◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Jacob Andreas

MIT

40 papers hereh-index 5312.1k citations93 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • sole author4
  • first author3
  • middle author21
  • last author10

Across the 38 of 40 papers where every author was matched, so the position is known.

fields
  • cs.CL26
  • cs.LG5
  • cs.CV4
  • cs.FL1
  • cs.PL1
  • cs.RO1
affiliations
  • MIT
  • Microsoft
Homepage
same name
  • Jacob Andreas — 9 papers, h 7
  • Jacob Andreas — 7 papers, h 4
  • Jacob Andreas — 7 papers, h 6
  • Jacob Andreas — 6 papers, h 4
  • Jacob Andreas — 6 papers, h 5
  • Jacob Andreas — 6 papers, h 4

Either other researchers who publish under this name, or the same person where the external sources have not merged their records.

identity via Semantic Scholar / OpenAlex

activity
20122023
most citedMeasuring Compositionality in Representation Learning

24 citations · 159 across the 20 of their papers we have counts for

collaborators
Showing 2019Show all

4 papers · 1 filter

cs.LG2019

A Survey of Reinforcement Learning Informed by Natural Language

Jelena Luketina, Nantas Nardelli, Gregory Farquhar +5

To be successful in real-world tasks, Reinforcement Learning (RL) needs to exploit the compositional, relational, and hierarchical structure of the world, and learn to transfer it…

cs.CL2019★ 8 cited

Pragmatically Informative Text Generation

Sheng Shen, Daniel Fried, Jacob Andreas +1

We improve the informativeness of models for conditional text generation using techniques from computational pragmatics. These techniques formulate language production as a game be…

cs.CL2019

Good-Enough Compositional Data Augmentation

Jacob Andreas

We propose a simple data augmentation protocol aimed at providing a compositional inductive bias in conditional and unconditional sequence models. Under this protocol, synthetic tr…

cs.LG2019★ 24 cited

Measuring Compositionality in Representation Learning

Jacob Andreas

Many machine learning algorithms represent input data with vector embeddings or discrete codes. When inputs exhibit compositional structure (e.g. objects built from parts or proced…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.