UNAL-NLP: Combining Soft Cardinality Features for Semantic Textual Similarity, Relatedness and Entailment

By Sergio Jiménez, George Dueñas, Julia Baquero, Alexander Gelbukh. 2014

71 citations recorded by the source corpus.

This paper describes our participation in the SemEval-2014 tasks 1, 3 and 10. We used an uniform approach for addressing all the tasks using the soft cardinality for extracting features from text pairs, and machine learning for predicting the gold standards. Our submitted systems ranked among the top systems in all the task and sub-tasks in which we participated. These results confirm the results obtained in previous SemEval campaigns suggesting that the soft cardinality is a simple and useful tool for addressing a wide range of natural language processing problems.

Subfields: Artificial Intelligence, Information Retrieval & Search, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Retrieval & Search

In Natural Language Processing

Citations in the corpus

Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks (2015, neutral): “We also compare against four of the topperforming systems6 submitted to the SemEval 2014 semantic relatedness shared task: ECNU (Zhao et al., 2014), The Meaning Factory (Bjerva et al., 2014), UNAL-NLP (Jimenez et al., 2014), and Illinois-LH (Lai and Hockenmaier, 2014).”
Reasoning about Entailment with Neural Attention (2015, background): “…systems for RTE so far relied heavily on engineered NLP pipelines, extensive manual creation of features, as well as various external resources and specialized subcomponents such as negation detection (e.g. Lai and Hockenmaier, 2014; Jimenez et al., 2014; Zhao et al., 2014; Beltagy et al., 2015).”
SemEval-2014 Task 1: Evaluation of Compositional Distributional Semantic Models on Full Sentences through Semantic Relatedness and Textual Entailment (2014, background): “…and Zanzotto, 2014; Bjerva et al., 2014; Beltagy et al., 2014; Lai and Hockenmaier, 2014; Alves et al., 2014; León et al., 2014; Bestgen, 2014; Zhao et al., 2014; Vo et al., 2014; Biçici and Way, 2014; Lien and Kouylekov, 2014; Jimenez et al., 2014; Proisl and Evert, 2014; Gupta et al., 2014).”
SemEval-2014 Task 10: Multilingual Semantic Textual Similarity (2014, neutral): “, 2014), UNALNLP (Jimenez et al., 2014), UNED (Martinez-Romo et al.”
Multi-Reward Reinforced Summarization with Saliency and Entailment (2018, methodology): “Recognizing Textual Entailment (RTE), the task of classifying two sentences as entailment, contra-diction, or neutral, has been used for Q&A and IE tasks (Harabagiu and Hickl, 2006; Dagan et al., 2006; Lai and Hockenmaier, 2014; Jimenez et al., 2014).”
Reinforced Video Captioning with Entailment Rewards (2017, background): “Recognizing Textual Entailment (RTE) is a traditional NLP task (Dagan et al., 2006; Lai and Hockenmaier, 2014; Jimenez et al., 2014), boosted by a large dataset (SNLI) recently introduced by Bowman et al. (2015).”
Soft Layer-Specific Multi-Task Summarization with Entailment and Question Generation (2018, methodology): “For the second auxiliary task of entailment generation, we use the generation version of the RTE classification task (Dagan et al., 2006; Lai and Hockenmaier, 2014; Jimenez et al., 2014; Bowman et al., 2015).”
A Natural Proof System for Natural Language (2017, methodology): “UNAL-NLP (Jimenez et al., 2014) uses Soft Cardinality for additional features and decision tree with grafting for classification.”
SICK through the SemEval glasses. Lesson learned from the evaluation of compositional distributional semantic models on full sentences through semantic relatedness and textual entailment (2016, background): “In the table, systems in bold are those for which the authors submitted a paper: haLF (Ferrone and Zanzotto, 2014) (Jimenez et al, 2014), Se-mantiKLUE (Proisl and Evert, 2014) and UoW (Gupta et al, 2014).”
Learning to Compose Words into Sentences with Reinforcement Learning (2016, methodology): “Some of these models (Lai & Hockenmaier, 2014; Jimenez et al., 2014; Bjerva et al., 2014) rely on feature engineering and are designed speciﬁcally for this task.”
Multi-Task Video Captioning with Video and Entailment Generation (2017, methodology): “The recent Stanford Natural Language Inference (SNLI) corpus by Bowman et al. (2015) allowed training end-to-end neural networks that outperform earlier feature-based RTE models (Lai and Hockenmaier, 2014; Jimenez et al., 2014).”