User profiles for Aalok Sathe
Aalok SatheResearch Associate, MIT Brain and Cognitive Sciences Verified email at mit.edu Cited by 169 |
Driving and suppressing the human language network using large language models
Transformer models such as GPT generate human-like language and are predictive of human
brain responses to language. Here, using functional-MRI-measured brain responses to …
brain responses to language. Here, using functional-MRI-measured brain responses to …
[HTML][HTML] Probabilistic atlas for the language network based on precision fMRI data from> 800 individuals
Two analytic traditions characterize fMRI language research. One relies on averaging activations
across individuals. This approach has limitations: because of inter-individual variability …
across individuals. This approach has limitations: because of inter-individual variability …
Automated fact-checking of claims from Wikipedia
Automated fact checking is becoming increasingly vital as both truthful and fallacious information
accumulate online. Research on fact checking has benefited from large-scale datasets …
accumulate online. Research on fact checking has benefited from large-scale datasets …
TaxiNLI: Taking a ride up the NLU hill
Pre-trained Transformer-based neural architectures have consistently achieved state-of-the-art
performance in the Natural Language Inference (NLI) task. Since NLI examples …
performance in the Natural Language Inference (NLI) task. Since NLI examples …
SentSpace: Large-scale benchmarking and evaluation of text using cognitively motivated lexical, syntactic, and semantic features
SentSpace is a modular framework for streamlined evaluation of text. SentSpacecharacterizes
textual input using diverse lexical, syntactic, and semantic features derivedfrom corpora …
textual input using diverse lexical, syntactic, and semantic features derivedfrom corpora …
Analyzing the effects of reasoning types on cross-lingual transfer performance
Multilingual language models achieve impressive zero-shot accuracies in many languages
in complex tasks such as Natural Language Inference (NLI). Examples in NLI (and …
in complex tasks such as Natural Language Inference (NLI). Examples in NLI (and …
Automatic fact-checking with document-level annotations using bert and multiple instance learning
Automatic fact-checking is crucial for recognizing misinformation spreading on the internet.
Most existing fact-checkers break down the process into several subtasks, one of which …
Most existing fact-checkers break down the process into several subtasks, one of which …
Block symmetries in graph coloring reconfiguration systems
…, S Krehbiel, R Morris, HM Russell, A Sathe… - Advances in Applied …, 2023 - Elsevier
In this paper, we study reconfiguration systems for proper graph colorings modified by single-vertex
recolorings. Applying a general construction of Ghrist and Peterson [15] to the graph …
recolorings. Applying a general construction of Ghrist and Peterson [15] to the graph …
Sample-efficient linguistic generalizations through program synthesis: Experiments with phonology problems
Neural models excel at extracting statistical patterns from large amounts of data, but struggle
to learn patterns or reason about language from only a few examples. In this paper, we ask: …
to learn patterns or reason about language from only a few examples. In this paper, we ask: …
[PDF][PDF] A rule-based system for the transcription of Sanskrit from the Devanagari orthography to the International Phonetic Alphabet
A Sathe - Sustaining Knowledge Diversity in the Digital Age, 2018 - dipot.ulb.ac.be
We propose a new system for the transcription of Sanskrit text written using the Devanagari
orthography, into the International Phonetic Alphabet, and supplement it with free and open-…
orthography, into the International Phonetic Alphabet, and supplement it with free and open-…