Anders Søgaard

is this you? claim profile

∙ 0 followers

Professor in Natural Language Processing and Machine Learning, Dpt. of Computer Science, University of Copenhagen

On the Interaction of Belief Bias and Explanations

A myriad of explainability methods have been proposed in recent years, b...
06/29/2021 ∙ by Ana Valeria Gonzalez, et al. ∙ 1 ∙ share

read it
Itihasa: A large-scale corpus for Sanskrit to English translation

This work introduces Itihasa, a large-scale translation dataset containi...
06/06/2021 ∙ by Rahul Aralikatte, et al. ∙ 0 ∙ share

read it
John praised Mary because he? Implicit Causality Bias and Its Interaction with Explicit Cues in LMs

Some interpersonal verbs can implicitly attribute causality to either th...
06/02/2021 ∙ by Yova Kementchedjhieva, et al. ∙ 0 ∙ share

read it
Minimax and Neyman-Pearson Meta-Learning for Outlier Languages

Model-agnostic meta-learning (MAML) has been recently put forth as a str...
06/02/2021 ∙ by Edoardo Maria Ponti, et al. ∙ 0 ∙ share

read it
Replicating and Extending "Because Their Treebanks Leak": Graph Isomorphism, Covariants, and Parser Performance

Søgaard (2020) obtained results suggesting the fraction of trees occurri...
06/01/2021 ∙ by Mark Anderson, et al. ∙ 0 ∙ share

read it
Do End-to-End Speech Recognition Models Care About Context?

The two most common paradigms for end-to-end speech recognition are conn...
02/17/2021 ∙ by Lasse Borgholt, et al. ∙ 0 ∙ share

read it
Does injecting linguistic structure into language models lead to better alignment with brain recordings?

Neuroscientists evaluate deep neural networks for natural language proce...
01/29/2021 ∙ by Mostafa Abdou, et al. ∙ 24 ∙ share

read it
Attention Can Reflect Syntactic Structure (If You Let It)

Since the popularization of the Transformer as a general-purpose feature...
01/26/2021 ∙ by Vinit Ravishankar, et al. ∙ 13 ∙ share

read it
Grammatical Error Correction in Low Error Density Domains: A New Benchmark and Analyses

Evaluation of grammatical error correction (GEC) systems has primarily f...
10/15/2020 ∙ by Simon Flachs, et al. ∙ 0 ∙ share

read it
Joint Semantic Analysis with Document-Level Cross-Task Coherence Rewards

Coreference resolution and semantic role labeling are NLP tasks that cap...
10/12/2020 ∙ by Rahul Aralikatte, et al. ∙ 0 ∙ share

read it
Type B Reflexivization as an Unambiguous Testbed for Multilingual Multi-Task Gender Bias

The one-sided focus on English in previous studies of gender bias in NLP...
09/24/2020 ∙ by Ana Valeria Gonzalez, et al. ∙ 0 ∙ share

read it
Worst-Case-Aware Curriculum Learning for Zero and Few Shot Transfer

Multi-task transfer learning based on pre-trained language encoders achi...
09/23/2020 ∙ by Sheng Zhang, et al. ∙ 0 ∙ share

read it
The Sensitivity of Language Models and Humans to Winograd Schema Perturbations

Large-scale pretrained language models are the major driving force behin...
05/04/2020 ∙ by Mostafa Abdou, et al. ∙ 0 ∙ share

read it
We Need to Talk About Random Splits

Gorman and Bedrick (2019) recently argued for using random splits rather...
05/01/2020 ∙ by Anders Søgaard, et al. ∙ 0 ∙ share

read it
Weakly Supervised POS Taggers Perform Poorly on Truly Low-Resource Languages

Part-of-speech (POS) taggers for low-resource languages which are exclus...
04/28/2020 ∙ by Katharina Kann, et al. ∙ 0 ∙ share

read it
Are All Good Word Vector Spaces Isomorphic?

Existing algorithms for aligning cross-lingual word vector spaces assume...
04/08/2020 ∙ by Ivan Vulić, et al. ∙ 0 ∙ share

read it
Parsing as Pretraining

Recent analyses suggest that encoders pretrained for language modeling c...
02/05/2020 ∙ by David Vilares, et al. ∙ 0 ∙ share

read it
What Do You Mean `Why?': Resolving Sluices in Conversations

In conversation, we often ask one-word questions such as `Why?' or `Who?...
11/21/2019 ∙ by Victor Petrén Bach Hansen, et al. ∙ 0 ∙ share

read it
Retrieval-based Goal-Oriented Dialogue Generation

Most research on dialogue has focused either on dialogue generation for ...
09/30/2019 ∙ by Ana Valeria Gonzalez, et al. ∙ 0 ∙ share

read it
Domain Transfer in Dialogue Systems without Turn-Level Supervision

Task oriented dialogue systems rely heavily on specialized dialogue stat...
09/16/2019 ∙ by Joachim Bingel, et al. ∙ 0 ∙ share

read it
Lost in Evaluation: Misleading Benchmarks for Bilingual Dictionary Induction

The task of bilingual dictionary induction (BDI) is commonly used for in...
09/12/2019 ∙ by Yova Kementchedjhieva, et al. ∙ 0 ∙ share

read it
A systematic comparison of methods for low-resource dependency parsing on genuinely low-resource languages

Parsers are available for only a handful of the world's languages, since...
09/06/2019 ∙ by Clara Vania, et al. ∙ 0 ∙ share

read it
Rewarding Coreference Resolvers for Being Consistent with World Knowledge

Unresolved coreference is a bottleneck for relation extraction, and high...
09/05/2019 ∙ by Rahul Aralikatte, et al. ∙ 0 ∙ share

read it
Higher-order Comparisons of Sentence Encoder Representations

Representational Similarity Analysis (RSA) is a technique developed by n...
09/01/2019 ∙ by Mostafa Abdou, et al. ∙ 0 ∙ share

read it
Ellipsis and Coreference Resolution as Question Answering

Coreference and many forms of ellipsis are similar to reading comprehens...
08/29/2019 ∙ by Rahul Aralikatte, et al. ∙ 0 ∙ share

read it
X-WikiRE: A Large, Multilingual Resource for Relation Extraction as Machine Comprehension

Although the vast majority of knowledge bases KBs are heavily biased tow...
08/14/2019 ∙ by Mostafa Abdou, et al. ∙ 0 ∙ share

read it
X-WikiRE: A Large, Multilingual Resource for Relation Extraction asMachine Comprehension

Although the vast majority of knowledge bases KBs are heavily biased tow...
08/14/2019 ∙ by Mostafa Abdou, et al. ∙ 0 ∙ share

read it
Model-based annotation of coreference

Humans do not make inferences over texts, but over models of what texts ...
06/25/2019 ∙ by Rahul Aralikatte, et al. ∙ 0 ∙ share

read it
Multi-Task Semantic Dependency Parsing with Policy Gradient for Learning Easy-First Strategies

In Semantic Dependency Parsing (SDP), semantic relations form directed a...
06/04/2019 ∙ by Shuhei Kurita, et al. ∙ 0 ∙ share

read it
Issue Framing in Online Discussion Fora

In online discussion fora, speakers often make arguments for or against ...
04/08/2019 ∙ by Mareike Hartmann, et al. ∙ 0 ∙ share

read it
Few-Shot and Zero-Shot Learning for Historical Text Normalization

Historical text normalization often relies on small training datasets. R...
03/12/2019 ∙ by Marcel Bollmann, et al. ∙ 0 ∙ share

read it
Better, Faster, Stronger Sequence Tagging Constituent Parsers

Sequence tagging models for constituent parsing are faster, but less acc...
02/28/2019 ∙ by David Vilares, et al. ∙ 0 ∙ share

read it
Jointly Learning to Label Sentences and Tokens

Learning to construct text representations in end-to-end systems can be ...
11/14/2018 ∙ by Marek Rei, et al. ∙ 8 ∙ share

read it
Why is unsupervised alignment of English embeddings from different algorithms so hard?

This paper presents a challenge to the community: Generative adversarial...
09/01/2018 ∙ by Mareike Hartmann, et al. ∙ 0 ∙ share

read it
Nightmare at test time: How punctuation prevents parsers from generalizing

Punctuation is a strong indicator of syntactic structure, and parsers tr...
08/31/2018 ∙ by Anders Søgaard, et al. ∙ 0 ∙ share

read it
Generalizing Procrustes Analysis for Better Bilingual Dictionary Induction

Most recent approaches to bilingual dictionary induction find a linear a...
08/31/2018 ∙ by Yova Kementchedjhieva, et al. ∙ 0 ∙ share

read it
A Discriminative Latent-Variable Model for Bilingual Lexicon Induction

We introduce a novel discriminative latent-variable model for the task o...
08/28/2018 ∙ by Sebastian Ruder, et al. ∙ 2 ∙ share

read it
Parameter sharing between dependency parsers for related languages

Previous work has suggested that parameter sharing between transition-ba...
08/27/2018 ∙ by Miryam de Lhoneux, et al. ∙ 0 ∙ share

read it
A strong baseline for question relevancy ranking

The best systems at the SemEval-16 and SemEval-17 community question ans...
08/27/2018 ∙ by Ana V. González-Garduño, et al. ∙ 0 ∙ share

read it
On the Limitations of Unsupervised Bilingual Dictionary Induction

Unsupervised machine translation---i.e., not assuming any cross-lingual ...
05/09/2018 ∙ by Anders Søgaard, et al. ∙ 2 ∙ share

read it
Zero-shot Sequence Labeling: Transferring Knowledge from Sentences to Tokens

Can attention- or gradient-based visualization techniques be used to inf...
05/06/2018 ∙ by Marek Rei, et al. ∙ 0 ∙ share

read it
Multi-task Learning of Pairwise Sequence Classification Tasks Over Disparate Label Spaces

We combine multi-task learning and semi-supervised learning by inducing ...
02/27/2018 ∙ by Isabelle Augenstein, et al. ∙ 0 ∙ share

read it
Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm

NLP tasks are often limited by scarcity of manually annotated data. In s...
08/01/2017 ∙ by Bjarke Felbo, et al. ∙ 0 ∙ share

read it
Is writing style predictive of scientific fraud?

The problem of detecting scientific fraud using machine learning was rec...
07/13/2017 ∙ by Chloé Braud, et al. ∙ 0 ∙ share

read it
A Survey Of Cross-lingual Word Embedding Models

Cross-lingual representations of words enable us to reason about word me...
06/15/2017 ∙ by Sebastian Ruder, et al. ∙ 0 ∙ share

read it
Sluice networks: Learning what to share between loosely related tasks

Multi-task learning is partly motivated by the observation that humans b...
05/23/2017 ∙ by Sebastian Ruder, et al. ∙ 0 ∙ share

read it
Cross-lingual and cross-domain discourse segmentation of entire documents

Discourse segmentation is a crucial step in building end-to-end discours...
04/13/2017 ∙ by Chloé Braud, et al. ∙ 0 ∙ share

read it
Multi-Task Learning of Keyphrase Boundary Classification

Keyphrase boundary classification (KBC) is the task of detecting keyphra...
04/03/2017 ∙ by Isabelle Augenstein, et al. ∙ 0 ∙ share

read it
Identifying beneficial task relations for multi-task learning in deep neural networks

Multi-task learning (MTL) in deep neural networks for NLP has recently r...
02/27/2017 ∙ by Joachim Bingel, et al. ∙ 0 ∙ share

read it
Parsing Universal Dependencies without training

We propose UDP, the first training-free parser for Universal Dependencie...
01/11/2017 ∙ by Héctor Martínez Alonso, et al. ∙ 0 ∙ share

read it

Anders Søgaard

Featured Co-authors