Daniele Pighin

Google (United States)

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Alessandro Moschitti

Amazon (United States)

Roberto Basili

University of Rome Tor Vergata

GÖ

Gözde Özbal

Fondazione Bruno Kessler

Carlo Strapparava

Fondazione Bruno Kessler

Lluı́s Màrquez

Amazon (Germany)

Sebastian Krause

German Research Centre for Artificial Intelligence

Enrique Alfonseca

Google (United States)

Mikhail Kozhevnikov

Ural Federal University

Bonaventura Coppola

University of Trento

Jakub Adámek

Silesian University of Technology

Cooperative Institutions

Google (United States)

Fondazione Bruno Kessler

Jožef Stefan Institute

University of Trento

Google (Switzerland)

Ferioli & Gianotti (Italy)

Istituto Centrale per la Ricerca Scientifica e Tecnologica Applicata al Mare

Universitat Politècnica de Catalunya

University of Copenhagen

Amazon (United States)

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

Tree Kernels for Semantic Role Labeling

Computational Linguistics (2008)

Alessandro Moschitti Daniele Pighin Roberto Basili

The availability of large scale data sets of manually annotated predicate-argument structures has recently favored the use of machine learning approaches to the design of automated semantic role labeling (SRL) systems. The main research in this area relates to the design choices for feature representation and for effective decompositions of the task in different learning models. Regarding the former choice, structural properties of full syntactic parses are largely employed as they represent ways to encode different principles suggested by the linking theory between syntax and semantics. The latter choice relates to several learning schemes over global views of the parses. For example, re-ranking stages operating over alternative predicate-argument sequences of the same sentence have shown to be very effective. In this article, we propose several kernel functions to model parse tree properties in kernel-based machines, for example, perceptrons or support vector machines. In particular, we define different kinds of tree kernels as general approaches to feature engineering in SRL. Moreover, we extensively experiment with such kernels to investigate their contribution to individual stages of an SRL architecture both in isolation and in combination with other traditional manually coded features. The results for boundary recognition, classification, and re-ranking stages provide systematic evidence about the significant impact of tree kernels on the overall accuracy, especially when the amount of training data is small. As a conclusive result, tree kernels allow for a general and easily portable feature engineering method which is applicable to a large family of natural language processing tasks.

Tree kernel

Semantic role labeling

Predicate (mathematical logic)

Tree (set theory)

10.1162/coli.2008.34.2.193

Cite

Citations (161)

CUNIT

Mona Diab Alessandro Moschitti Daniele Pighin

In this paper, we present a system for Arabic semantic role labeling (SRL) based on SVMs and standard features. The system is evaluated on the released SEMEVAL 2007 development and test data. The results show an Fβ=1 score of 94.06 on argument boundary detection and an overall Fβ=1 score of 81.43 on the complete semantic role labeling task using gold parse trees.

SemEval

Argument (complex analysis)

Semantic role labeling

F1 score

10.3115/1621474.1621500

Cite

Citations (8)

Stepwise Extractive Summarization and Planning with Structured Transformers

arXiv (Cornell University) (2020)

Shashi Narayan Joshua Maynez Jakub Adámek Daniele Pighin Blaž Bratanič

We propose encoder-centric stepwise models for extractive summarization using structured transformers -- HiBERT and Extended Transformers. We enable stepwise summarization by injecting the previously generated summary into the structured transformer as an auxiliary sub-structure. Our models are not only efficient in modeling the structure of long inputs, but they also do not rely on task-specific redundancy-aware modeling, making them a general purpose extractive content planner for different tasks. When evaluated on CNN/DailyMail extractive summarization, stepwise models achieve state-of-the-art performance in terms of Rouge without any redundancy aware modeling or sentence filtering. This also holds true for Rotowire table-to-text generation, where our models surpass previously reported metrics for content selection, planning and ordering, highlighting the strength of stepwise modeling. Amongst the two structured transformers we test, stepwise Extended Transformers provides the best performance across both datasets and sets a new standard for these challenges.

Source

Cite

Citations (1)

BRAINSUP: Brainstorming Support for Creative Sentence Generation

Meeting of the Association for Computational Linguistics (2013)

Gözde Özbal Daniele Pighin Carlo Strapparava

We present BRAINSUP, an extensible framework for the generation of creative sentences in which users are able to force several words to appear in the sentences and to control the generation process across several semantic dimensions, namely emotions, colors, domain relatedness and phonetic properties. We evaluate its performance on a creative sentence generation task, showing its capability of generating well-formed, catchy and effective sentences that have all the good qualities of slogans produced by human copywriters.

Brainstorming

Text generation

Source

Cite

Citations (40)

Automatic Prediction of Discourse Connectives

arXiv (Cornell University) (2017)

Eric Malmi Daniele Pighin Sebastian Krause Mikhail Kozhevnikov

Accurate prediction of suitable discourse connectives (however, furthermore, etc.) is a key component of any system aimed at building coherent and fluent discourses from shorter sentences and passages. As an example, a dialog system might assemble a long and informative answer by sampling passages extracted from different documents retrieved from the Web. We formulate the task of discourse connective prediction and release a dataset of 2.9M sentence pairs separated by discourse connectives for this task. Then, we evaluate the hardness of the task for human raters, apply a recently proposed decomposable attention (DA) model to this task and observe that the automatic predictor has a higher F1 than human raters (32 vs. 30). Nevertheless, under specific conditions the raters still outperform the DA model, suggesting that there is headroom for future improvements.

10.48550/arxiv.1702.00992

Cite

Citations (11)

The FAUST Corpus of Adequacy Assessments for Real-World Machine Translation Output

Language Resources and Evaluation (2012)

Daniele Pighin Lluı́s Màrquez Lluís Formiga

Slang

Crowdsourcing

Source

Cite

Citations (5)

Semantic role labeling via tree kernel joint inference

Alessandro Moschitti Daniele Pighin Roberto Basili

Recent work on Semantic Role Labeling (SRL) has shown that to achieve high accuracy a joint inference on the whole predicate argument structure should be applied. In this paper, we used syntactic subtrees that span potential argument structures of the target predicate in tree kernel functions. This allows Support Vector Machines to discern between correct and incorrect predicate structures and to re-rank them based on the joint probability of their arguments. Experiments on the PropBank data show that both classification and re-ranking based on tree kernels can improve SRL systems.

Predicate (mathematical logic)

Semantic role labeling

Tree kernel

10.3115/1596276.1596289

Cite

Citations (57)

FBK-IRST: Kernel methods for semantic relation extraction

Daniele Pighin

Kernel (algebra)

Relationship extraction

Source

Cite

Citations (3)

Automatic Projection of Semantic Structures: an Application to Pairwise Translation Ranking

Meeting of the Association for Computational Linguistics (2011)

Daniele Pighin Lluı́s Màrquez

We present a model for the inclusion of semantic role annotations in the framework of confidence estimation for machine translation. The model has several interesting properties, most notably: 1) it only requires a linguistic processor on the (generally well-formed) source side of the translation; 2) it does not directly rely on properties of the translation model (hence, it can be applied beyond phrase-based systems). These features make it potentially appealing for system ranking, translation re-ranking and user feedback evaluation. Preliminary experiments in pairwise hypothesis ranking on five confidence estimation benchmarks show that the model has the potential to capture salient aspects of translation quality.

Phrase

Source

Cite

Citations (10)

Evaluation of the DiversiNews diversified news service

arXiv (Cornell University) (2014)

Daniele Pighin Enrique Alfonseca Felix Leif Keppmann Mitja Trampuš

In this report we present the outcome of an extensive evaluation of the DiversiNews platform [8, 10] for diversified browsing of news, developed in the scope of the RENDER project. The evaluation was carried out along two main directions: a component evaluation, in which we assessed the maturity of the components underlying DiversiNews, and a user experience (UX) evaluation involving users of online news services. The results of the evaluation confirm the high value of DiversiNews as a novel paradigm for diversity-aware news browsing.

Scope (computer science)

Component (thermodynamics)

Value (mathematics)

10.48550/arxiv.1407.4454

Cite

Citations (1)