Search Results for author:
Found 91 papers, 8 papers with code
Some Languages Seem Easier to Parse Because Their Treebanks Leak
Cross-language differences in (universal) dependency parsing performance are mostly attributed to treebank size, average sentence length, average dependency length, morphological complexity, and domain differences.
Spurious Correlations in Cross-Topic Argument Mining
Recent work in cross-topic argument mining attempts to learn models that generalise across topics rather than merely relying on within-topic spurious correlations.
Replicating and Extending ``Because Their Treebanks Leak'': Graph Isomorphism, Covariants, and Parser Performance
S{\o}gaard (2020) obtained results suggesting the fraction of trees occurring in the test data isomorphic to trees in the training set accounts for a non-trivial variation in parser performance.
Error Analysis and the Role of Morphology
We evaluate two common conjectures in error analysis of NLP models: (i) Morphology is predictive of errors; and (ii) the importance of morphology increases with the morphological complexity of a language.
Neural Speed Reading Audited
Several approaches to neural speed reading have been presented at major NLP and machine learning conferences in 2017{--}20; i. e., {``}human-inspired{''} recurrent network architectures that learn to {``}read{''} text faster by skipping irrelevant words, typically optimizing the joint objective of minimizing classification error rate and FLOPs used at inference time.
DaNE: A Named Entity Resource for Danish
We present a named entity annotation for the Danish Universal Dependencies treebank using the CoNLL-2003 annotation scheme: DaNE.
WikiBank: Using Wikidata to Improve Multilingual Frame-Semantic Parsing
Frame-semantic annotations exist for a tiny fraction of the world{'}s languages, Wikidata, however, links knowledge base triples to texts in many languages, providing a common, distant supervision signal for semantic parsers.
Adversarial Removal of Demographic Attributes Revisited
Elazar and Goldberg (2018) showed that protected attributes can be extracted from the representations of a debiased neural network for mention detection at above-chance levels, by evaluating a diagnostic classifier on a held-out subsample of the data it was trained on.
Naive Regularizers for Low-Resource Neural Machine Translation
Neural machine translation models have little inductive bias, which can be a disadvantage in low-resource scenarios.
Noisy Channel for Low Resource Grammatical Error Correction
This paper describes our contribution to the low-resource track of the BEA 2019 shared task on Grammatical Error Correction (GEC).
Unsupervised Cross-Lingual Representation Learning
In this tutorial, we provide a comprehensive survey of the exciting recent work on cutting-edge weakly-supervised and unsupervised cross-lingual word representations.
Historical Text Normalization with Delayed Rewards
Training neural sequence-to-sequence models with simple token-level log-likelihood is now a standard approach to historical text normalization, albeit often outperformed by phrase-based models.
CoAStaL at SemEval-2019 Task 3: Affect Classification in Dialogue using Attentive BiLSTMs
This work describes the system presented by the CoAStaL Natural Language Processing group at University of Copenhagen.
A Simple and Robust Approach to Detecting Subject-Verb Agreement Errors
While rule-based detection of subject-verb agreement (SVA) errors is sensitive to syntactic parsing errors and irregularities and exceptions to the main rules, neural sequential labelers have a tendency to overfit their training data.
When does deep multi-task learning work for loosely related document classification tasks?
This work aims to contribute to our understanding of \textit{when} multi-task learning through parameter sharing in deep neural networks leads to improvements over single-task learning.
Linguistic representations in multi-task neural networks for ellipsis resolution
Sluicing resolution is the task of identifying the antecedent to a question ellipsis.
Sequence Classification with Human Attention
Learning attention functions requires large volumes of data, but many NLP tasks simulate human behavior, and in this paper, we show that human attention really does provide a good inductive bias on many attention functions in NLP.
Sentiment analysis under temporal shift
Sentiment analysis models often rely on training data that is several years old.
Lexi: A tool for adaptive, personalized text simplification
Most previous research in text simplification has aimed to develop generic solutions, assuming very homogeneous target audiences with consistent intra-group simplification needs.
Multi-task learning for historical text normalization: Size matters
Historical text normalization suffers from small datasets that exhibit high variance, and previous work has shown that multi-task learning can be used to leverage data from related problems in order to obtain more robust models.
Character-level Supervision for Low-resource POS Tagging
Neural part-of-speech (POS) taggers are known to not perform well with little training data.
Sluice Resolution without Hand-Crafted Features over Brittle Syntax Trees
Sluice resolution in English is the problem of finding antecedents of \textit{wh}-fronted ellipses.
Using hyperlinks to improve multilingual partial parsers
Syntactic annotation is costly and not available for the vast majority of the world{'}s languages.
Using Gaze to Predict Text Readability
We show that text readability prediction improves significantly from hard parameter sharing with models predicting first pass duration, total fixation duration and regression duration.
Cross-Lingual Word Representations: Induction and Evaluation
With the increasing use of monolingual word vectors, there is a need for word vectors that can be used as efficiently across multiple languages as monolingually.
Is writing style predictive of scientific fraud?
The problem of detecting scientific fraud using machine learning was recently introduced, with initial, positive results from a model taking into account various general indicators.
Does syntax help discourse segmentation? Not so much
Discourse segmentation is the first step in building discourse parsers.
Huntsville, hospitals, and hockey teams: Names can reveal your location
Geolocation is the task of identifying a social media user{'}s primary location, and in natural language processing, there is a growing literature on to what extent automated analysis of social media posts can help.
Evaluating hypotheses in geolocation on a very large sample of Twitter
Recent work in geolocation has made several hypotheses about what linguistic markers are relevant to detect where people write from.
Learning attention for historical text normalization by learning to pronounce
Automated processing of historical texts often relies on pre-normalization to modern word forms.
Cross-lingual and cross-domain discourse segmentation of entire documents
Discourse segmentation is a crucial step in building end-to-end discourse parsers.
Cross-Lingual Dependency Parsing with Late Decoding for Truly Low-Resource Languages
In cross-lingual dependency annotation projection, information is often lost during transfer because of early decoding.
Cross-lingual tagger evaluation without test data
We address the challenge of cross-lingual POS tagger evaluation in absence of manually annotated test data.
Multi-view and multi-task training of RST discourse parsers
We experiment with different ways of training LSTM networks to predict RST discourse trees.
Ranked #5 on
Discourse Parsing
on RST-DT
(RST-Parseval (Full) metric)
Cross-lingual Transfer of Correlations between Parts of Speech and Gaze Features
Several recent studies have shown that eye movements during reading provide information about grammatical and syntactic processing, which can assist the induction of NLP models.
The SemDaX Corpus ― Sense Annotations with Scalable Sense Inventories
The aim of the developed corpus is twofold: i) to assess the reliability of the different sense annotation schemes for Danish measured by qualitative analyses and annotation agreement scores, and ii) to serve as training and test data for machine learning algorithms with the practical purpose of developing sense taggers for Danish.
Multilingual Projection for Parsing Truly Low-Resource Languages
We propose a novel approach to cross-lingual part-of-speech tagging and dependency parsing for truly low-resource languages.
Crowdsourcing and annotating NER for Twitter \#drift
We present two new NER datasets for Twitter; a manually annotated set of 1, 467 tweets (kappa=0. 942) and a set of 2, 975 expert-corrected, crowdsourced NER annotated tweets from the dataset described in Finin et al. (2010).
When POS data sets don't add up: Combatting sample bias
We present a systematic study of several Twitter POS data sets, the problems of label and data bias, discuss their effects on model performance, and show how to overcome them to learn models that perform well on various test sets, achieving relative error reduction of up to 21{\%}.
DSim, a Danish Parallel Corpus for Text Simplification
We compare DSim to different examples of monolingual parallel corpora, and we argue that this corpus is a promising basis for future development of automatic data-driven text simplification systems in Danish.
