1 code implementation • 2 Oct 2023 • Yue Wu, Xuan Tang, Tom M. Mitchell, Yuanzhi Li
We introduce SmartPlay: both a challenging benchmark and a methodology for evaluating LLMs as agents.
no code implementations • 26 Apr 2023 • Daniel L. Silver, Tom M. Mitchell
We propose that symbols are first and foremost external communication tools used between intelligent agents that allow knowledge to be transferred in a more efficient and effective manner than having to experience the world directly.
no code implementations • 8 Feb 2022 • Robin Schmucker, Tom M. Mitchell
(ii) In the inductive transfer setting, we tune pre-trained course-agnostic performance models to new courses using small-scale target course data (e. g., collected during a pilot study).
1 code implementation • 4 Sep 2021 • Robin Schmucker, Jingbo Wang, Shijia Hu, Tom M. Mitchell
This student performance (SP) modeling problem is a critical step for building adaptive online teaching systems.
no code implementations • 8 Jun 2021 • Otilia Stretcu, Emmanouil Antonios Platanios, Tom M. Mitchell, Barnabás Póczos
However, in machine learning, models are most often trained to solve the target tasks directly. Inspired by human learning, we propose a novel curriculum learning approach which decomposes challenging tasks into sequences of easier intermediate goals that are used to pre-train a model before tackling the target task.
2 code implementations • 6 May 2021 • Abulhair Saparov, Tom M. Mitchell
We derive and implement an inference algorithm that reads sentences by parsing and abducing updates to its latent world model that capture the semantics of those sentences, and evaluate it on two out-of-domain question-answering datasets: (1) ProofWriter and (2) a new dataset we call FictionalGeoQA, designed to be more representative of real language but still simple enough to focus on evaluating reasoning ability, while being robust against heuristics.
no code implementations • 22 Jan 2021 • Ashiqur R. KhudaBukhsh, Rupak Sarkar, Mark S. Kamlet, Tom M. Mitchell
The growing political polarization of the American electorate over the last several decades has been widely studied and documented.
1 code implementation • 5 Oct 2020 • Ashiqur R. KhudaBukhsh, Rupak Sarkar, Mark S. Kamlet, Tom M. Mitchell
Polarization among US political parties, media and elites is a widely studied topic.
1 code implementation • NeurIPS 2020 • Mariya Toneva, Otilia Stretcu, Barnabas Poczos, Leila Wehbe, Tom M. Mitchell
These results suggest that only the end of semantic processing of a word is task-dependent, and pose a challenge for future research to formulate new hypotheses for earlier task effects as a function of the task and stimuli.
no code implementations • 31 Aug 2020 • Ashiqur R. KhudaBukhsh, Shriphani Palakodety, Tom M. Mitchell
In this work, we utilize a single Skip-gram model trained on a multilingual corpus yielding polyglot word embeddings, and present a novel finding that a surprisingly simple constrained nearest-neighbor sampling technique in this embedding space can retrieve bilingual lexicons, even in harsh social media data sets predominantly written in English and Romanized Hindi and often exhibiting code switching.
no code implementations • 5 Mar 2020 • Toby Jia-Jun Li, Jingya Chen, Tom M. Mitchell, Brad A. Myers
Lastly, we identify several challenges and opportunities, and describe our ongoing work
no code implementations • CL 2019 • Mrinmaya Sachan, Avinava Dubey, Eduard H. Hovy, Tom M. Mitchell, Dan Roth, Eric P. Xing
At the same time, these help the readers pick up the structure of the discourse and comprehend the conveyed information.
no code implementations • 30 Aug 2019 • Toby Jia-Jun Li, Marissa Radensky, Justin Jia, Kirielle Singarajah, Tom M. Mitchell, Brad A. Myers
In this paper, we describe a new multi-modal domain-independent approach that combines natural language programming and programming-by-demonstration to allow users to first naturally describe tasks and associated conditions at a high level, and then collaborate with the agent to recursively resolve any ambiguities or vagueness through conversations and demonstrations.
Human-Computer Interaction
1 code implementation • NAACL 2019 • Emmanouil Antonios Platanios, Otilia Stretcu, Graham Neubig, Barnabas Poczos, Tom M. Mitchell
In this paper, we propose a curriculum learning framework for NMT that reduces training time, reduces the need for specialized heuristics or large batch sizes, and results in overall better performance.
no code implementations • NeurIPS 2018 • Mrinmaya Sachan, Kumar Avinava Dubey, Tom M. Mitchell, Dan Roth, Eric P. Xing
Finally, we also show how Nuts&Bolts can be used to achieve improvements on a relation extraction task and on the end task of answering Newtonian physics problems.
no code implementations • 13 Nov 2018 • Mrinmaya Sachan, Kumar Avinava Dubey, Eduard H. Hovy, Tom M. Mitchell, Dan Roth, Eric P. Xing
At the same time, these help the readers pick up the structure of the discourse and comprehend the conveyed information.
no code implementations • WS 2017 • Jer{\'o}nimo Hern{\'a}ndez-Gonz{\'a}lez, Estevam R. Hruschka Jr., Tom M. Mitchell
Recently, different systems which learn to populate and extend a knowledge base (KB) from the web in different languages have been presented.
no code implementations • NeurIPS 2017 • Emmanouil A. Platanios, Hoifung Poon, Tom M. Mitchell, Eric Horvitz
We propose an efficient method to estimate the accuracy of classifiers using only unlabeled data.
no code implementations • 16 Dec 2016 • Ndapandula Nakashole, Tom M. Mitchell
In this paper, we pursue a different approach; machine reading methods that make use of background knowledge to facilitate language understanding.
no code implementations • TACL 2015 • Jayant Krishnamurthy, Tom M. Mitchell
Crucially, our approach uses an open predicate vocabulary, enabling it to produce denotations for phrases such as {``}Republican front-runner from Texas{''} whose semantics cannot be represented using the Freebase schema.
no code implementations • NeurIPS 2009 • Mark Palatucci, Dean Pomerleau, Geoffrey E. Hinton, Tom M. Mitchell
To achieve this, we define the notion of a semantic output code classifier (SOC) which utilizes a knowledge base of semantic properties of $Y$ to extrapolate to novel classes.