no code implementations • 20 Nov 2024 • Angel Hsing-Chi Hwang, Q. Vera Liao, Su Lin Blodgett, Alexandra Olteanu, Adam Trischler
Given the rising proliferation and diversity of AI writing assistance tools, especially those powered by large language models (LLMs), both writers and readers may have concerns about the impact of these tools on the authenticity of writing work.
no code implementations • 18 Nov 2023 • Yu Lu Liu, Meng Cao, Su Lin Blodgett, Jackie Chi Kit Cheung, Alexandra Olteanu, Adam Trischler
We focus on how, which, and when responsible AI issues are covered, which relevant stakeholders are considered, and mismatches between stated and realized research goals.
1 code implementation • NeurIPS 2023 • Alessandro Sordoni, Xingdi Yuan, Marc-Alexandre Côté, Matheus Pereira, Adam Trischler, Ziang Xiao, Arian Hosseini, Friederike Niedtner, Nicolas Le Roux
Thus, they can be seen as stochastic language layers in a language network, where the learnable parameters are the natural language prompts at each layer.
1 code implementation • 24 May 2023 • Jikun Kang, Romain Laroche, Xingdi Yuan, Adam Trischler, Xue Liu, Jie Fu
We argue that this inefficiency stems from the forgetting phenomenon, in which a model memorizes its behaviors in parameters throughout training.
1 code implementation • 16 Mar 2023 • Ian Porada, Alexandra Olteanu, Kaheer Suleman, Adam Trischler, Jackie Chi Kit Cheung
To study this, we view evaluation through the lens of measurement modeling, a framework commonly used in the social sciences for analyzing the validity of measurements.
1 code implementation • 15 Dec 2022 • Akshatha Arodi, Martin Pömsl, Kaheer Suleman, Adam Trischler, Alexandra Olteanu, Jackie Chi Kit Cheung
In this work, we propose a test suite of coreference resolution subtasks that require reasoning over multiple facts.
no code implementations • NAACL 2022 • Kaitlyn Zhou, Su Lin Blodgett, Adam Trischler, Hal Daumé III, Kaheer Suleman, Alexandra Olteanu
There are many ways to express similar things in text, which makes evaluating natural language generation (NLG) systems difficult.
no code implementations • ACL 2021 • Ali Emami, Ian Porada, Alexandra Olteanu, Kaheer Suleman, Adam Trischler, Jackie Chi Kit Cheung
A false contract is more likely to be rejected than a contract is, yet a false key is less likely than a key to open doors.
1 code implementation • NAACL 2021 • Ian Porada, Kaheer Suleman, Adam Trischler, Jackie Chi Kit Cheung
Understanding natural language requires common sense, one aspect of which is the ability to discern the plausibility of events.
no code implementations • ICLR 2021 • Mohit Shridhar, Xingdi Yuan, Marc-Alexandre Cote, Yonatan Bisk, Adam Trischler, Matthew Hausknecht
ALFWorld enables the creation of a new BUTLER agent whose abstract knowledge, learned in TextWorld, corresponds directly to concrete, visually grounded actions.
1 code implementation • Joint Conference on Lexical and Computational Semantics 2020 • Abhilasha Ravichander, Eduard Hovy, Kaheer Suleman, Adam Trischler, Jackie Chi Kit Cheung
In particular, we demonstrate through a simple consistency probe that the ability to correctly retrieve hypernyms in cloze tasks, as used in prior work, does not correspond to systematic knowledge in BERT.
1 code implementation • COLING 2020 • Ali Emami, Adam Trischler, Kaheer Suleman, Jackie Chi Kit Cheung
The Winograd Schema Challenge (WSC) and variants inspired by it have become important benchmarks for common-sense reasoning (CSR).
2 code implementations • 8 Oct 2020 • Mohit Shridhar, Xingdi Yuan, Marc-Alexandre Côté, Yonatan Bisk, Adam Trischler, Matthew Hausknecht
ALFWorld enables the creation of a new BUTLER agent whose abstract knowledge, learned in TextWorld, corresponds directly to concrete, visually grounded actions.
1 code implementation • NAACL 2021 • Rui Meng, Xingdi Yuan, Tong Wang, Sanqiang Zhao, Adam Trischler, Daqing He
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.
1 code implementation • EMNLP 2020 • Tu Vu, Tong Wang, Tsendsuren Munkhdalai, Alessandro Sordoni, Adam Trischler, Andrew Mattarella-Micke, Subhransu Maji, Mohit Iyyer
We also develop task embeddings that can be used to predict the most transferable source tasks for a given target task, and we validate their effectiveness in experiments controlled for source and target data size.
no code implementations • EMNLP 2020 • Tao Shen, Yi Mao, Pengcheng He, Guodong Long, Adam Trischler, Weizhu Chen
In contrast to existing paradigms, our approach uses knowledge graphs implicitly, only during pre-training, to inject language models with structured knowledge via learning from raw text.
1 code implementation • ICLR 2020 • Jie Fu, Xue Geng, Zhijian Duan, Bohan Zhuang, Xingdi Yuan, Adam Trischler, Jie Lin, Chris Pal, Hao Dong
To our knowledge, existing methods overlook the fact that although the student absorbs extra knowledge from the teacher, both models share the same input data -- and this data is the only medium by which the teacher's knowledge can be demonstrated.
1 code implementation • NeurIPS 2020 • Ashutosh Adhikari, Xingdi Yuan, Marc-Alexandre Côté, Mikuláš Zelinka, Marc-Antoine Rondeau, Romain Laroche, Pascal Poupart, Jian Tang, Adam Trischler, William L. Hamilton
Playing text-based games requires skills in processing natural language and sequential decision making.
1 code implementation • 21 Oct 2019 • Mikuláš Zelinka, Xingdi Yuan, Marc-Alexandre Côté, Romain Laroche, Adam Trischler
We are interested in learning how to update Knowledge Graphs (KG) from text.
1 code implementation • 9 Sep 2019 • Rui Meng, Xingdi Yuan, Tong Wang, Peter Brusilovsky, Adam Trischler, Daqing He
Recently, concatenating multiple keyphrases as a target sequence has been proposed as a new learning paradigm for keyphrase generation.
1 code implementation • IJCNLP 2019 • Xingdi Yuan, Marc-Alexandre Cote, Jie Fu, Zhouhan Lin, Christopher Pal, Yoshua Bengio, Adam Trischler
In QAit, an agent must interact with a partially observable text-based environment to gather information required to answer questions.
Deep Reinforcement Learning
Machine Reading Comprehension
+1
1 code implementation • ACL 2020 • Xingdi Yuan, Jie Fu, Marc-Alexandre Cote, Yi Tay, Christopher Pal, Adam Trischler
Existing machine reading comprehension (MRC) models do not scale effectively to real-world applications like web-level information retrieval and question answering (QA).
1 code implementation • NeurIPS 2019 • Tsendsuren Munkhdalai, Alessandro Sordoni, Tong Wang, Adam Trischler
We augment recurrent neural networks with an external memory mechanism that builds upon recent progress in metalearning.
no code implementations • ICLR Workshop drlStructPred 2019 • Layla El Asri, Adam Trischler
We show through extensive experiments and analysis that, when trained with policy gradient, recurrent neural networks often fail to learn a state representation that leads to an optimal policy in settings where the same action should be taken at different states.
3 code implementations • ICLR 2019 • Mariya Toneva, Alessandro Sordoni, Remi Tachet des Combes, Adam Trischler, Yoshua Bengio, Geoffrey J. Gordon
Inspired by the phenomenon of catastrophic forgetting, we investigate the learning dynamics of neural networks as they train on single classification tasks.
no code implementations • NeurIPS 2018 • Sandeep Subramanian, Sai Rajeswar Mudumba, Alessandro Sordoni, Adam Trischler, Aaron C. Courville, Chris Pal
We generate outlines with an adversarial model trained to approximate the distribution of sentences in a latent space induced by general-purpose sentence encoders.
1 code implementation • IJCNLP 2019 • Paul Trichelair, Ali Emami, Adam Trischler, Kaheer Suleman, Jackie Chi Kit Cheung
Recent studies have significantly improved the state-of-the-art on common-sense reasoning (CSR) benchmarks like the Winograd Schema Challenge (WSC) and SWAG.
Ranked #36 on
Coreference Resolution
on Winograd Schema Challenge
1 code implementation • ACL 2019 • Ali Emami, Paul Trichelair, Adam Trischler, Kaheer Suleman, Hannes Schulz, Jackie Chi Kit Cheung
To explain this performance gap, we show empirically that state-of-the art models often fail to capture context, instead relying on the gender or number of candidate antecedents to make a decision.
no code implementations • ICLR 2019 • Rajarshi Das, Tsendsuren Munkhdalai, Xingdi Yuan, Adam Trischler, Andrew McCallum
We harness and extend a recently proposed machine reading comprehension (MRC) model to query for entity states, since these states are generally communicated in spans of text and MRC models perform well in extracting entity-centric spans.
Ranked #3 on
Procedural Text Understanding
on ProPara
1 code implementation • ACL 2020 • Xingdi Yuan, Tong Wang, Rui Meng, Khushboo Thaker, Peter Brusilovsky, Daqing He, Adam Trischler
With both previous and new evaluation metrics, our model outperforms strong baselines on all datasets.
no code implementations • EMNLP 2018 • Ali Emami, Noelia De La Cruz, Adam Trischler, Kaheer Suleman, Jackie Chi Kit Cheung
We introduce an automatic system that achieves state-of-the-art results on the Winograd Schema Challenge (WSC), a common sense reasoning task that requires diverse, complex forms of inference and knowledge.
Ranked #65 on
Coreference Resolution
on Winograd Schema Challenge
8 code implementations • ICLR 2019 • R. Devon Hjelm, Alex Fedorov, Samuel Lavoie-Marchildon, Karan Grewal, Phil Bachman, Adam Trischler, Yoshua Bengio
In this work, we perform unsupervised learning of representations by maximizing mutual information between an input and the output of a deep neural network encoder.
no code implementations • 12 Jul 2018 • Tsendsuren Munkhdalai, Adam Trischler
We unify recent neural approaches to one-shot learning with older ideas of associative memory in a model for metalearning.
no code implementations • WS 2018 • S Subramanian, eep, Tong Wang, Xingdi Yuan, Saizheng Zhang, Adam Trischler, Yoshua Bengio
We propose a two-stage neural model to tackle question generation from documents.
2 code implementations • 29 Jun 2018 • Xingdi Yuan, Marc-Alexandre Côté, Alessandro Sordoni, Romain Laroche, Remi Tachet des Combes, Matthew Hausknecht, Adam Trischler
We propose a recurrent RL agent with an episodic exploration mechanism that helps discovering good policies in text-based game environments.
1 code implementation • 29 Jun 2018 • Marc-Alexandre Côté, Ákos Kádár, Xingdi Yuan, Ben Kybartas, Tavian Barnes, Emery Fine, James Moore, Ruo Yu Tao, Matthew Hausknecht, Layla El Asri, Mahmoud Adada, Wendy Tay, Adam Trischler
We introduce TextWorld, a sandbox learning environment for the training and evaluation of RL agents on text-based games.
no code implementations • ICML 2018 • Nan Rosemary Ke, Konrad Zolna, Alessandro Sordoni, Zhouhan Lin, Adam Trischler, Yoshua Bengio, Joelle Pineau, Laurent Charlin, Chris Pal
We evaluate this method on several types of tasks with different attributes.
Ranked #3 on
Open-Domain Question Answering
on SearchQA
(Unigram Acc metric)
no code implementations • NAACL 2018 • Ali Emami, Adam Trischler, Kaheer Suleman, Jackie Chi Kit Cheung
We introduce an automatic system that performs well on two common-sense reasoning tasks, the Winograd Schema Challenge (WSC) and the Choice of Plausible Alternatives (COPA).
4 code implementations • ICLR 2018 • Sandeep Subramanian, Adam Trischler, Yoshua Bengio, Christopher J. Pal
In this work, we present a simple, effective multi-task learning framework for sentence representations that combines the inductive biases of diverse training objectives in a single model.
Ranked #1 on
Semantic Textual Similarity
on SentEval
no code implementations • ICLR 2018 • R. Devon Hjelm, Athul Paul Jacob, Adam Trischler, Gerry Che, Kyunghyun Cho, Yoshua Bengio
We introduce a method for training GANs with discrete data that uses the estimated difference measure from the discriminator to compute importance weights for generated samples, thus providing a policy gradient for training the generator.
no code implementations • ICML 2018 • Tsendsuren Munkhdalai, Xingdi Yuan, Soroush Mehri, Adam Trischler
We describe a mechanism by which artificial neural networks can learn rapid adaptation - the ability to adapt on the fly, with little data, to new tasks - that we call conditionally shifted neurons.
1 code implementation • NeurIPS 2017 • Francis Dutil, Caglar Gulcehre, Adam Trischler, Yoshua Bengio
We investigate the integration of a planning mechanism into sequence-to-sequence models using attention.
no code implementations • ICLR 2018 • Samira Shabanian, Devansh Arpit, Adam Trischler, Yoshua Bengio
Bidirectional LSTMs (Bi-LSTMs) on the other hand model sequences along both forward and backward directions and are generally known to perform better at such tasks because they capture a richer representation of the data.
1 code implementation • ICLR 2018 • Samira Ebrahimi Kahou, Vincent Michalski, Adam Atkinson, Akos Kadar, Adam Trischler, Yoshua Bengio
To resolve, such questions often require reference to multiple plot elements and synthesis of information distributed spatially throughout a figure.
Ranked #3 on
Visual Question Answering (VQA)
on FigureQA - test 1
2 code implementations • ICLR 2018 • Dmitriy Serdyuk, Nan Rosemary Ke, Alessandro Sordoni, Adam Trischler, Chris Pal, Yoshua Bengio
We propose a simple technique for encouraging generative RNNs to plan ahead.
no code implementations • WS 2017 • Caglar Gulcehre, Francis Dutil, Adam Trischler, Yoshua Bengio
We investigate the integration of a planning mechanism into an encoder-decoder architecture with attention.
no code implementations • ICML 2017 • Philip Bachman, Alessandro Sordoni, Adam Trischler
We introduce a model that learns active learning algorithms via metalearning.
no code implementations • 14 Jun 2017 • Sandeep Subramanian, Tong Wang, Xingdi Yuan, Saizheng Zhang, Yoshua Bengio, Adam Trischler
We propose a two-stage neural model to tackle question generation from documents.
1 code implementation • 13 Jun 2017 • Caglar Gulcehre, Francis Dutil, Adam Trischler, Yoshua Bengio
We investigate the integration of a planning mechanism into an encoder-decoder architecture with an explicit alignment for character-level machine translation.
no code implementations • 5 Jun 2017 • Tong Wang, Xingdi Yuan, Adam Trischler
We propose a generative machine comprehension model that learns jointly to ask and answer questions based on documents.
4 code implementations • WS 2017 • Xingdi Yuan, Tong Wang, Caglar Gulcehre, Alessandro Sordoni, Philip Bachman, Sandeep Subramanian, Saizheng Zhang, Adam Trischler
We propose a recurrent neural model that generates natural-language questions from documents, conditioned on answers.
6 code implementations • 27 Feb 2017 • R. Devon Hjelm, Athul Paul Jacob, Tong Che, Adam Trischler, Kyunghyun Cho, Yoshua Bengio
We introduce a method for training GANs with discrete data that uses the estimated difference measure from the discriminator to compute importance weights for generated samples, thus providing a policy gradient for training the generator.
no code implementations • 8 Dec 2016 • Philip Bachman, Alessandro Sordoni, Adam Trischler
We develop a general problem setting for training and testing the ability of agents to gather information efficiently.
2 code implementations • WS 2017 • Adam Trischler, Tong Wang, Xingdi Yuan, Justin Harris, Alessandro Sordoni, Philip Bachman, Kaheer Suleman
We present NewsQA, a challenging machine comprehension dataset of over 100, 000 human-generated question-answer pairs.
1 code implementation • 7 Jun 2016 • Alessandro Sordoni, Philip Bachman, Adam Trischler, Yoshua Bengio
We propose a novel neural attention architecture to tackle machine comprehension tasks, such as answering Cloze-style queries with respect to a document.
Ranked #3 on
Question Answering
on Children's Book Test
(Accuracy-NE metric)
no code implementations • EMNLP 2016 • Adam Trischler, Zheng Ye, Xingdi Yuan, Kaheer Suleman
We present the EpiReader, a novel model for machine comprehension of text.
Ranked #7 on
Question Answering
on Children's Book Test
1 code implementation • ACL 2016 • Adam Trischler, Zheng Ye, Xingdi Yuan, Jing He, Phillip Bachman, Kaheer Suleman
The parallel hierarchy enables our model to compare the passage, question, and answer from a variety of trainable perspectives, as opposed to using a manually designed, rigid feature set.
Ranked #1 on
Question Answering
on MCTest-160
no code implementations • 17 Dec 2015 • Adam Trischler, Gabriele MT D'Eleuterio
We review several of the most widely used techniques for training recurrent neural networks to approximate dynamical systems, then describe a novel algorithm for this task.