Search Results for author: Marjorie Freedman

Found 20 papers, 5 papers with code

Agenda Pushing in Email to Thwart Phishing

no code implementations ACL (dialdoc) 2021 Hyundong Cho, Genevieve Bartlett, Marjorie Freedman

In this work, we draw parallels between automatically responding to emails for combating social-engineering attacks and document-grounded response generation and lay out the blueprint of our approach.

Response Generation

Perhaps PTLMs Should Go to School – A Task to Assess Open Book and Closed Book QA

no code implementations AKBC Workshop CSKB 2021 Manuel Ciosici, Joe Cecil, Dong-Ho Lee, Alex Hedges, Marjorie Freedman, Ralph Weischedel

Our goal is to deliver a new task and leaderboard to stimulate research on question answering and pre-trained language models (PTLMs) to understand a significant instructional document, e. g., an introductory college textbook or a manual.

Question Answering

Remember what you did so you know what to do next

no code implementations30 Oct 2023 Manuel R. Ciosici, Alex Hedges, Yash Kankanampati, Justin Martin, Marjorie Freedman, Ralph Weischedel

In work contemporaneous with ours, Lin et al. (2023) demonstrated a two-part approach (SwiftSage) that uses a small LLM (T5-large) complemented by OpenAI's massive LLMs to achieve outstanding results in ScienceWorld.

Language Modelling Large Language Model +1

RECAP: Retrieval-Enhanced Context-Aware Prefix Encoder for Personalized Dialogue Response Generation

1 code implementation12 Jun 2023 Shuai Liu, Hyundong J. Cho, Marjorie Freedman, Xuezhe Ma, Jonathan May

Endowing chatbots with a consistent persona is essential to an engaging conversation, yet it remains an unresolved challenge.

Response Generation Retrieval

Understanding Multimodal Procedural Knowledge by Sequencing Multimodal Instructional Manuals

no code implementations ACL 2022 Te-Lin Wu, Alex Spangher, Pegah Alipoormolabashi, Marjorie Freedman, Ralph Weischedel, Nanyun Peng

The ability to sequence unordered events is an essential skill to comprehend and reason about real world task procedures, which often requires thorough understanding of temporal common sense and multimodal information, as these procedures are often communicated through a combination of texts and images.

Common Sense Reasoning Open-Ended Question Answering

Perhaps PTLMs Should Go to School -- A Task to Assess Open Book and Closed Book QA

no code implementations4 Oct 2021 Manuel R. Ciosici, Joe Cecil, Alex Hedges, Dong-Ho Lee, Marjorie Freedman, Ralph Weischedel

Our goal is to deliver a new task and leaderboard to stimulate research on question answering and pre-trained language models (PTLMs) to understand a significant instructional document, e. g., an introductory college textbook or a manual.

Question Answering

A Grounded Approach to Modeling Generic Knowledge Acquisition

1 code implementation7 May 2021 Deniz Beser, Joe Cecil, Marjorie Freedman, Jacob Lichtefeld, Mitch Marcus, Sarah Payne, Charles Yang

We introduce and implement a cognitively plausible model for learning from generic language, statements that express generalizations about members of a category and are an important aspect of concept development in language acquisition (Carlson & Pelletier, 1995; Gelman, 2009).

Language Acquisition

ADAM: A Sandbox for Implementing Language Learning

1 code implementation5 May 2021 Ryan Gabbard, Deniz Beser, Jacob Lichtefeld, Joe Cecil, Mitch Marcus, Sarah Payne, Charles Yang, Marjorie Freedman

We present ADAM, a software system for designing and running child language learning experiments in Python.

Language Acquisition

GAIA: A Fine-grained Multimedia Knowledge Extraction System

no code implementations ACL 2020 Manling Li, Alireza Zareian, Ying Lin, Xiaoman Pan, Spencer Whitehead, Brian Chen, Bo Wu, Heng Ji, Shih-Fu Chang, Clare Voss, Daniel Napierski, Marjorie Freedman

We present the first comprehensive, open source multimedia knowledge extraction system that takes a massive stream of unstructured, heterogeneous multimedia data from various sources and languages as input, and creates a coherent, structured knowledge base, indexing entities, relations, and events, following a rich, fine-grained ontology.

SEARCHER: Shared Embedding Architecture for Effective Retrieval

no code implementations LREC 2020 Joel Barry, Elizabeth Boschee, Marjorie Freedman, Scott Miller

We describe an approach to cross lingual information retrieval that does not rely on explicit translation of either document or query terms.

Cross-Lingual Information Retrieval Retrieval +1

Training with Streaming Annotation

no code implementations11 Feb 2020 Tongtao Zhang, Heng Ji, Shih-Fu Chang, Marjorie Freedman

In this paper, we address a practical scenario where training data is released in a sequence of small-scale batches and annotation in earlier phases has lower quality than the later counterparts.

Event Extraction

Contextualized Cross-Lingual Event Trigger Extraction with Minimal Resources

no code implementations CONLL 2019 Meryem M{'}hamdi, Marjorie Freedman, Jonathan May

Our work is the first to experiment with two event architecture variants in a cross-lingual setting, to show the effectiveness of contextualized embeddings obtained using BERT, and to explore and analyze its performance on Arabic.

Event Extraction Transfer Learning

SARAL: A Low-Resource Cross-Lingual Domain-Focused Information Retrieval System for Effective Rapid Document Triage

no code implementations ACL 2019 Elizabeth Boschee, Joel Barry, Jayadev Billa, Marjorie Freedman, Thamme Gowda, Constantine Lignos, Chester Palen-Michel, Michael Pust, Banriskhem Kayang Khonglah, Srikanth Madikeri, Jonathan May, Scott Miller

In this paper we present an end-to-end cross-lingual information retrieval (CLIR) and summarization system for low-resource languages that 1) enables English speakers to search foreign language repositories of text and audio using English queries, 2) summarizes the retrieved documents in English with respect to a particular information need, and 3) provides complete transcriptions and translations as needed.

Cross-Lingual Information Retrieval Machine Translation +2

Events Beyond ACE: Curated Training for Events

no code implementations14 Sep 2018 Ryan Gabbard, Jay DeYoung, Marjorie Freedman

We explore a human-driven approach to annotation, curated training (CT), in which annotation is framed as teaching the system by using interactive search to identify informative snippets of text to annotate, unlike traditional approaches which either annotate preselected text or use active learning.

Active Learning Event Argument Extraction

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