Adam Trischler

Towards Information-Seeking Agents

2016 · arXiv (Cornell University)

We develop a general problem setting for training and testing the ability of agents to gather information efficiently. Specifically, we present a collection of tasks in which success requires searching through a partially-observed environment, for …

Counting to Explore and Generalize in Text-based Games

2018 · arXiv (Cornell University)

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 generated text-based games of varying difficulty where …

The KnowRef Coreference Corpus: Removing Gender and Number Cues for Difficult Pronominal Anaphora Resolution

2019

We introduce a new benchmark for coreference resolution and NLI, KNOWREF, that targets common-sense understanding and world knowledge. Previous coreference resolution tasks can largely be solved by exploiting the number and gender of the antecedents, …

Exploring and Predicting Transferability across NLP Tasks

2020

Tu Vu, Tong Wang, Tsendsuren Munkhdalai, Alessandro Sordoni, Adam Trischler, Andrew Mattarella-Micke, Subhransu Maji, Mohit Iyyer. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2020.

NewsQA: A Machine Comprehension Dataset

2017

We present NewsQA, a challenging machine comprehension dataset of over 100,000 human-generated question-answer pairs. Crowdworkers supply questions and answers based on a set of over 10,000 news articles from CNN, with answers consisting of spans …

Machine Comprehension by Text-to-Text Neural Question Generation

2017

Xingdi Yuan, Tong Wang, Caglar Gulcehre, Alessandro Sordoni, Philip Bachman, Saizheng Zhang, Sandeep Subramanian, Adam Trischler. Proceedings of the 2nd Workshop on Representation Learning for NLP. 2017.

A Joint Model for Question Answering and Question Generation

2017 · arXiv (Cornell University)

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 that encodes the document and generates a question (answer) given …

Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning

2018 · PolyPublie (École Polytechnique de Montréal)

A lot of the recent success in natural language processing (NLP) has been driven by distributed vector representations of words trained on large amounts of text in an unsupervised manner. These representations are typically used …

NewsQA: A Machine Comprehension Dataset

2016 · arXiv (Cornell University)

We present NewsQA, a challenging machine comprehension dataset of over 100,000 human-generated question-answer pairs. Crowdworkers supply questions and answers based on a set of over 10,000 news articles from CNN, with answers consisting of spans …

Assessing Factoid Question-Answer Generation for Portuguese (Short Paper)

2017 · arXiv (Cornell University)

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 supervised and reinforcement learning. After teacher forcing for standard …