Papers by Tom Mitchell
Learning to Learn Semantic Parsers from Natural Language Supervision (D18-1)
Copied to clipboard
| Challenge: | Existing logical forms require a user to be familiar with the underlying structure to learn a semantic parser. |
| Approach: | They propose a method for training semantic parsers from natural language feedback . they use natural language inputs to parse feedback to leverage it as a form of supervision . |
| Outcome: | The proposed algorithm learns a semantic parser from users’ corrections expressed in natural language. |
Interactive Task Learning from GUI-Grounded Natural Language Instructions and Demonstrations (2020.acl-demos)
Copied to clipboard
| Challenge: | SUGILITE is an intelligent task automation agent that can learn new tasks and relevant associated concepts interactively from the user’s natural language instructions and demonstrations using GUIs. |
| Approach: | They propose to use third-party mobile apps to teach new tasks and concepts using verbal instructions and demonstrations. |
| Outcome: | The proposed system can learn new tasks and relevant concepts from user's natural language instructions and demonstrations, and it generalizes taught concepts to different contexts and task domains. |
LIA: A Natural Language Programmable Personal Assistant (D18-2)
Copied to clipboard
| Challenge: | a prototype of an intelligent personal assistant can be programmed using natural language . a user can instruct her assistants using language similar to how humans teach other humans . |
| Approach: | They present LIA, an intelligent personal assistant that can be programmed using natural language. LIA resides on a typical mobile Android device. |
| Outcome: | The proposed system can be programmed using natural language, and it can perceive the external environment through sensors and effectors. |
Zero-shot Learning of Classifiers from Natural Language Quantification (P18-1)
Copied to clipboard
| Challenge: | Existing methods to learn concepts from natural language are limited or no labeled examples. |
| Approach: | They propose a framework through which a set of explanations of a concept can be used to learn a classifier without access to any labeled examples. |
| Outcome: | The proposed framework outperforms previous approaches for learning with limited data and is comparable with fully supervised classifiers trained from a small number of labeled examples. |
Conversational Multi-Hop Reasoning with Neural Commonsense Knowledge and Symbolic Logic Rules (2021.emnlp-main)
Copied to clipboard
| Challenge: | Currently, conversational agents lack commonsense reasoning, preventing them from engaging in rich conversations with humans. |
| Approach: | They propose a commonsense reasoning system that uncovers unstated presumptions from user commands satisfying a general template of if-(state), then-(action), because-(goal) They propose to use a transformer-based generative commons sense knowledge base as its source of background knowledge to extract multi-hop reasoning chains from the neural KB. |
| Outcome: | The proposed model achieves a 35% higher success rate than existing methods with human users. |
Competence-based Curriculum Learning for Neural Machine Translation (N19-1)
Copied to clipboard
| Challenge: | Existing NMT systems require specialized heuristics and large batch sizes. |
| Approach: | They propose a curriculum learning framework for NMT that reduces training time and costs . framework consists of a principled way of deciding which training samples are shown to the model . |
| Outcome: | The proposed framework can reduce training time and improve performance of recurrent neural network models and Transformers. |
Contextual Parameter Generation for Universal Neural Machine Translation (D18-1)
Copied to clipboard
| Challenge: | Existing approaches to multilingual neural machine translation lack language-specific parameterization. |
| Approach: | They propose a modification to existing neural machine translation models that allows for language specific parameterization and domain adaptation. |
| Outcome: | The proposed model surpasses state-of-the-art for both the IWSLT-15 and IWSTL-17 datasets and can perform zero-shot translation. |
Look-up and Adapt: A One-shot Semantic Parser (D19-1)
Copied to clipboard
| Challenge: | Current conversational agents such as Siri, Alexa or Google Assistant do not cater to the specific phrasing of a user or the specific action. |
| Approach: | They propose a semantic parser that generalizes to out-of-domain examples by adapting the logical forms of seen utterances to fit an unseen utterant. |
| Outcome: | The proposed parser improves on one-shot parsing by 68.8% compared to baselines . it adapts the logical forms of seen utterances to fit the unseen utterant . |
Learning to Ask for Conversational Machine Learning (D19-1)
Copied to clipboard
| Challenge: | Empirical analysis across three domains shows that learned question-asking strategies expedite classifier training by asking appropriate questions at different points in the learning process. |
| Approach: | They propose a reinforcement learning framework where the learner’s actions correspond to question types and the reward for asking a question is based on how the teacher’s response changes performance of the resulting machine learning model. |
| Outcome: | The proposed framework outperforms a random policy on learning classification tasks, but the dialog looks contrived from a human perspective. |
Relating Simple Sentence Representations in Deep Neural Networks and the Brain (P19-1)
Copied to clipboard
| Challenge: | Existing deep learning models for natural language processing are not fully studied. |
| Approach: | They investigate whether deep recurrent models learn sentences against those encoded by the brain and whether there is any correspondence between hidden layers of these models and brain regions when processing sentences. |
| Outcome: | The proposed models can be used to synthesize brain data and improve subsequent stimuli decoding accuracy. |
Understanding language-elicited EEG data by predicting it from a fine-tuned language model (N19-1)
Copied to clipboard
| Challenge: | Existing studies have only found two of the ERPs to be predictable from embeddings of a stream of language. |
| Approach: | They propose to fine tune a language model to predict ERPs by embedding a stream of language into a model that allows them to be more accurate. |
| Outcome: | The proposed model fine tunes the ERPs to predict them for the first time. |
The Internal State of an LLM Knows When It’s Lying (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have shown exceptional performance in various tasks, but one of their main drawbacks is generating inaccurate or false information with a confident tone. |
| Approach: | They propose to train a classifier that outputs the probability that a statement is truthful based on the hidden layer activations of the LLM as it reads or generates the statement. |
| Outcome: | The proposed classifier achieves an average of 71% to 83% accuracy labeling which sentences are true versus false, depending on the LLM base model. |