Search Results for author:
Found 58 papers, 10 papers with code
CollFrEn: Rich Bilingual English–French Collocation Resource
Collocations in the sense of idiosyncratic lexical co-occurrences of two syntactically bound words traditionally pose a challenge to language learners and many Natural Language Processing (NLP) applications alike.
The Third Multilingual Surface Realisation Shared Task (SR’20): Overview and Evaluation Results
As in SR’18 and SR’19, the shared task comprised two tracks: (1) a Shallow Track where the inputs were full UD structures with word order information removed and tokens lemmatised; and (2) a Deep Track where additionally, functional words and morphological information were removed.
Targets and Aspects in Social Media Hate Speech
Mainstream research on hate speech focused so far predominantly on the task of classifying mainly social media posts with respect to predefined typologies of rather coarse-grained hate speech categories.
A Case Study of NLG from Multimedia Data Sources: Generating Architectural Landmark Descriptions
In this paper, we present a pipeline system that generates architectural landmark descriptions using textual, visual and structured data.
Cartography of Natural Language Processing for Social Good (NLP4SG): Searching for Definitions, Statistics and White Spots
Based on a list of keywords retrieved from the literature and revised in view of the task, we select from this corpus articles that can be considered to be on NLP4SG according to our definition and analyze them in terms of trends along the time line, etc.
Disentangling Hate Across Target Identities
Experiments on popular industrial and academic models demonstrate that HS detectors assign a higher hatefulness score merely based on the mention of specific target identities.
GPT-HateCheck: Can LLMs Write Better Functional Tests for Hate Speech Detection?
A recent proposal in this direction is HateCheck, a suite for testing fine-grained model functionalities on synthesized data generated using templates of the kind "You are just a [slur] to me."
User Identity Linkage in Social Media Using Linguistic and Social Interaction Features
Social media users often hold several accounts in their effort to multiply the spread of their thoughts, ideas, and viewpoints.
Towards Weakly-Supervised Hate Speech Classification Across Datasets
As pointed out by several scholars, current research on hate speech (HS) recognition is characterized by unsystematic data creation strategies and diverging annotation schemata.
Missing Information, Unresponsive Authors, Experimental Flaws: The Impossibility of Assessing the Reproducibility of Previous Human Evaluations in NLP
We report our efforts in identifying a set of previous human evaluations in NLP that would be suitable for a coordinated study examining what makes human evaluations in NLP more/less reproducible.
Multilingual Extraction and Categorization of Lexical Collocations with Graph-aware Transformers
Recognizing and categorizing lexical collocations in context is useful for language learning, dictionary compilation and downstream NLP.
How much pretraining data do language models need to learn syntax?
This calls for a study of the impact of pretraining data size on the knowledge of the models.
Assessing the Syntactic Capabilities of Transformer-based Multilingual Language Models
More specifically, we evaluate the syntactic generalization potential of the models on English and Spanish tests, comparing the syntactic abilities of monolingual and multilingual models on the same language (English), and of multilingual models on two different languages (English and Spanish).
Evaluating language models for the retrieval and categorization of lexical collocations
We first construct a dataset of apparitions of lexical collocations in context, categorized into 17 representative semantic categories.
On the Evolution of Syntactic Information Encoded by BERT's Contextualized Representations
The adaptation of pretrained language models to solve supervised tasks has become a baseline in NLP, and many recent works have focused on studying how linguistic information is encoded in the pretrained sentence representations.
Concept Extraction Using Pointer-Generator Networks
Concept extraction is crucial for a number of downstream applications.
Toxic, Hateful, Offensive or Abusive? What Are We Really Classifying? An Empirical Analysis of Hate Speech Datasets
The field of the automatic detection of hate speech and related concepts has raised a lot of interest in the last years.
ThemePro: A Toolkit for the Analysis of Thematic Progression
This paper introduces ThemePro, a toolkit for the automatic analysis of thematic progression.
The Second Multilingual Surface Realisation Shared Task (SR'19): Overview and Evaluation Results
We report results from the SR{'}19 Shared Task, the second edition of a multilingual surface realisation task organised as part of the EMNLP{'}19 Workshop on Multilingual Surface Realisation.
Teaching FORGe to Verbalize DBpedia Properties in Spanish
Statistical generators increasingly dominate the research in NLG.
A Hierarchically-Labeled Portuguese Hate Speech Dataset
Firstly, non-experts annotated the tweets with binary labels ({`}hate{'} vs. {`}no-hate{'}).
Collocation Classification with Unsupervised Relation Vectors
Lexical relation classification is the task of predicting whether a certain relation holds between a given pair of words.
Sentence Packaging in Text Generation from Semantic Graphs as a Community Detection Problem
An increasing amount of research tackles the challenge of text generation from abstract ontological or semantic structures, which are in their very nature potentially large connected graphs.
Underspecified Universal Dependency Structures as Inputs for Multilingual Surface Realisation
In this paper, we present the datasets used in the Shallow and Deep Tracks of the First Multilingual Surface Realisation Shared Task (SR{'}18).
The First Multilingual Surface Realisation Shared Task (SR'18): Overview and Evaluation Results
We report results from the SR{'}18 Shared Task, a new multilingual surface realisation task organised as part of the ACL{'}18 Workshop on Multilingual Surface Realisation.
Shared Task Proposal: Multilingual Surface Realization Using Universal Dependency Trees
We propose a shared task on multilingual Surface Realization, i. e., on mapping unordered and uninflected universal dependency trees to correctly ordered and inflected sentences in a number of languages.
A demo of FORGe: the Pompeu Fabra Open Rule-based Generator
This demo paper presents the multilingual deep sentence generator developed by the TALN group at Universitat Pompeu Fabra, implemented as a series of rule-based graph-transducers for the syntacticization of the input graphs, the resolution of morphological agreements, and the linearization of the trees.
FORGe at SemEval-2017 Task 9: Deep sentence generation based on a sequence of graph transducers
We present the contribution of Universitat Pompeu Fabra{'}s NLP group to the SemEval Task 9. 2 (AMR-to-English Generation).
Automatic Extraction of Parallel Speech Corpora from Dubbed Movies
This paper presents a methodology to extract parallel speech corpora based on any language pair from dubbed movies, together with an application framework in which some corresponding prosodic parameters are extracted.
On the Relevance of Syntactic and Discourse Features for Author Profiling and Identification
The majority of approaches to author profiling and author identification focus mainly on lexical features, i. e., on the content of a text.
An Automatic Prosody Tagger for Spontaneous Speech
Speech prosody is known to be central in advanced communication technologies.
Extending WordNet with Fine-Grained Collocational Information via Supervised Distributional Learning
WordNet is probably the best known lexical resource in Natural Language Processing.
Praat on the Web: An Upgrade of Praat for Semi-Automatic Speech Annotation
This paper presents an implementation of the widely used speech analysis tool Praat as a web application with an extended functionality for feature annotation.
Towards Multiple Antecedent Coreference Resolution in Specialized Discourse
Despite the popularity of coreference resolution as a research topic, the overwhelming majority of the work in this area focused so far on single antecedence coreference only.
Example-based Acquisition of Fine-grained Collocation Resources
Collocations such as {``}heavy rain{''} or {``}make [a] decision{''}, are combinations of two elements where one (the base) is freely chosen, while the choice of the other (collocate) is restricted, depending on the base.
A Semi-Supervised Approach for Gender Identification
In most of the research studies on Author Profiling, large quantities of correctly labeled data are used to train the models.
How to Use less Features and Reach Better Performance in Author Gender Identification
Over the last years, author profiling in general and author gender identification in particular have become a popular research area due to their potential attractive applications that range from forensic investigations to online marketing studies.
An Exercise in Reuse of Resources: Adapting General Discourse Coreference Resolution for Detecting Lexical Chains in Patent Documentation
The Stanford Coreference Resolution System (StCR) is a multi-pass, rule-based system that scored best in the CoNLL 2011 shared task on general discourse coreference resolution.
