224 citations · 1.1k across the 33 of their papers we have counts for
27 papers · 1 filter
Joint Prompt Optimization of Stacked LLMs using Variational Inference
Alessandro Sordoni, Xingdi Yuan, Marc-Alexandre Côté +6
Large language models (LLMs) can be seen as atomic units of computation mapping sequences to a distribution over sequences. Thus, they can be seen as stochastic language layers in…
It Takes Two to Tango: Navigating Conceptualizations of NLP Tasks and Measurements of Performance
Arjun Subramonian, Xingdi Yuan, Hal Daumé +1
Progress in NLP is increasingly measured through benchmarks; hence, contextualizing progress requires understanding when and why practitioners may disagree about the validity of be…
ByteSized32: A Corpus and Challenge Task for Generating Task-Specific World Models Expressed as Text Games
Ruoyao Wang, Graham Todd, Eric Yuan +3
In this work, we investigate the capacity of language models to generate explicit, interpretable, and interactive world models of scientific and common-sense reasoning tasks. We op…
Supporting Qualitative Analysis with Large Language Models: Combining Codebook with GPT-3 for Deductive Coding
Ziang Xiao, Xingdi Yuan, Q. Vera Liao +2
Qualitative analysis of textual contents unpacks rich and valuable information by assigning labels to the data. However, this process is often labor-intensive, particularly when wo…
GPT-3-driven pedagogical agents for training children's curious question-asking skills
Rania Abdelghani, Yen-Hsiang Wang, Xingdi Yuan +4
In order to train children's ability to ask curiosity-driven questions, previous research has explored designing specific exercises relying on providing semantic and linguistic cue…
Selecting Better Samples from Pre-trained LLMs: A Case Study on Question Generation
Xingdi Yuan, Tong Wang, Yen-Hsiang Wang +5
Large Language Models (LLMs) have in recent years demonstrated impressive prowess in natural language generation. A common practice to improve generation diversity is to sample mul…
General-to-Specific Transfer Labeling for Domain Adaptable Keyphrase Generation
Rui Meng, Tong Wang, Xingdi Yuan +2
Training keyphrase generation (KPG) models require a large amount of annotated data, which can be prohibitively expensive and often limited to specific domains. In this study, we f…
One-Shot Learning from a Demonstration with Hierarchical Latent Language
Nathaniel Weir, Xingdi Yuan, Marc-Alexandre Côté +5
Humans have the capability, aided by the expressive compositionality of their language, to learn quickly by demonstration. They are able to describe unseen task-performing procedur…
Interactive Machine Comprehension with Dynamic Knowledge Graphs
Xingdi Yuan
Interactive machine reading comprehension (iMRC) is machine comprehension tasks where knowledge sources are partially observable. An agent must interact with an environment sequent…
Bringing Structure into Summaries: a Faceted Summarization Dataset for Long Scientific Documents
Rui Meng, Khushboo Thaker, Lei Zhang +4
Faceted summarization provides briefings of a document from different perspectives. Readers can quickly comprehend the main points of a long document with the help of a structured…
ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
Mohit Shridhar, Xingdi Yuan, Marc-Alexandre Côté +3
Given a simple request like Put a washed apple in the kitchen fridge, humans can reason in purely abstract terms by imagining action sequences and scoring their likelihood of succe…
An Empirical Study on Neural Keyphrase Generation
Rui Meng, Xingdi Yuan, Tong Wang +3
Recent years have seen a flourishing of neural keyphrase generation (KPG) works, including the release of several large-scale datasets and a host of new models to tackle them. Mode…
Learning Dynamic Belief Graphs to Generalize on Text-Based Games
Ashutosh Adhikari, Xingdi Yuan, Marc-Alexandre Côté +7
Playing text-based games requires skills in processing natural language and sequential decision making. Achieving human-level performance on text-based games remains an open challe…
Building Dynamic Knowledge Graphs from Text-based Games
Mikuláš Zelinka, Xingdi Yuan, Marc-Alexandre Côté +2
We are interested in learning how to update Knowledge Graphs (KG) from text. In this preliminary work, we propose a novel Sequence-to-Sequence (Seq2Seq) architecture to generate el…
Does Order Matter? An Empirical Study on Generating Multiple Keyphrases as a Sequence
Rui Meng, Xingdi Yuan, Tong Wang +3
Recently, concatenating multiple keyphrases as a target sequence has been proposed as a new learning paradigm for keyphrase generation. Existing studies concatenate target keyphras…
Interactive Language Learning by Question Answering
Xingdi Yuan, Marc-Alexandre Cote, Jie Fu +4
Humans observe and interact with the world to acquire knowledge. However, most existing machine reading comprehension (MRC) tasks miss the interactive, information-seeking componen…
Interactive Machine Comprehension with Information Seeking Agents
Xingdi Yuan, Jie Fu, Marc-Alexandre Cote +3
Existing machine reading comprehension (MRC) models do not scale effectively to real-world applications like web-level information retrieval and question answering (QA). We argue t…
Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narratives
Yi Tay, Shuohang Wang, Luu Anh Tuan +6
This paper tackles the problem of reading comprehension over long narratives where documents easily span over thousands of tokens. We propose a curriculum learning (CL) based Point…
Building Dynamic Knowledge Graphs from Text using Machine Reading Comprehension
Rajarshi Das, Tsendsuren Munkhdalai, Xingdi Yuan +2
We propose a neural machine-reading model that constructs dynamic knowledge graphs from procedural text. It builds these graphs recurrently for each step of the described procedure…
One Size Does Not Fit All: Generating and Evaluating Variable Number of Keyphrases
Xingdi Yuan, Tong Wang, Rui Meng +4
Different texts shall by nature correspond to different number of keyphrases. This desideratum is largely missing from existing neural keyphrase generation models. In this study, w…
Counting to Explore and Generalize in Text-based Games
Xingdi Yuan, Marc-Alexandre Côté, Alessandro Sordoni +4
We propose a recurrent RL agent with an episodic exploration mechanism that helps discovering good policies in text-based game environments. We show promising results on a set of g…
A Joint Model for Question Answering and Question Generation
Tong Wang, Xingdi Yuan, Adam Trischler
We propose a generative machine comprehension model that learns jointly to ask and answer questions based on documents. The proposed model uses a sequence-to-sequence framework tha…
Neural Models for Key Phrase Detection and Question Generation
Sandeep Subramanian, Tong Wang, Xingdi Yuan +3
We propose a two-stage neural model to tackle question generation from documents. First, our model estimates the probability that word sequences in a document are ones that a human…
Machine Comprehension by Text-to-Text Neural Question Generation
Xingdi Yuan, Tong Wang, Caglar Gulcehre +5
We propose a recurrent neural model that generates natural-language questions from documents, conditioned on answers. We show how to train the model using a combination of supervis…