Search Results for author:
Found 21 papers, 5 papers with code
Toward Abstractive Summarization Using Semantic Representations
We present a novel abstractive summarization framework that draws on the recent development of a treebank for the Abstract Meaning Representation (AMR).
DocAMR: Multi-Sentence AMR Representation and Evaluation
Despite extensive research on parsing of English sentences into Abstraction Meaning Representation (AMR) graphs, which are compared to gold graphs via the Smatch metric, full-document parsing into a unified graph representation lacks well-defined representation and evaluation.
Diverse Retrieval-Augmented In-Context Learning for Dialogue State Tracking
There has been significant interest in zero and few-shot learning for dialogue state tracking (DST) due to the high cost of collecting and annotating task-oriented dialogues.
A New Approach Towards Autoformalization
This is a challenging task, and especially for higher-level mathematics found in research papers.
Improving Neural Machine Translation with the Abstract Meaning Representation by Combining Graph and Sequence Transformers
Previous studies have shown that the Abstract Meaning Representation (AMR) can improve Neural Machine Translation (NMT).
The Materials Science Procedural Text Corpus: Annotating Materials Synthesis Procedures with Shallow Semantic Structures
Materials science literature contains millions of materials synthesis procedures described in unstructured natural language text.
Athena: Constructing Dialogues Dynamically with Discourse Constraints
This report describes Athena, a dialogue system for spoken conversation on popular topics and current events.
ASQ: Automatically Generating Question-Answer Pairs using AMRs
We introduce ASQ, a tool to automatically mine questions and answers from a sentence using the Abstract Meaning Representation (AMR).
Avoiding Overlap in Data Augmentation for AMR-to-Text Generation
We propose methods for excluding parts of Gigaword to remove this overlap, and show that our approach leads to a more realistic evaluation of the task of AMR-to-text generation.
Forming Trees with Treeformers
Human language is known to exhibit a nested, hierarchical structure, allowing us to form complex sentences out of smaller pieces.
Automatic Identification of Motivation for Code-Switching in Speech Transcripts
We build the first system (to our knowledge) to automatically identify a wide range of motivations that speakers code-switch in everyday speech, achieving an accuracy of 75% across all motivations.
Dependency Dialogue Acts -- Annotation Scheme and Case Study
DDA combines and adapts features from existing dialogue annotation frameworks, and emphasizes the multi-relational response structure of dialogues in addition to the dialogue acts and rhetorical relations.
Does the "most sinfully decadent cake ever" taste good? Answering Yes/No Questions from Figurative Contexts
Yes/no questions, in particular, are a useful probe of figurative language understanding capabilities of large language models.
Understanding the Role of Optimization in Double Descent
Our results suggest the following implication: Double descent is unlikely to be a problem for real-world machine learning setups.
Task Contamination: Language Models May Not Be Few-Shot Anymore
Large language models (LLMs) offer impressive performance in various zero-shot and few-shot tasks.
