Search Results for author:
Found 28 papers, 6 papers with code
SmartPlay: A Benchmark for LLMs as Intelligent Agents
We introduce SmartPlay: both a challenging benchmark and a methodology for evaluating LLMs as agents.
The Roles of Symbols in Neural-based AI: They are Not What You Think!
We propose that symbols are first and foremost external communication tools used between intelligent agents that allow knowledge to be transferred in a more efficient and effective manner than having to experience the world directly.
Transferable Student Performance Modeling for Intelligent Tutoring Systems
(ii) In the inductive transfer setting, we tune pre-trained course-agnostic performance models to new courses using small-scale target course data (e. g., collected during a pilot study).
Assessing the Performance of Online Students -- New Data, New Approaches, Improved Accuracy
This student performance (SP) modeling problem is a critical step for building adaptive online teaching systems.
Coarse-to-Fine Curriculum Learning
However, in machine learning, models are most often trained to solve the target tasks directly. Inspired by human learning, we propose a novel curriculum learning approach which decomposes challenging tasks into sequences of easier intermediate goals that are used to pre-train a model before tackling the target task.
Towards General Natural Language Understanding with Probabilistic Worldbuilding
We derive and implement an inference algorithm that reads sentences by parsing and abducing updates to its latent world model that capture the semantics of those sentences, and evaluate it on two out-of-domain question-answering datasets: (1) ProofWriter and (2) a new dataset we call FictionalGeoQA, designed to be more representative of real language but still simple enough to focus on evaluating reasoning ability, while being robust against heuristics.
Fringe News Networks: Dynamics of US News Viewership following the 2020 Presidential Election
The growing political polarization of the American electorate over the last several decades has been widely studied and documented.
We Don't Speak the Same Language: Interpreting Polarization through Machine Translation
Polarization among US political parties, media and elites is a widely studied topic.
Modeling Task Effects on Meaning Representation in the Brain via Zero-Shot MEG Prediction
These results suggest that only the end of semantic processing of a word is task-dependent, and pose a challenge for future research to formulate new hypotheses for earlier task effects as a function of the task and stimuli.
Discovering Bilingual Lexicons in Polyglot Word Embeddings
In this work, we utilize a single Skip-gram model trained on a multilingual corpus yielding polyglot word embeddings, and present a novel finding that a surprisingly simple constrained nearest-neighbor sampling technique in this embedding space can retrieve bilingual lexicons, even in harsh social media data sets predominantly written in English and Romanized Hindi and often exhibiting code switching.
Towards Effective Human-AI Collaboration in GUI-Based Interactive Task Learning Agents
Lastly, we identify several challenges and opportunities, and describe our ongoing work
Discourse in Multimedia: A Case Study in Extracting Geometry Knowledge from Textbooks
At the same time, these help the readers pick up the structure of the discourse and comprehend the conveyed information.
Interactive Task and Concept Learning from Natural Language Instructions and GUI Demonstrations
In this paper, we describe a new multi-modal domain-independent approach that combines natural language programming and programming-by-demonstration to allow users to first naturally describe tasks and associated conditions at a high level, and then collaborate with the agent to recursively resolve any ambiguities or vagueness through conversations and demonstrations.
Human-Computer Interaction
Competence-based Curriculum Learning for Neural Machine Translation
In this paper, we propose a curriculum learning framework for NMT that reduces training time, reduces the need for specialized heuristics or large batch sizes, and results in overall better performance.
Learning Pipelines with Limited Data and Domain Knowledge: A Study in Parsing Physics Problems
Finally, we also show how Nuts&Bolts can be used to achieve improvements on a relation extraction task and on the end task of answering Newtonian physics problems.
Discourse in Multimedia: A Case Study in Information Extraction
At the same time, these help the readers pick up the structure of the discourse and comprehend the conveyed information.
Merging knowledge bases in different languages
Recently, different systems which learn to populate and extend a knowledge base (KB) from the web in different languages have been presented.
Estimating Accuracy from Unlabeled Data: A Probabilistic Logic Approach
We propose an efficient method to estimate the accuracy of classifiers using only unlabeled data.
Machine Reading with Background Knowledge
In this paper, we pursue a different approach; machine reading methods that make use of background knowledge to facilitate language understanding.
Learning a Compositional Semantics for Freebase with an Open Predicate Vocabulary
Crucially, our approach uses an open predicate vocabulary, enabling it to produce denotations for phrases such as {``}Republican front-runner from Texas{''} whose semantics cannot be represented using the Freebase schema.
Zero-shot Learning with Semantic Output Codes
To achieve this, we define the notion of a semantic output code classifier (SOC) which utilizes a knowledge base of semantic properties of $Y$ to extrapolate to novel classes.
