Daniel Hardt


2018

pdf bib
Classifying Sluice Occurrences in Dialogue
Austin Baird | Anissa Hamza | Daniel Hardt
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

pdf bib
Sluice Resolution without Hand-Crafted Features over Brittle Syntax Trees
Ola Rønning | Daniel Hardt | Anders Søgaard
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)

Sluice resolution in English is the problem of finding antecedents of wh-fronted ellipses. Previous work has relied on hand-crafted features over syntax trees that scale poorly to other languages and domains; in particular, to dialogue, which is one of the most interesting applications of sluice resolution. Syntactic information is arguably important for sluice resolution, but we show that multi-task learning with partial parsing as auxiliary tasks effectively closes the gap and buys us an additional 9% error reduction over previous work. Since we are not directly relying on features from partial parsers, our system is more robust to domain shifts, giving a 26% error reduction on embedded sluices in dialogue.

pdf bib
Predicting News Headline Popularity with Syntactic and Semantic Knowledge Using Multi-Task Learning
Sotiris Lamprinidis | Daniel Hardt | Dirk Hovy
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Newspapers need to attract readers with headlines, anticipating their readers’ preferences. These preferences rely on topical, structural, and lexical factors. We model each of these factors in a multi-task GRU network to predict headline popularity. We find that pre-trained word embeddings provide significant improvements over untrained embeddings, as do the combination of two auxiliary tasks, news-section prediction and part-of-speech tagging. However, we also find that performance is very similar to that of a simple Logistic Regression model over character n-grams. Feature analysis reveals structural patterns of headline popularity, including the use of forward-looking deictic expressions and second person pronouns.

pdf bib
Linguistic representations in multi-task neural networks for ellipsis resolution
Ola Rønning | Daniel Hardt | Anders Søgaard
Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP

Sluicing resolution is the task of identifying the antecedent to a question ellipsis. Antecedents are often sentential constituents, and previous work has therefore relied on syntactic parsing, together with complex linguistic features. A recent model instead used partial parsing as an auxiliary task in sequential neural network architectures to inject syntactic information. We explore the linguistic information being brought to bear by such networks, both by defining subsets of the data exhibiting relevant linguistic characteristics, and by examining the internal representations of the network. Both perspectives provide evidence for substantial linguistic knowledge being deployed by the neural networks.

2017

pdf bib
Predicting User Views in Online News
Daniel Hardt | Owen Rambow
Proceedings of the 2017 EMNLP Workshop: Natural Language Processing meets Journalism

We analyze user viewing behavior on an online news site. We collect data from 64,000 news articles, and use text features to predict frequency of user views. We compare predictiveness of the headline and “teaser” (viewed before clicking) and the body (viewed after clicking). Both are predictive of clicking behavior, with the full article text being most predictive.

2016

pdf bib
Antecedent Selection for Sluicing: Structure and Content
Pranav Anand | Daniel Hardt
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

2005

pdf bib
Syntactic Identification of Attribution in the RST Treebank
Peter Rossen Skadhauge | Daniel Hardt
Proceedings of the Sixth International Workshop on Linguistically Interpreted Corpora (LINC-2005)

2004

pdf bib
Dynamic Centering
Daniel Hardt
Proceedings of the Conference on Reference Resolution and Its Applications

2001

pdf bib
Generation of VP Ellipsis: A Corpus-Based Approach
Daniel Hardt | Owen Rambow
Proceedings of the 39th Annual Meeting of the Association for Computational Linguistics

1997

pdf bib
An Empirical Approach to VP Ellipsis
Daniel Hardt
Computational Linguistics, Volume 23, Number 4, December 1997

1996

pdf bib
Centering in Dynamic Semantics
Daniel Hardt
COLING 1996 Volume 1: The 16th International Conference on Computational Linguistics

1992

pdf bib
An Algorithm for VP Ellipsis
Daniel Hardt
30th Annual Meeting of the Association for Computational Linguistics

pdf bib
Some Problematic Cases of VP Ellipsis
Daniel Hardt
30th Annual Meeting of the Association for Computational Linguistics

pdf bib
VP Ellipsis and Contextual Interpretation
Daniel Hardt
COLING 1992 Volume 1: The 15th International Conference on Computational Linguistics