Search Results for author:
Found 38 papers, 3 papers with code
Creating generalizable downstream graph models with random projections
We investigate graph representation learning approaches that enable models to generalize across graphs: given a model trained using the representations from one graph, our goal is to apply inference using those same model parameters when given representations computed over a new graph, unseen during model training, with minimal degradation in inference accuracy.
Probing Factually Grounded Content Transfer with Factual Ablation
Particularly, this domain allows us to introduce the notion of factual ablation for automatically measuring factual consistency: this captures the intuition that the model should be less likely to produce an output given a less relevant grounding document.
When does text prediction benefit from additional context? An exploration of contextual signals for chat and email messages
We compare contextual text prediction in chat and email messages from two of the largest commercial platforms Microsoft Teams and Outlook, finding that contextual signals contribute to performance differently between these scenarios.
Text Editing by Command
A prevailing paradigm in neural text generation is one-shot generation, where text is produced in a single step.
Examination and Extension of Strategies for Improving Personalized Language Modeling via Interpolation
In this paper, we detail novel strategies for interpolating personalized language models and methods to handle out-of-vocabulary (OOV) tokens to improve personalized language models.
A Controllable Model of Grounded Response Generation
Current end-to-end neural conversation models inherently lack the flexibility to impose semantic control in the response generation process, often resulting in uninteresting responses.
Novel positional encodings to enable tree-based transformers
Neural models optimized for tree-based problems are of great value in tasks like SQL query extraction and program synthesis.
Multilingual Whispers: Generating Paraphrases with Translation
Naturally occurring paraphrase data, such as multiple news stories about the same event, is a useful but rare resource.
Microsoft Icecaps: An Open-Source Toolkit for Conversation Modeling
The Intelligent Conversation Engine: Code and Pre-trained Systems (Microsoft Icecaps) is an upcoming open-source natural language processing repository.
Towards Content Transfer through Grounded Text Generation
Recent work in neural generation has attracted significant interest in controlling the form of text, such as style, persona, and politeness.
Assigning people to tasks identified in email: The EPA dataset for addressee tagging for detected task intent
We describe the Enron People Assignment (EPA) dataset, in which tasks that are described in emails are associated with the person(s) responsible for carrying out these tasks.
Novel positional encodings to enable tree-structured transformers
With interest in program synthesis and similarly flavored problems rapidly increasing, neural models optimized for tree-domain problems are of great value.
Confidence Modeling for Neural Semantic Parsing
In this work we focus on confidence modeling for neural semantic parsers which are built upon sequence-to-sequence models.
Abstractions for AI-Based User Interfaces and Systems
We propose to treat these challenges as language-design problems.
Cross-Sentence N-ary Relation Extraction with Graph LSTMs
Past work in relation extraction has focused on binary relations in single sentences.
NLP for Precision Medicine
We will introduce precision medicine and showcase the vast opportunities for NLP in this burgeoning field with great societal impact.
Distant Supervision for Relation Extraction beyond the Sentence Boundary
At the core of our approach is a graph representation that can incorporate both standard dependencies and discourse relations, thus providing a unifying way to model relations within and across sentences.
deltaBLEU: A Discriminative Metric for Generation Tasks with Intrinsically Diverse Targets
We introduce Discriminative BLEU (deltaBLEU), a novel metric for intrinsic evaluation of generated text in tasks that admit a diverse range of possible outputs.
