Search Results for author:
Found 61 papers, 24 papers with code
Context Sensitivity Estimation in Toxicity Detection
We introduce a new task, context-sensitivity estimation, which aims to identify posts whose perceived toxicity changes if the context (previous post) is also considered.
From the Detection of Toxic Spans in Online Discussions to the Analysis of Toxic-to-Civil Transfer
We study the task of toxic spans detection, which concerns the detection of the spans that make a text toxic, when detecting such spans is possible.
MultiEURLEX - A multi-lingual and multi-label legal document classification dataset for zero-shot cross-lingual transfer
We use the dataset as a testbed for zero-shot cross-lingual transfer, where we exploit annotated training documents in one language (source) to classify documents in another language (target).
Processing Long Legal Documents with Pre-trained Transformers: Modding LegalBERT and Longformer
Even sparse-attention models, such as Longformer and BigBird, which increase the maximum input length to 4, 096 sub-words, severely truncate texts in three of the six datasets of LexGLUE.
Realistic Zero-Shot Cross-Lingual Transfer in Legal Topic Classification
We consider zero-shot cross-lingual transfer in legal topic classification using the recent MultiEURLEX dataset.
Data Augmentation for Biomedical Factoid Question Answering
We study the effect of seven data augmentation (da) methods in factoid question answering, focusing on the biomedical domain, where obtaining training instances is particularly difficult.
FiNER: Financial Numeric Entity Recognition for XBRL Tagging
We, therefore, introduce XBRL tagging as a new entity extraction task for the financial domain and release FiNER-139, a dataset of 1. 1M sentences with gold XBRL tags.
Restoring and attributing ancient texts using deep neural networks
Ithaca can attribute inscriptions to their original location with an accuracy of 71% and can date them to less than 30 years of their ground-truth ranges, redating key texts of Classical Athens and contributing to topical debates in ancient history.
Ranked #1 on
Ancient Text Restoration
on I.PHI
Toxicity Detection can be Sensitive to the Conversational Context
User posts whose perceived toxicity depends on the conversational context are rare in current toxicity detection datasets.
LexGLUE: A Benchmark Dataset for Legal Language Understanding in English
Laws and their interpretations, legal arguments and agreements\ are typically expressed in writing, leading to the production of vast corpora of legal text.
Ranked #1 on
Natural Language Understanding
on LexGLUE
MAGNEx: A Model Agnostic Global Neural Explainer
Black-box decision models have been widely adopted both in industry and academia due to their excellent performance across many challenging tasks and domains.
EDGAR-CORPUS: Billions of Tokens Make The World Go Round
We use EDGAR-CORPUS to train and release EDGAR-W2V, which are WORD2VEC embeddings for the financial domain.
MultiEURLEX -- A multi-lingual and multi-label legal document classification dataset for zero-shot cross-lingual transfer
We use the dataset as a testbed for zero-shot cross-lingual transfer, where we exploit annotated training documents in one language (source) to classify documents in another language (target).
SemEval-2021 Task 5: Toxic Spans Detection
For the supervised sequence labeling approach and evaluation purposes, posts previously labeled as toxic were crowd-annotated for toxic spans.
A Neural Model for Joint Document and Snippet Ranking in Question Answering for Large Document Collections
To test our key findings on another dataset, we modified the Natural Questions dataset so that it can also be used for document and snippet retrieval.
Deception detection in text and its relation to the cultural dimension of individualism/collectivism
Our focus is on automatic deception detection in text across cultures.
Cultural Vocal Bursts Intensity Prediction
Deception Detection
Paragraph-level Rationale Extraction through Regularization: A case study on European Court of Human Rights Cases
We also release a new dataset comprising European Court of Human Rights cases, including annotations for paragraph-level rationales.
Diagnostic Captioning: A Survey
Diagnostic Captioning (DC) concerns the automatic generation of a diagnostic text from a set of medical images of a patient collected during an examination.
Neural Contract Element Extraction Revisited: Letters from Sesame Street
Morpho-syntactic features in the form of POS tag and token shape embeddings, as well as context-aware ELMO embeddings do not improve performance.
LEGAL-BERT: The Muppets straight out of Law School
Thus we propose a systematic investigation of the available strategies when applying BERT in specialised domains.
An Empirical Study on Large-Scale Multi-Label Text Classification Including Few and Zero-Shot Labels
Furthermore, we show that Transformer-based approaches outperform the state-of-the-art in two of the datasets, and we propose a new state-of-the-art method which combines BERT with LWANs.
Multi-Label Classification
Multi Label Text Classification
+4
Domain Adversarial Fine-Tuning as an Effective Regularizer
To address this issue, we introduce a new regularization technique, AFTER; domain Adversarial Fine-Tuning as an Effective Regularizer.
GREEK-BERT: The Greeks visiting Sesame Street
We expect these resources to boost NLP research and applications for modern Greek.
Toxicity Detection: Does Context Really Matter?
Moderation is crucial to promoting healthy on-line discussions.
BIOMRC: A Dataset for Biomedical Machine Reading Comprehension
Non-expert human performance is also higher on the new dataset compared to BIOREAD, and biomedical experts perform even better.
SUM-QE: a BERT-based Summary Quality Estimation Model
We propose SUM-QE, a novel Quality Estimation model for summarization based on BERT.
SumQE: a BERT-based Summary Quality Estimation Model
We propose SumQE, a novel Quality Estimation model for summarization based on BERT.
Transfer Learning for Causal Sentence Detection
We consider the task of detecting sentences that express causality, as a step towards mining causal relations from texts.
Embedding Biomedical Ontologies by Jointly Encoding Network Structure and Textual Node Descriptors
Many existing NE methods rely only on network structure, overlooking other information associated with the nodes, e. g., text describing the nodes.
Large-Scale Multi-Label Text Classification on EU Legislation
We consider Large-Scale Multi-Label Text Classification (LMTC) in the legal domain.
Ranked #1 on
Multi-Label Text Classification
on EUR-Lex
Neural Legal Judgment Prediction in English
Legal judgment prediction is the task of automatically predicting the outcome of a court case, given a text describing the case's facts.
Ranked #1 on
Binary text classification
on ECHR Non-Anonymized
ConvAI at SemEval-2019 Task 6: Offensive Language Identification and Categorization with Perspective and BERT
This paper presents the application of two strong baseline systems for toxicity detection and evaluates their performance in identifying and categorizing offensive language in social media.
SEQ\^3: Differentiable Sequence-to-Sequence-to-Sequence Autoencoder for Unsupervised Abstractive Sentence Compression
The proposed model does not require parallel text-summary pairs, achieving promising results in unsupervised sentence compression on benchmark datasets.
A Survey on Biomedical Image Captioning
Image captioning applied to biomedical images can assist and accelerate the diagnosis process followed by clinicians.
Extreme Multi-Label Legal Text Classification: A case study in EU Legislation
We consider the task of Extreme Multi-Label Text Classification (XMTC) in the legal domain.
SEQ^3: Differentiable Sequence-to-Sequence-to-Sequence Autoencoder for Unsupervised Abstractive Sentence Compression
The proposed model does not require parallel text-summary pairs, achieving promising results in unsupervised sentence compression on benchmark datasets.
Generating Texts with Integer Linear Programming
Content selection, for example, may greedily select the most important facts, which may require, however, too many words to express, and this may be undesirable when space is limited or expensive.
Extracting Linguistic Resources from the Web for Concept-to-Text Generation
Many concept-to-text generation systems require domain-specific linguistic resources to produce high quality texts, but manually constructing these resources can be tedious and costly.
AUEB at BioASQ 6: Document and Snippet Retrieval
We present AUEB's submissions to the BioASQ 6 document and snippet retrieval tasks (parts of Task 6b, Phase A).
Deep Relevance Ranking Using Enhanced Document-Query Interactions
We explore several new models for document relevance ranking, building upon the Deep Relevance Matching Model (DRMM) of Guo et al. (2016).
Ranked #7 on
Ad-Hoc Information Retrieval
on TREC Robust04
Obligation and Prohibition Extraction Using Hierarchical RNNs
We consider the task of detecting contractual obligations and prohibitions.
Deeper Attention to Abusive User Content Moderation
Experimenting with a new dataset of 1. 6M user comments from a news portal and an existing dataset of 115K Wikipedia talk page comments, we show that an RNN operating on word embeddings outpeforms the previous state of the art in moderation, which used logistic regression or an MLP classifier with character or word n-grams.
Improved Abusive Comment Moderation with User Embeddings
Experimenting with a dataset of approximately 1. 6M user comments from a Greek news sports portal, we explore how a state of the art RNN-based moderation method can be improved by adding user embeddings, user type embeddings, user biases, or user type biases.
Deep Learning for User Comment Moderation
We also compare against a CNN and a word-list baseline, considering both fully automatic and semi-automatic moderation.
Probabilistic Cascading for Large Scale Hierarchical Classification
Hierarchies are frequently used for the organization of objects.
LSHTC: A Benchmark for Large-Scale Text Classification
LSHTC is a series of challenges which aims to assess the performance of classification systems in large-scale classification in a a large number of classes (up to hundreds of thousands).
Generating Natural Language Descriptions from OWL Ontologies: the NaturalOWL System
We present NaturalOWL, a natural language generation system that produces texts describing individuals or classes of OWL ontologies.
Evaluation Measures for Hierarchical Classification: a unified view and novel approaches
Hierarchical classification addresses the problem of classifying items into a hierarchy of classes.
A Survey of Paraphrasing and Textual Entailment Methods
Paraphrasing methods recognize, generate, or extract phrases, sentences, or longer natural language expressions that convey almost the same information.
