Papers by Benjamin Sznajder

8 papers
Financial Event Extraction Using Wikipedia-Based Weak Supervision (D19-51)

Copied to clipboard

Challenge: Existing methods for detecting financial and economic events from text have relied on a knowledge-base of financial events, or corresponding financial figures.
Approach: They propose to use Wikipedia sections to extract weak labels for sentences describing economic events from text.
Outcome: The proposed method can extract weak labels for sentences describing economic events from Wikipedia sentences.
TWEETSUMM - A Dialog Summarization Dataset for Customer Service (2021.findings-emnlp)

Copied to clipboard

Challenge: a dataset focused on customer care dialog summarization is the first to focus on real-world customer care conversations . it contains extractive and abstractive summaries, and extractive summarizing methods are also introduced .
Approach: They present a customer care dialog summarization dataset with 6500 human annotated summaries . they introduce an unsupervised method for extracting dialog summary data .
Outcome: The proposed method is based on real-world customer support dialogs and includes extractive and abstractive summaries.
Using Question Answering Rewards to Improve Abstractive Summarization (2021.findings-emnlp)

Copied to clipboard

Challenge: Neural abstractive summarization models have seen improvements in recent years, but they still suffer from multiple drawbacks.
Approach: They propose a general framework to train abstractive summarization models to alleviate these issues by question-answering based rewards.
Outcome: The proposed framework is preferred over general abstractive summarization models.
Argument Invention from First Principles (P19-1)

Copied to clipboard

Challenge: Argument Invention is a task that is often referred to as a natural way of inventing arguments, but has not been formalized in the context of NLP.
Approach: They propose to define a taxonomy of recurring arguments and to automatically identify which of them are relevant to the topic.
Outcome: The proposed taxonomy is coherent, covers the relevant topics and coincides with what debaters actually argue in their speeches, and facilitates automatic argument invention for new topics.
The Benefits of Bad Advice: Autocontrastive Decoding across Model Layers (2023.acl-long)

Copied to clipboard

Challenge: Existing approaches to apply language models to tasks that require intermediate representations are less informative.
Approach: They propose a novel approach that utilizes the contrast between layers to improve text generation outputs.
Outcome: The proposed approach mitigates degenerative behaviors of the model in open-ended generation, significantly improving the quality of generated texts.
Label-Efficient Model Selection for Text Generation (2024.acl-long)

Copied to clipboard

Challenge: Model selection for a given task can entail extensive annotation of the quality of outputs of different models.
Approach: They propose a model-agnostic method to make an informed decision between candidate text generation models based on preference annotations.
Outcome: The proposed method reduces the required number of annotations by up to 75% while maintaining high evaluation reliability.
Summary Grounded Conversation Generation (2021.findings-acl)

Copied to clipboard

Challenge: Existing datasets for conversation summarization are small due to the lack of large-scale datasets.
Approach: They propose three approaches to generate summary grounded conversations, and evaluate the generated conversations using automatic measures and human judgements.
Outcome: The proposed models can generate entire conversations with only a summary of a conversation as the input.
Learning Concept Abstractness Using Weak Supervision (D18-1)

Copied to clipboard

Challenge: Existing methods for inferring abstractness of words and expressions without labeled data are limited and limited.
Approach: They propose a weakly supervised approach for inferring the property of abstractness of words and expressions in the absence of labeled data.
Outcome: The proposed approach obtains high correlation with human labels in the absence of labeled data.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations