
-
A Primer on Contrastive Pretraining in Language Processing: Methods, Lessons Learned and Perspectives
Modern natural language processing (NLP) methods employ self-supervised ...
read it
-
Disembodied Machine Learning: On the Illusion of Objectivity in NLP
Machine Learning seeks to identify and encode bodies of knowledge within...
read it
-
Does Typological Blinding Impede Cross-Lingual Sharing?
Bridging the performance gap between high- and low-resource languages ha...
read it
-
Multi-Sense Language Modelling
The effectiveness of a language model is influenced by its token represe...
read it
-
Longitudinal Citation Prediction using Temporal Graph Neural Networks
Citation count prediction is the task of predicting the number of citati...
read it
-
SIGTYP 2020 Shared Task: Prediction of Typological Features
Typological knowledge bases (KBs) such as WALS (Dryer and Haspelmath, 20...
read it
-
What Can We Do to Improve Peer Review in NLP?
Peer review is our best tool for judging the quality of conference submi...
read it
-
Unsupervised Evaluation for Question Answering with Transformers
It is challenging to automatically evaluate the answer of a QA model at ...
read it
-
Long-Tail Zero and Few-Shot Learning via Contrastive Pretraining on and for Small Data
For natural language processing (NLP) tasks such as sentiment or topic c...
read it
-
A Diagnostic Study of Explainability Techniques for Text Classification
Recent developments in machine learning have introduced models that appr...
read it
-
Generating Label Cohesive and Well-Formed Adversarial Claims
Adversarial attacks reveal important vulnerabilities and flaws of traine...
read it
-
Transformer Based Multi-Source Domain Adaptation
In practical machine learning settings, the data on which a model must m...
read it
-
Multi-Hop Fact Checking of Political Claims
Recently, novel multi-hop models and datasets have been introduced to ac...
read it
-
Time-Aware Evidence Ranking for Fact-Checking
Truth can vary over time. Therefore, fact-checking decisions on claim ve...
read it
-
Inducing Language-Agnostic Multilingual Representations
Multilingual representations have the potential to make cross-lingual sy...
read it
-
2kenize: Tying Subword Sequences for Chinese Script Conversion
Simplified Chinese to Traditional Chinese character conversion is a comm...
read it
-
SubjQA: A Dataset for Subjectivity and Review Comprehension
Subjectivity is the expression of internal opinions or beliefs which can...
read it
-
Generating Fact Checking Explanations
Most existing work on automated fact checking is concerned with predicti...
read it
-
Zero-Shot Cross-Lingual Transfer with Meta Learning
Learning what to share between tasks has been a topic of high importance...
read it
-
Fact Check-Worthiness Detection as Positive Unlabelled Learning
A critical component of automatically combating misinformation is the de...
read it
-
TX-Ray: Quantifying and Explaining Model-Knowledge Transfer in (Un-)Supervised NLP
While state-of-the-art NLP explainability (XAI) methods focus on supervi...
read it
-
Joint Emotion Label Space Modelling for Affect Lexica
Emotion lexica are commonly used resources to combat data poverty in aut...
read it
-
Mapping (Dis-)Information Flow about the MH17 Plane Crash
Digital media enables not only fast sharing of information, but also dis...
read it
-
Retrieval-based Goal-Oriented Dialogue Generation
Most research on dialogue has focused either on dialogue generation for ...
read it
-
Domain Transfer in Dialogue Systems without Turn-Level Supervision
Task oriented dialogue systems rely heavily on specialized dialogue stat...
read it
-
Back to the Future -- Sequential Alignment of Text Representations
Language evolves over time in many ways relevant to natural language pro...
read it
-
MultiFC: A Real-World Multi-Domain Dataset for Evidence-Based Fact Checking of Claims
We contribute the largest publicly available dataset of naturally occurr...
read it
-
Transductive Auxiliary Task Self-Training for Neural Multi-Task Models
Multi-task learning and self-training are two common ways to improve a m...
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...
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...
read it
-
Uncovering Probabilistic Implications in Typological Knowledge Bases
The study of linguistic typology is rooted in the implications we find b...
read it
-
Unsupervised Discovery of Gendered Language through Latent-Variable Modeling
Studying the ways in which language is gendered has long been an area of...
read it
-
Issue Framing in Online Discussion Fora
In online discussion fora, speakers often make arguments for or against ...
read it
-
Combining Sentiment Lexica with a Multi-View Variational Autoencoder
When assigning quantitative labels to a dataset, different methodologies...
read it
-
A Probabilistic Generative Model of Linguistic Typology
In the Principles and Parameters framework, the structural features of l...
read it
-
What do Language Representations Really Represent?
A neural language model trained on a text corpus can be used to induce d...
read it
-
Copenhagen at CoNLL--SIGMORPHON 2018: Multilingual Inflection in Context with Explicit Morphosyntactic Decoding
This paper documents the Team Copenhagen system which placed first in th...
read it
-
Nightmare at test time: How punctuation prevents parsers from generalizing
Punctuation is a strong indicator of syntactic structure, and parsers tr...
read it
-
Parameter sharing between dependency parsers for related languages
Previous work has suggested that parameter sharing between transition-ba...
read it
-
A strong baseline for question relevancy ranking
The best systems at the SemEval-16 and SemEval-17 community question ans...
read it
-
Jack the Reader - A Machine Reading Framework
Many Machine Reading and Natural Language Understanding tasks require re...
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 ...
read it
-
From Phonology to Syntax: Unsupervised Linguistic Typology at Different Levels with Language Embeddings
A core part of linguistic typology is the classification of languages ac...
read it
-
Discourse-Aware Rumour Stance Classification in Social Media Using Sequential Classifiers
Rumour stance classification, defined as classifying the stance of speci...
read it
-
Tracking Typological Traits of Uralic Languages in Distributed Language Representations
Although linguistic typology has a long history, computational approache...
read it
-
A simple but tough-to-beat baseline for the Fake News Challenge stance detection task
Identifying public misinformation is a complicated and challenging task....
read it
-
A Supervised Approach to Extractive Summarisation of Scientific Papers
Automatic summarisation is a popular approach to reduce a document to it...
read it
-
Sluice networks: Learning what to share between loosely related tasks
Multi-task learning is partly motivated by the observation that humans b...
read it
-
Turing at SemEval-2017 Task 8: Sequential Approach to Rumour Stance Classification with Branch-LSTM
This paper describes team Turing's submission to SemEval 2017 RumourEval...
read it
-
SemEval 2017 Task 10: ScienceIE - Extracting Keyphrases and Relations from Scientific Publications
We describe the SemEval task of extracting keyphrases and relations betw...
read it