Search Results for author:
Found 41 papers, 12 papers with code
AgentKit: Flow Engineering with Graphs, not Coding
The chains of nodes can be designed to explicitly enforce a naturally structured "thought process".
Reasoning Capacity in Multi-Agent Systems: Limitations, Challenges and Human-Centered Solutions
We present a formal definition of reasoning capacity and illustrate its utility in identifying limitations within each component of the system.
Ruffle&Riley: Towards the Automated Induction of Conversational Tutoring Systems
Conversational tutoring systems (CTSs) offer learning experiences driven by natural language interaction.
SPRING: Studying the Paper and Reasoning to Play Games
Finally, we show the potential of games as a test bed for LLMs.
Plan, Eliminate, and Track -- Language Models are Good Teachers for Embodied Agents
We propose the Plan, Eliminate, and Track (PET) framework.
The Internal State of an LLM Knows When It's Lying
While Large Language Models (LLMs) have shown exceptional performance in various tasks, one of their most prominent drawbacks is generating inaccurate or false information with a confident tone.
Zero-shot Triplet Extraction by Template Infilling
We propose a novel framework, ZETT (ZEro-shot Triplet extraction by Template infilling), that aligns the task objective to the pre-training objective of generative transformers to generalize to unseen relations.
Ranked #1 on
Zero-shot Relation Triplet Extraction
on FewRel
Conversational Multi-Hop Reasoning with Neural Commonsense Knowledge and Symbolic Logic Rules
Our reasoner uses a state-of-the-art transformer-based generative commonsense knowledge base (KB) as its source of background knowledge for reasoning.
Interactive Task Learning from GUI-Grounded Natural Language Instructions and Demonstrations
We show SUGILITE, an intelligent task automation agent that can learn new tasks and relevant associated concepts interactively from the user{'}s natural language instructions and demonstrations, using the graphical user interfaces (GUIs) of third-party mobile apps.
Conversational Neuro-Symbolic Commonsense Reasoning
More precisely, we consider the problem of identifying the unstated presumptions of the speaker that allow the requested action to achieve the desired goal from the given state (perhaps elaborated by making the implicit presumptions explicit).
Learning from Imperfect Annotations
Many machine learning systems today are trained on large amounts of human-annotated data.
Jelly Bean World: A Testbed for Never-Ending Learning
Never-ending learning is a machine learning paradigm that aims to bridge this gap, with the goal of encouraging researchers to design machine learning systems that can learn to perform a wider variety of inter-related tasks in more complex environments.
Game Design for Eliciting Distinguishable Behavior
The ability to inferring latent psychological traits from human behavior is key to developing personalized human-interacting machine learning systems.
Learning to Ask for Conversational Machine Learning
Natural language has recently been explored as a new medium of supervision for training machine learning models.
Learning Data Manipulation for Augmentation and Weighting
In this work, we propose a new method that supports learning different manipulation schemes with the same gradient-based algorithm.
Look-up and Adapt: A One-shot Semantic Parser
In this paper, we propose a semantic parser that generalizes to out-of-domain examples by learning a general strategy for parsing an unseen utterance through adapting the logical forms of seen utterances, instead of learning to generate a logical form from scratch.
Learning from Imperfect Annotations: An End-to-End Approach
Many machine learning systems today are trained on large amounts of human-annotated data.
Relating Simple Sentence Representations in Deep Neural Networks and the Brain
To the best of our knowledge, this is the first work showing that the MEG brain recording when reading a word in a sentence can be used to distinguish earlier words in the sentence.
Leveraging Knowledge Bases in LSTMs for Improving Machine Reading
This paper focuses on how to take advantage of external knowledge bases (KBs) to improve recurrent neural networks for machine reading.
Learning to Learn Semantic Parsers from Natural Language Supervision
As humans, we often rely on language to learn language.
LIA: A Natural Language Programmable Personal Assistant
We present LIA, an intelligent personal assistant that can be programmed using natural language.
Contextual Parameter Generation for Universal Neural Machine Translation
We propose a simple modification to existing neural machine translation (NMT) models that enables using a single universal model to translate between multiple languages while allowing for language specific parameterization, and that can also be used for domain adaptation.
Zero-shot Learning of Classifiers from Natural Language Quantification
Humans can efficiently learn new concepts using language.
Joint Concept Learning and Semantic Parsing from Natural Language Explanations
Natural language constitutes a predominant medium for much of human learning and pedagogy.
A Joint Sequential and Relational Model for Frame-Semantic Parsing
We introduce a new method for frame-semantic parsing that significantly improves the prior state of the art.
Joint Extraction of Events and Entities within a Document Context
Events and entities are closely related; entities are often actors or participants in events and events without entities are uncommon.
Inferring Interpersonal Relations in Narrative Summaries
In this work, we address the problem of inferring the polarity of relationships between people in narrative summaries.
Sense Discovery via Co-Clustering on Images and Text
We present a co-clustering framework that can be used to discover multiple semantic and visual senses of a given Noun Phrase (NP).
Efficient Inference and Learning in a Large Knowledge Base: Reasoning with Extracted Information using a Locally Groundable First-Order Probabilistic Logic
We show that the problem of constructing proofs for this logic is related to computation of personalized PageRank (PPR) on a linearized version of the proof space, and using on this connection, we develop a proveably-correct approximate grounding scheme, based on the PageRank-Nibble algorithm.
