ECNU: One Stone Two Birds: Ensemble of Heterogenous Measures for Semantic Relatedness and Textual Entailment

By Jiang Zhao, Tiantian Zhu, Man Lan. 2014

105 citations recorded by the source corpus.

This paper presents our approach to semantic relatedness and textual entailment subtasks organized as task 1 in SemEval 2014. Specifically, we address two questions: (1) Can we solve these two subtasks together? (2) Are features proposed for textual entailment task still effective for semantic relatedness task? To address them, we extracted seven types of features including text difference measures proposed in entailment judgement subtask, as well as common text similarity measures used in both subtasks. Then we exploited the same feature set to solve the both subtasks by considering them as a regression and a classification task respectively and performed a study of influence of different features. We achieved the first and the second rank for relatedness and entailment task respectively.

Subfields: Artificial Intelligence, Natural Language Processing, Information Extraction

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 Natural Language Processing

In Information Extraction

Citations in the corpus

Skip-Thought Vectors (2015, neutral): “re used and gradients are clipped if the norm of the parameter 4 Method r ˆ MSE Illinois-LH [18] 0.7993 0.7538 0.3692 UNAL-NLP [19] 0.8070 0.7489 0.3550 Meaning Factory [20] 0.8268 0.7721 0.3224 ECNU [21] 0.8414 – – Mean vectors [22] 0.7577 0.6738 0.4557 DT-RNN [23] 0.7923 0.7319 0.3822 SDT-RNN [23]”
Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks (2015, background): “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.”
Reasoning about Entailment with Neural Attention (2015, background): “State-of-the-art 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 ”
SemEval-2014 Task 1: Evaluation of Compositional Distributional Semantic Models on Full Sentences through Semantic Relatedness and Textual Entailment (2014, background): “In the table, systems in bold are those for which the authors submitted a paper (Ferrone 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 ”
Jointly optimizing word representations for lexical and sentential tasks with the C-PHRASE model (2015, methodology): “The top performance (from the SICK SemEval shared task) was reached by Zhao et al. (2014) using a heterogeneous set of features”
Siamese Recurrent Architectures for Learning Sentence Similarity (2016, neutral): “One of the best original submissions, from Zhao, Zhu, and Lan (2014), learns vector-space representations using latent semantic analysis along with numerous other handcrafted features.”
A Natural Proof System for Natural Language (2017, methodology): “ECNU (Zhao et al., 2014) extracts 72 features (involving semantic and surface text similarities, text difference measures, corpus based features, etc.”
Modelling Sentence Pairs with Tree-structured Attentive Encoder (2016, methodology): “ECNU (Zhao et al., 2014), the best result of SemEval 2014 submissions, achieves a 0.”
ECNU at SemEval-2017 Task 1: Leverage Kernel-based Traditional NLP features and Neural Networks to Build a Universal Model for Multilingual and Cross-lingual Semantic Textual Similarity (2017, methodology): “MT based Features: Following previous work in (Zhao et al., 2014) and (Zhao et al., 2015), we use MT evaluation metrics to measure the semantic equivalence of the given sentence pairs.”
Reinforced Self-Attention Network: a Hybrid of Hard and Soft Attention for Sequence Modeling (2018, background): “Thus, it cannot be optimized through back-propagation and more typically rely on policy gradient, e.g., REINFORCE [ Williams, 1992 ] .”
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, unknown): “Again, quite interestingly, the compositional feature of Illinois increases its performance while the full system drops; similarly the compositional module of ECNU has a slightly lower drop than its full system.”