Search Results for author: Jeffrey Flanigan

Found 24 papers, 7 papers with code

The Power of the Noisy Channel: Unsupervised End-to-End Task-Oriented Dialogue with LLMs

1 code implementation23 Apr 2024 Brendan King, Jeffrey Flanigan

Training task-oriented dialogue systems typically requires turn-level annotations for interacting with their APIs: e. g. a dialogue state and the system actions taken at each step.

Task-Oriented Dialogue Systems

Future Language Modeling from Temporal Document History

1 code implementation16 Apr 2024 Changmao Li, Jeffrey Flanigan

While there are many automated systems for predicting future numerical data, such as weather, stock prices, and demand for products, there is relatively little work in automatically predicting textual data.

Language Modelling

Task Contamination: Language Models May Not Be Few-Shot Anymore

no code implementations26 Dec 2023 Changmao Li, Jeffrey Flanigan

Large language models (LLMs) offer impressive performance in various zero-shot and few-shot tasks.

Inference Attack Membership Inference Attack

Understanding the Role of Optimization in Double Descent

no code implementations6 Dec 2023 Chris Yuhao Liu, Jeffrey Flanigan

Our results suggest the following implication: Double descent is unlikely to be a problem for real-world machine learning setups.

A New Approach Towards Autoformalization

1 code implementation12 Oct 2023 Nilay Patel, Rahul Saha, Jeffrey Flanigan

This is a challenging task, and especially for higher-level mathematics found in research papers.

Entity Linking Mathematical Proofs

Does the "most sinfully decadent cake ever" taste good? Answering Yes/No Questions from Figurative Contexts

no code implementations24 Sep 2023 Geetanjali Rakshit, Jeffrey Flanigan

Yes/no questions, in particular, are a useful probe of figurative language understanding capabilities of large language models.

Question Answering

Diverse Retrieval-Augmented In-Context Learning for Dialogue State Tracking

1 code implementation4 Jul 2023 Brendan King, Jeffrey Flanigan

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.

Dialogue State Tracking Few-Shot Learning +2

Dependency Dialogue Acts -- Annotation Scheme and Case Study

no code implementations25 Feb 2023 Jon Z. Cai, Brendan King, Margaret Perkoff, Shiran Dudy, Jie Cao, Marie Grace, Natalia Wojarnik, Ananya Ganesh, James H. Martin, Martha Palmer, Marilyn Walker, Jeffrey Flanigan

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.

Automatic Identification of Motivation for Code-Switching in Speech Transcripts

no code implementations30 Nov 2022 Ritu Belani, Jeffrey Flanigan

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.

Forming Trees with Treeformers

no code implementations14 Jul 2022 Nilay Patel, Jeffrey Flanigan

Human language is known to exhibit a nested, hierarchical structure, allowing us to form complex sentences out of smaller pieces.

Abstractive Text Summarization Inductive Bias +3

DocAMR: Multi-Sentence AMR Representation and Evaluation

1 code implementation NAACL 2022 Tahira Naseem, Austin Blodgett, Sadhana Kumaravel, Tim O'Gorman, Young-suk Lee, Jeffrey Flanigan, Ramón Fernandez Astudillo, Radu Florian, Salim Roukos, Nathan Schneider

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.

coreference-resolution Sentence

Avoiding Overlap in Data Augmentation for AMR-to-Text Generation

no code implementations ACL 2021 Wenchao Du, Jeffrey Flanigan

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.

AMR-to-Text Generation Data Augmentation +1

ASQ: Automatically Generating Question-Answer Pairs using AMRs

no code implementations20 May 2021 Geetanjali Rakshit, Jeffrey Flanigan

We introduce ASQ, a tool to automatically mine questions and answers from a sentence using the Abstract Meaning Representation (AMR).

Sentence valid

Toward Abstractive Summarization Using Semantic Representations

1 code implementation HLT 2015 Fei Liu, Jeffrey Flanigan, Sam Thomson, Norman Sadeh, Noah A. Smith

We present a novel abstractive summarization framework that draws on the recent development of a treebank for the Abstract Meaning Representation (AMR).

Abstractive Text Summarization

Cannot find the paper you are looking for? You can Submit a new open access paper.