Tiantian Zhu

Bio: Tiantian Zhu is an academic researcher from East China Normal University. The author has contributed to research in topics: Semantic similarity & SemEval. The author has an hindex of 3, co-authored 3 publications receiving 127 citations.

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

Abstract: 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.

ECNU: Expression- and Message-level Sentiment Orientation Classification in Twitter Using Multiple Effective Features

Abstract: Microblogging websites (such as Twitter, Facebook) are rich sources of data for opinion mining and sentiment analysis. In this paper, we describe our approaches used for sentiment analysis in twitter (task 9) organized in SemEval 2014. This task tries to determine whether the sentiment orientations conveyed by the whole tweets or pieces of tweets are positive, negative or neutral. To solve this problem, we extracted several simple and basic features considering the following aspects: surface text, syntax, sentiment score and twitter characteristic. Then we exploited these features to build a classifier using SVM algorithm. Despite the simplicity of features, our systems rank above the average.

ECNU: Leveraging on Ensemble of Heterogeneous Features and Information Enrichment for Cross Level Semantic Similarity Estimation

Abstract: This paper reports our submissions to the Cross Level Semantic Similarity (CLSS) task in SemEval 2014. We submitted one Random Forest regression system on each cross level text pair, i.e., Paragraph to Sentence (P-S), Sentence to Phrase (SPh), Phrase to Word (Ph-W) and Word to Sense (W-Se). For text pairs on P-S level and S-Ph level, we consider them as sentences and extract heterogeneous types of similarity features, i.e., string features, knowledge based features, corpus based features, syntactic features, machine translation based features, multi-level text features, etc. For text pairs on Ph-W level and W-Se level, due to lack of information, most of these features are not applicable or available. To overcome this problem, we propose several information enrichment methods using WordNet synonym and definition. Our systems rank the 2nd out of 18 teams both on Pearson correlation (official rank) and Spearman rank correlation. Specifically, our systems take the second place on P-S level, S-Ph level and Ph-W level and the 4th place on W-Se level in terms of Pearson correlation.

Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks

Abstract: A Long Short-Term Memory (LSTM) network is a type of recurrent neural network architecture which has recently obtained strong results on a variety of sequence modeling tasks. The only underlying LSTM structure that has been explored so far is a linear chain. However, natural language exhibits syntactic properties that would naturally combine words to phrases. We introduce the Tree-LSTM, a generalization of LSTMs to tree-structured network topologies. TreeLSTMs outperform all existing systems and strong LSTM baselines on two tasks: predicting the semantic relatedness of two sentences (SemEval 2014, Task 1) and sentiment classification (Stanford Sentiment Treebank).

Skip-thought vectors

Abstract: We describe an approach for unsupervised learning of a generic, distributed sentence encoder. Using the continuity of text from books, we train an encoder-decoder model that tries to reconstruct the surrounding sentences of an encoded passage. Sentences that share semantic and syntactic properties are thus mapped to similar vector representations. We next introduce a simple vocabulary expansion method to encode words that were not seen as part of training, allowing us to expand our vocabulary to a million words. After training our model, we extract and evaluate our vectors with linear models on 8 tasks: semantic relatedness, paraphrase detection, image-sentence ranking, question-type classification and 4 benchmark sentiment and subjectivity datasets. The end result is an off-the-shelf encoder that can produce highly generic sentence representations that are robust and perform well in practice.

Skip-Thought Vectors

Abstract: We describe an approach for unsupervised learning of a generic, distributed sentence encoder. Using the continuity of text from books, we train an encoder-decoder model that tries to reconstruct the surrounding sentences of an encoded passage. Sentences that share semantic and syntactic properties are thus mapped to similar vector representations. We next introduce a simple vocabulary expansion method to encode words that were not seen as part of training, allowing us to expand our vocabulary to a million words. After training our model, we extract and evaluate our vectors with linear models on 8 tasks: semantic relatedness, paraphrase detection, image-sentence ranking, question-type classification and 4 benchmark sentiment and subjectivity datasets. The end result is an off-the-shelf encoder that can produce highly generic sentence representations that are robust and perform well in practice. We will make our encoder publicly available.

ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs

Abstract: How to model a pair of sentences is a critical issue in many NLP tasks such as answer selection (AS), paraphrase identification (PI) and textual entailment (TE). Most prior work (i) deals with one individual task by fine-tuning a specific system; (ii) models each sentence's representation separately, rarely considering the impact of the other sentence; or (iii) relies fully on manually designed, task-specific linguistic features. This work presents a general Attention Based Convolutional Neural Network (ABCNN) for modeling a pair of sentences. We make three contributions. (i) The ABCNN can be applied to a wide variety of tasks that require modeling of sentence pairs. (ii) We propose three attention schemes that integrate mutual influence between sentences into CNNs; thus, the representation of each sentence takes into consideration its counterpart. These interdependent sentence pair representations are more powerful than isolated sentence representations. (iii) ABCNNs achieve state-of-the-art performance on AS, PI and TE tasks. We release code at: https://github.com/yinwenpeng/Answer_Selection.

Siamese recurrent architectures for learning sentence similarity

Abstract: We present a siamese adaptation of the Long Short-Term Memory (LSTM) network for labeled data comprised of pairs of variable-length sequences. Our model is applied to assess semantic similarity between sentences, where we exceed state of the art, outperforming carefully handcrafted features and recently proposed neural network systems of greater complexity. For these applications, we provide word-embedding vectors supplemented with synonymic information to the LSTMs, which use a fixed size vector to encode the underlying meaning expressed in a sentence (irrespective of the particular wording/syntax). By restricting subsequent operations to rely on a simple Manhattan metric, we compel the sentence representations learned by our model to form a highly structured space whose geometry reflects complex semantic relationships. Our results are the latest in a line of findings that showcase LSTMs as powerful language models capable of tasks requiring intricate understanding.