Ido Dagan

SetExpander: End-to-end Term Set Expansion Based on Multi-Context Term Embeddings

2018 · International Conference on Computational Linguistics

We present SetExpander, a corpus-based system for expanding a seed set of terms into a more complete set of terms that belong to the same semantic class. SetExpander implements an iterative end-to end workflow for …

Cross-Document Language Modeling.

2021 · arXiv (Cornell University)

We introduce a new pretraining approach for language models that are geared to support multi-document NLP tasks. Our cross-document language model (CD-LM) improves masked language modeling for these tasks with two key ideas. First, we …

Realistic Evaluation Principles for Cross-document Coreference Resolution

2021 · arXiv (Cornell University)

We point out that common evaluation practices for cross-document coreference resolution have been unrealistically permissive in their assumed settings, yielding inflated results. We propose addressing this issue via two evaluation methodology principles. First, as in …

SummHelper: Collaborative Human-Computer Summarization

2023 · arXiv (Cornell University)

Current approaches for text summarization are predominantly automatic, with rather limited space for human intervention and control over the process. In this paper, we introduce SummHelper, a 2-phase summarization assistant designed to foster human-machine collaboration. …

Improving Distributional Similarity with Lessons Learned from Word Embeddings

2015 · Transactions of the Association for Computational Linguistics

Recent trends suggest that neural-network-inspired word embedding models outperform traditional count-based distributional models on word similarity and analogy detection tasks. We reveal that much of the performance gains of word embeddings are due to certain …

Do Supervised Distributional Methods Really Learn Lexical Inference Relations?

2015

Omer Levy, Steffen Remus, Chris Biemann, Ido Dagan. Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2015.

context2vec: Learning Generic Context Embedding with Bidirectional LSTM

2016

Context representations are central to various NLP tasks, such as word sense disambiguation, named entity recognition, coreference resolution, and many more. In this work we present a neural model for efficiently learning a generic context …

Supervised Open Information Extraction

2018

Gabriel Stanovsky, Julian Michael, Luke Zettlemoyer, Ido Dagan. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). 2018.

Ranking Generated Summaries by Correctness: An Interesting but Challenging Application for Natural Language Inference

2019

While recent progress on abstractive summarization has led to remarkably fluent summaries, factual errors in generated summaries still severely limit their use in practice. In this paper, we evaluate summaries produced by state-of-the-art models via …

Revisiting Joint Modeling of Cross-document Entity and Event Coreference Resolution

2019

Recognizing coreferring events and entities across multiple texts is crucial for many NLP applications. Despite the task's importance, research focus was given mostly to withindocument entity coreference, with rather little attention to the other variants. …

Zero-Shot Transfer Learning for Event Extraction

2018

Most previous supervised event extraction methods have relied on features derived from manual annotations, and thus cannot be applied to new event types without extra annotation effort. We take a fresh look at event extraction …

Still a Pain in the Neck: Evaluating Text Representations on Lexical Composition

2019 · Transactions of the Association for Computational Linguistics

Building meaningful phrase representations is challenging because phrase meanings are not simply the sum of their constituent meanings. Lexical composition can shift the meanings of the constituent words and introduce implicit information. We tested a …