Search Results for author:
Found 15 papers, 7 papers with code
Perhaps PTLMs Should Go to School – A Task to Assess Open Book and Closed Book QA
Our goal is to deliver a new task and leaderboard to stimulate research on question answering and pre-trained language models (PTLMs) to understand a significant instructional document, e. g., an introductory college textbook or a manual.
Remember what you did so you know what to do next
In work contemporaneous with ours, Lin et al. (2023) demonstrated a two-part approach (SwiftSage) that uses a small LLM (T5-large) complemented by OpenAI's massive LLMs to achieve outstanding results in ScienceWorld.
Understanding Multimodal Procedural Knowledge by Sequencing Multimodal Instructional Manuals
The ability to sequence unordered events is an essential skill to comprehend and reason about real world task procedures, which often requires thorough understanding of temporal common sense and multimodal information, as these procedures are often communicated through a combination of texts and images.
Perhaps PTLMs Should Go to School -- A Task to Assess Open Book and Closed Book QA
Our goal is to deliver a new task and leaderboard to stimulate research on question answering and pre-trained language models (PTLMs) to understand a significant instructional document, e. g., an introductory college textbook or a manual.
Plot-guided Adversarial Example Construction for Evaluating Open-domain Story Generation
We propose to tackle these issues by generating a more comprehensive set of implausible stories using {\em plots}, which are structured representations of controllable factors used to generate stories.
Machine-Assisted Script Curation
We describe Machine-Aided Script Curator (MASC), a system for human-machine collaborative script authoring.
Learning to Generalize for Sequential Decision Making
However, the large amount of computation necessary to adequately train and explore the search space of sequential decision making, under a reinforcement learning paradigm, precludes the inclusion of large contextualized language models, which might otherwise enable the desired generalization ability.
Content Planning for Neural Story Generation with Aristotelian Rescoring
Long-form narrative text generated from large language models manages a fluent impersonation of human writing, but only at the local sentence level, and lacks structure or global cohesion.
Predictive Engagement: An Efficient Metric For Automatic Evaluation of Open-Domain Dialogue Systems
In this paper, we investigate the possibility and efficacy of estimating utterance-level engagement and define a novel metric, {\em predictive engagement}, for automatic evaluation of open-domain dialogue systems.
Deep Structured Neural Network for Event Temporal Relation Extraction
We propose a novel deep structured learning framework for event temporal relation extraction.
Last Words: What Can Be Accomplished with the State of the Art in Information Extraction? A Personal View
Though information extraction (IE) research has more than a 25-year history, F1 scores remain low.
Plan-And-Write: Towards Better Automatic Storytelling
Automatic storytelling is challenging since it requires generating long, coherent natural language to describes a sensible sequence of events.
Learning Transferable Representation for Bilingual Relation Extraction via Convolutional Neural Networks
The learnt representation is discriminative and transferable between languages.
