Search Results for author:
Found 182 papers, 6 papers with code
Neural Multi-task Text Normalization and Sanitization with Pointer-Generator
Its generator effectively captures linguistic context during normalization and sanitization while its pointer dynamically preserves the entities that are generally missing in the vocabulary.
A Systematic Study of Inner-Attention-Based Sentence Representations in Multilingual Neural Machine Translation
In particular, we show that larger intermediate layers not only improve translation quality, especially for long sentences, but also push the accuracy of trainable classification tasks.
An Evaluation Benchmark for Testing the Word Sense Disambiguation Capabilities of Machine Translation Systems
Lexical ambiguity is one of the many challenging linguistic phenomena involved in translation, i. e., translating an ambiguous word with its correct sense.
Computing with Subjectivity Lexicons
In this paper, we introduce a new set of lexicons for expressing subjectivity in text documents written in Brazilian Portuguese.
Are Word Embeddings Really a Bad Fit for the Estimation of Thematic Fit?
While neural embeddings represent a popular choice for word representation in a wide variety of NLP tasks, their usage for thematic fit modeling has been limited, as they have been reported to lag behind syntax-based count models.
Supervised Event Coding from Text Written in Arabic: Introducing Hadath
This article introduces Hadath, a supervised protocol for coding event data from text written in Arabic.
FRAQUE: a FRAme-based QUEstion-answering system for the Public Administration domain
In this paper, we propose FRAQUE, a question answering system for factoid questions in the Public administration domain.
Representing Verbs with Visual Argument Vectors
Is it possible to use images to model verb semantic similarities?
``Voices of the Great War'': A Richly Annotated Corpus of Italian Texts on the First World War
{``}Voices of the Great War{''} is the first large corpus of Italian historical texts dating back to the period of First World War.
The DipInfoUniTo Realizer at SRST'19: Learning to Rank and Deep Morphology Prediction for Multilingual Surface Realization
We describe the system presented at the SR{'}19 shared task by the DipInfoUnito team.
Big Generalizations with Small Data: Exploring the Role of Training Samples in Learning Adjectives of Size
In this paper, we experiment with a recently proposed visual reasoning task dealing with quantities {--} modeling the multimodal, contextually-dependent meaning of size adjectives ({`}big{'}, {`}small{'}) {--} and explore the impact of varying the training data on the learning behavior of a state-of-art system.
Is the Red Square Big? MALeViC: Modeling Adjectives Leveraging Visual Contexts
This work aims at modeling how the meaning of gradable adjectives of size ({`}big{'}, {`}small{'}) can be learned from visually-grounded contexts.
Training Data Augmentation for Detecting Adverse Drug Reactions in User-Generated Content
Social media provides a timely yet challenging data source for adverse drug reaction (ADR) detection.
Using NLG for speech synthesis of mathematical sentences
People with sight impairments can access to a mathematical expression by using its LaTeX source.
A Neural Network Component for Knowledge-Based Semantic Representations of Text
SNNs can be trained to encode explicit semantic knowledge from an arbitrary knowledge base, and can subsequently be combined with other deep learning architectures.
Demo Application for LETO: Learning Engine Through Ontologies
The massive amount of multi-formatted information available on the Web necessitates the design of software systems that leverage this information to obtain knowledge that is valid and useful.
An Evaluation of Language-Agnostic Inner-Attention-Based Representations in Machine Translation
In this paper, we explore a multilingual translation model with a cross-lingually shared layer that can be used as fixed-size sentence representation in different downstream tasks.
Distributional Semantics Meets Construction Grammar. towards a Unified Usage-Based Model of Grammar and Meaning
In this paper, we propose a new type of semantic representation of Construction Grammar that combines constructions with the vector representations used in Distributional Semantics.
Give It a Shot: Few-shot Learning to Normalize ADR Mentions in Social Media Posts
This paper describes the system that team MYTOMORROWS-TU DELFT developed for the 2019 Social Media Mining for Health Applications (SMM4H) Shared Task 3, for the end-to-end normalization of ADR tweet mentions to their corresponding MEDDRA codes.
The MuCoW Test Suite at WMT 2019: Automatically Harvested Multilingual Contrastive Word Sense Disambiguation Test Sets for Machine Translation
Supervised Neural Machine Translation (NMT) systems currently achieve impressive translation quality for many language pairs.
A General-Purpose Annotation Model for Knowledge Discovery: Case Study in Spanish Clinical Text
This paper presents an annotation model designed to capture a large portion of the semantics of natural language text.
Quantifiers in a Multimodal World: Hallucinating Vision with Language and Sound
Inspired by the literature on multisensory integration, we develop a computational model to ground quantifiers in perception.
Dependency Parsing with your Eyes: Dependency Structure Predicts Eye Regressions During Reading
Backward saccades during reading have been hypothesized to be involved in structural reanalysis, or to be related to the level of text difficulty.
A Study of Latent Structured Prediction Approaches to Passage Reranking
The structured output framework provides a helpful tool for learning to rank problems.
Analyzing the use of existing systems for the CLPsych 2019 Shared Task
We explore the use of two systems trained with ReachOut data from the 2016 CLPsych task, and compare them to a baseline system trained with the data provided for this task.
Designing and testing the messages produced by a virtual dietitian
This paper presents a project about the automatic generation of persuasive messages in the context of the diet management.
An Analysis of Encoder Representations in Transformer-Based Machine Translation
We assess the representations of the encoder by extracting dependency relations based on self-attention weights, we perform four probing tasks to study the amount of syntactic and semantic captured information and we also test attention in a transfer learning scenario.
Adapting SimpleNLG to Galician language
In this paper, we describe SimpleNLG-GL, an adaptation of the linguistic realisation SimpleNLG library for the Galician language.
The University of Helsinki submissions to the WMT18 news task
This paper describes the University of Helsinki{'}s submissions to the WMT18 shared news translation task for English-Finnish and English-Estonian, in both directions.
Cross-Pair Text Representations for Answer Sentence Selection
High-level semantics tasks, e. g., paraphrasing, textual entailment or question answering, involve modeling of text pairs.
Natural Language Inference
Open-Domain Question Answering
+1
Supervised Clustering of Questions into Intents for Dialog System Applications
Modern automated dialog systems require complex dialog managers able to deal with user intent triggered by high-level semantic questions.
Semantic Linking in Convolutional Neural Networks for Answer Sentence Selection
State-of-the-art networks that model relations between two pieces of text often use complex architectures and attention.
Modeling Violations of Selectional Restrictions with Distributional Semantics
Distributional Semantic Models have been successfully used for modeling selectional preferences in a variety of scenarios, since distributional similarity naturally provides an estimate of the degree to which an argument satisfies the requirement of a given predicate.
Learning to Progressively Recognize New Named Entities with Sequence to Sequence Models
In this paper, we propose to use a sequence to sequence model for Named Entity Recognition (NER) and we explore the effectiveness of such model in a progressive NER setting {--} a Transfer Learning (TL) setting.
A Flexible, Efficient and Accurate Framework for Community Question Answering Pipelines
Although deep neural networks have been proving to be excellent tools to deliver state-of-the-art results, when data is scarce and the tackled tasks involve complex semantic inference, deep linguistic processing and traditional structure-based approaches, such as tree kernel methods, are an alternative solution.
The DipInfo-UniTo system for SRST 2018
This paper describes the system developed by the DipInfo-UniTo team to participate to the shallow track of the Surface Realization Shared Task 2018.
Sociolinguistic Corpus of WhatsApp Chats in Spanish among College Students
This work presents the Sociolinguistic Corpus of WhatsApp Chats in Spanish among College Students, a corpus of raw data for general use.
Learning Hierarchical Structures On-The-Fly with a Recurrent-Recursive Model for Sequences
We propose a hierarchical model for sequential data that learns a tree on-the-fly, i. e. while reading the sequence.
Complex Word Identification: Convolutional Neural Network vs. Feature Engineering
We describe the systems of NLP-CIC team that participated in the Complex Word Identification (CWI) 2018 shared task.
SemEval-2018 Task 10: Capturing Discriminative Attributes
This paper describes the SemEval 2018 Task 10 on Capturing Discriminative Attributes.
SupWSD: A Flexible Toolkit for Supervised Word Sense Disambiguation
In this demonstration we present SupWSD, a Java API for supervised Word Sense Disambiguation (WSD).
Ranking Kernels for Structures and Embeddings: A Hybrid Preference and Classification Model
Recent work has shown that Tree Kernels (TKs) and Convolutional Neural Networks (CNNs) obtain the state of the art in answer sentence reranking.
Neural Sequence Learning Models for Word Sense Disambiguation
Word Sense Disambiguation models exist in many flavors.
Ranked #20 on
Word Sense Disambiguation
on Supervised:
What to Write? A topic recommender for journalists
In this paper we present a recommender system, What To Write and Why, capable of suggesting to a journalist, for a given event, the aspects still uncovered in news articles on which the readers focus their interest.
Adapting SimpleNLG to Spanish
We describe SimpleNLG-ES, an adaptation of the SimpleNLG realization library for the Spanish language.
Logical Metonymy in a Distributional Model of Sentence Comprehension
In theoretical linguistics, logical metonymy is defined as the combination of an event-subcategorizing verb with an entity-denoting direct object (e. g., The author began the book), so that the interpretation of the VP requires the retrieval of a covert event (e. g., writing).
Sew-Embed at SemEval-2017 Task 2: Language-Independent Concept Representations from a Semantically Enriched Wikipedia
This paper describes Sew-Embed, our language-independent approach to multilingual and cross-lingual semantic word similarity as part of the SemEval-2017 Task 2.
KeLP at SemEval-2017 Task 3: Learning Pairwise Patterns in Community Question Answering
This paper describes the KeLP system participating in the SemEval-2017 community Question Answering (cQA) task.
Learning Contextual Embeddings for Structural Semantic Similarity using Categorical Information
In this paper, we combine them by modeling context word similarity in semantic TKs.
Collaborative Partitioning for Coreference Resolution
This paper presents a collaborative partitioning algorithm{---}a novel ensemble-based approach to coreference resolution.
Self-Crowdsourcing Training for Relation Extraction
In this paper we introduce a self-training strategy for crowdsourcing.
Enriching Complex Networks with Word Embeddings for Detecting Mild Cognitive Impairment from Speech Transcripts
The approach using linguistic features yielded higher accuracy if the transcriptions of the Cinderella dataset were manually revised.
EuroSense: Automatic Harvesting of Multilingual Sense Annotations from Parallel Text
Parallel corpora are widely used in a variety of Natural Language Processing tasks, from Machine Translation to cross-lingual Word Sense Disambiguation, where parallel sentences can be exploited to automatically generate high-quality sense annotations on a large scale.
Don't understand a measure? Learn it: Structured Prediction for Coreference Resolution optimizing its measures
An interesting aspect of structured prediction is the evaluation of an output structure against the gold standard.
Effective shared representations with Multitask Learning for Community Question Answering
An important asset of using Deep Neural Networks (DNNs) for text applications is their ability to automatically engineering features.
A Practical Perspective on Latent Structured Prediction for Coreference Resolution
Latent structured prediction theory proposes powerful methods such as Latent Structural SVM (LSSVM), which can potentially be very appealing for coreference resolution (CR).
Word Sense Disambiguation: A Unified Evaluation Framework and Empirical Comparison
In this paper we develop a unified evaluation framework and analyze the performance of various Word Sense Disambiguation systems in a fair setup.
Ranked #4 on
Word Sense Disambiguation
on Knowledge-based:
Measuring the Italian-English lexical gap for action verbs and its impact on translation
This paper describes a method to measure the lexical gap of action verbs in Italian and English by using the IMAGACT ontology of action.
Semantic Indexing of Multilingual Corpora and its Application on the History Domain
The increasing amount of multilingual text collections available in different domains makes its automatic processing essential for the development of a given field.
Named Entity Recognition and Hashtag Decomposition to Improve the Classification of Tweets
We evaluate and compare several automatic classification systems using part or all of the items described in our contributions and found that filtering by part of speech and named entity recognition dramatically increase the classification precision to 77. 3 {\%}.
Towards a Distributional Model of Semantic Complexity
The composition cost of a sentence depends on the semantic coherence of the event being constructed and on the activation degree of the linguistic constructions.
Antonymy and Canonicity: Experimental and Distributional Evidence
Previous studies have showed that some pairs of antonyms are perceived to be better examples of opposition than others, and are so considered representative of the whole category (e. g., Deese, 1964; Murphy, 2003; Paradis et al., 2009).
Selecting Sentences versus Selecting Tree Constituents for Automatic Question Ranking
Community question answering (cQA) websites are focused on users who query questions onto an online forum, expecting for other users to provide them answers or suggestions.
An Interactive System for Exploring Community Question Answering Forums
We present an interactive system to provide effective and efficient search capabilities in Community Question Answering (cQA) forums.
Lexfom: a lexical functions ontology model
For example, the antonymy is a type of relation that is represented by the lexical function Anti: Anti(big) = small.
``Beware the Jabberwock, dear reader!'' Testing the distributional reality of construction semantics
Notwithstanding the success of the notion of construction, the computational tradition still lacks a way to represent the semantic content of these linguistic entities.
Neural Attention for Learning to Rank Questions in Community Question Answering
In real-world data, e. g., from Web forums, text is often contaminated with redundant or irrelevant content, which leads to introducing noise in machine learning algorithms.
The CogALex-V Shared Task on the Corpus-Based Identification of Semantic Relations
The task is split into two subtasks: (i) identification of related word pairs vs. unrelated ones; (ii) classification of the word pairs according to their semantic relation.
LexFr: Adapting the LexIt Framework to Build a Corpus-based French Subcategorization Lexicon
This paper introduces LexFr, a corpus-based French lexical resource built by adapting the framework LexIt, originally developed to describe the combinatorial potential of Italian predicates.
Summ-it++: an Enriched Version of the Summ-it Corpus
This paper presents Summ-it++, an enriched version the Summ-it corpus.
Towards Lexical Encoding of Multi-Word Expressions in Spanish Dialects
This paper describes a pilot study in lexical encoding of multi-word expressions (MWEs) in 4 Latin American dialects of Spanish: Costa Rican, Colombian, Mexican and Peruvian.
Adapting an Entity Centric Model for Portuguese Coreference Resolution
This paper presents the adaptation of an Entity Centric Model for Portuguese coreference resolution, considering 10 named entity categories.
Italian VerbNet: A Construction-based Approach to Italian Verb Classification
This paper proposes a new method for Italian verb classification -and a preliminary example of resulting classes- inspired by Levin (1993) and VerbNet (Kipper-Schuler, 2005), yet partially independent from these resources; we achieved such a result by integrating Levin and VerbNet{'}s models of classification with other theoretic frameworks and resources.
Evaluating Context Selection Strategies to Build Emotive Vector Space Models
In this paper we compare different context selection approaches to improve the creation of Emotive Vector Space Models (VSMs).
Comparative Analysis of Portuguese Named Entities Recognition Tools
This paper describes an experiment to compare four tools to recognize named entities in Portuguese texts.
NIF4OGGD - NLP Interchange Format for Open German Governmental Data
In the last couple of years the amount of structured open government data has increased significantly.
SenTube: A Corpus for Sentiment Analysis on YouTube Social Media
In this paper we present SenTube -- a dataset of user-generated comments on YouTube videos annotated for information content and sentiment polarity.
Bootstrapping an Italian VerbNet: data-driven analysis of verb alternations
The goal of this paper is to propose a classification of the syntactic alternations admitted by the most frequent Italian verbs.
Choosing which to use? A study of distributional models for nominal lexical semantic classification
This paper empirically evaluates the performances of different state-of-the-art distributional models in a nominal lexical semantic classification task.
The SSPNet-Mobile Corpus: Social Signal Processing Over Mobile Phones.
This article presents the SSPNet-Mobile Corpus, a collection of 60 mobile phone calls between unacquainted individuals (120 subjects).
Crowdsourcing for the identification of event nominals: an experiment
This paper presents the design and results of a crowdsourcing experiment on the recognition of Italian event nominals.
The IMAGACT Visual Ontology. An Extendable Multilingual Infrastructure for the representation of lexical encoding of Action
IMAGACT makes explicit the variation of meaning of action verbs within one language and allows comparisons of verb variations within and across languages.
The DIRHA simulated corpus
This paper describes a multi-microphone multi-language acoustic corpus being developed under the EC project Distant-speech Interaction for Robust Home Applications (DIRHA).
Investigating the Image of Entities in Social Media: Dataset Design and First Results
The objective of this paper is to describe the design of a dataset that deals with the image (i. e., representation, web reputation) of various entities populating the Internet: politicians, celebrities, companies, brands etc.
Entity Linking meets Word Sense Disambiguation: a Unified Approach
Entity Linking (EL) and Word Sense Disambiguation (WSD) both address the lexical ambiguity of language.
Ranked #3 on
Word Sense Disambiguation
on Knowledge-based:
The annotation of the C-ORAL-BRASIL oral through the implementation of the Palavras Parser
This article describes the morphosyntactic annotation of the C-ORAL-BRASIL speech corpus, using an adapted version of the Palavras parser.
LexIt: A Computational Resource on Italian Argument Structure
The aim of this paper is to introduce LexIt, a computational framework for the automatic acquisition and exploration of distributional information about Italian verbs, nouns and adjectives, freely available through a web interface at the address http://sesia. humnet. unipi. it/lexit.
The IMAGACT Cross-linguistic Ontology of Action. A new infrastructure for natural language disambiguation
This is a consequence of the peculiar way each natural language categorizes Action i. e. it is a consequence of semantic factors.
Enriching the ISST-TANL Corpus with Semantic Frames
The paper describes the design and the results of a manual annotation methodology devoted to enrich the ISST--TANL Corpus, derived from the Italian Syntactic--Semantic Treebank (ISST), with Semantic Frames information.
Chinese Whispers: Cooperative Paraphrase Acquisition
We present a framework for the acquisition of sentential paraphrases based on crowdsourcing.
RIDIRE-CPI: an Open Source Crawling and Processing Infrastructure for Supervised Web-Corpora Building
This paper introduces the RIDIRE-CPI, an open source tool for the building of web corpora with a specific design through a targeted crawling strategy.
