper•Wed Oct 04 2017

This work studies how a visually grounded speech model, trained on images of scenes paired with spoken captions, captures aspects of semantics, and introduces a newly collected data set of human semantic relevance judgements and an associated task, semantic speech retrieval, where the goal is to search for spoken utterances that are semantically relevant to a given text query.

Content

BabySLM

54

0

Paper Graph

Predicting and Explaining Human Semantic Search in a Cognitive Model

Aida Nematzadeh, S. Stevenson, Filip Miscevic•Tue Nov 28 2017

A model is presented that incrementally updates a semantic network, with limited computational steps, and replicates many patterns found in human semantic fluency using a simple random walk, showing that a combination of both structural and semantic features are correlated with human performance patterns.

0 0

Paper Graph

Interactive Grounded Language Acquisition and Generalization in a 2D World

W. Xu, Haonan Yu•Tue Jan 30 2018

The proposed model significantly outperforms five comparison methods for interpreting zero-shot sentences and demonstrates human-interpretable intermediate outputs of the model in the appendix.

80 0

Paper Graph

Neural Network Acceptability Judgments

Amanpreet Singh, Samuel R. Bowman, Alex Warstadt•Wed May 30 2018

This paper introduces the Corpus of Linguistic Acceptability (CoLA), a set of 10,657 English sentences labeled as grammatical or ungrammatical from published linguistics literature, and trains several recurrent neural network models on acceptability classification, and finds that the authors' models outperform unsupervised models by Lau et al. (2016) on CoLA.

1548 0

Paper Graph

Context Based Approach for Second Language Acquisition

Nihal V. Nayak, A. Rao•Thu May 31 2018

This system uses a logistic regression model to predict the likelihood of a student making a mistake while answering an exercise on Duolingo in all three language tracks - English/Spanish (en/es), Spanish/ English (es/en) and French/English (fr/en).

4 0

Paper Graph

Learning Music Helps You Read: Using Transfer to Study Linguistic Structure in Language Models

Dan Jurafsky, Isabel Papadimitriou•Wed Apr 29 2020

Experiments on transfer between natural languages show that zero-shot performance on a test language is highly correlated with typological syntactic similarity to the training language, suggesting that representations induced from natural languages correspond to the cross-linguistic syntactic properties studied in linguistic typology.

72 0

Paper Graph

Language as a Cognitive Tool to Imagine Goals in Curiosity-Driven Exploration

Pierre-Yves Oudeyer, Cédric Colas, Tristan Karch, Nicolas Lair, Jean-Michel Dussoux, Clément Moulin-Frier, Peter Ford Dominey•Thu Feb 20 2020

It is argued that the ability to imagine out-of-distribution goals is key to enable creative discoveries and open-ended learning, and Imagine, an intrinsically motivated deep reinforcement learning architecture that models this ability is introduced.

135 0

Paper Graph

Visually Grounded Continual Learning of Compositional Phrases

R. Nevatia, Xiang Ren, Arka Sadhu, Xisen Jin, Junyi Du•Fri May 01 2020

VisCOLL, a visually grounded language learning task, which simulates the continual acquisition of compositional phrases from streaming visual scenes, and reveals that SoTA continual learning approaches provide little to no improvements on VisCOLL.

17 0

Paper Graph

Cross-linguistically consistent semantic and syntactic annotation of child-directed speech

Nathan Schneider, Mark Steedman, Ida Szubert, Omri Abend, Samuel Gibbon, Sharon Goldwater•Tue Sep 21 2021

A methodology for constructing corpora of CDS paired with sentential logical forms, and uses this method to create two corpora, in English and Hebrew, that provide syntactic and semantic annotation for two corpora from CHILDES.

7 0

Paper Graph

An Efficient, Probabilistically Sound Algorithm for Segmentation and Word Discovery

M. Brent•Sun Jan 31 1999

Experiments on phonemic transcripts of spontaneous speech by parents to young children suggest that the model-based, unsupervised algorithm for recovering word boundaries in a natural-language text from which they have been deleted is more effective than other proposed algorithms, at least when utterance boundaries are given and the text includes a substantial number of short utterances.

333 0

Paper Graph

Adding a benchmark result helps the community track progress.