A Hierarchical LSTM Model for Joint Tasks
نویسندگان
چکیده
Previous work has shown that joint modeling of two Natural Language Processing (NLP) tasks are effective for achieving better performances for both tasks. Lots of task-specific joint models are proposed. This paper proposes a Hierarchical Long Short-Term Memory (HLSTM) model and some its variants for modeling two tasks jointly. The models are flexible for modeling different types of combinations of tasks. It avoids task-specific feature engineering. Besides the enabling of correlation information between tasks, our models take the hierarchical relations between two tasks into consideration, which is not discussed in previous work. Experimental results show that our models outperform strong baselines in three different types of task combination. While both correlation information and hierarchical relations between two tasks are helpful to improve performances for both tasks, the models especially boost performance of tasks on the top of the hierarchical structures.
منابع مشابه
Variational Bi-LSTMs
Recurrent neural networks like long short-term memory (LSTM) are important architectures for sequential prediction tasks. LSTMs (and RNNs in general) model sequences along the forward time direction. Bidirectional LSTMs (Bi-LSTMs) on the other hand model sequences along both forward and backward directions and are generally known to perform better at such tasks because they capture a richer rep...
متن کاملUser Classification with Multiple Textual Perspectives
Textual information is of critical importance for automatic user classification in social media. However, most previous studies model textual features in a single perspective while the text in a user homepage typically possesses different styles of text, such as original message and comment from others. In this paper, we propose a novel approach, namely ensemble LSTM, to user classification by ...
متن کاملGeometric Scene Parsing with Hierarchical LSTM
This paper addresses the problem of geometric scene parsing, i.e. simultaneously labeling geometric surfaces (e.g. sky, ground and vertical plane) and determining the interaction relations (e.g. layering, supporting, siding and affinity) between main regions. This problem is more challenging than the traditional semantic scene labeling, as recovering geometric structures necessarily requires th...
متن کاملLatent LSTM Allocation: Joint Clustering and Non-Linear Dynamic Modeling of Sequence Data
Recurrent neural networks, such as long-short term memory (LSTM) networks, are powerful tools for modeling sequential data like user browsing history (Tan et al., 2016; Korpusik et al., 2016) or natural language text (Mikolov et al., 2010). However, to generalize across different user types, LSTMs require a large number of parameters, notwithstanding the simplicity of the underlying dynamics, r...
متن کاملA Joint Semantic Vector Representation Model for Text Clustering and Classification
Text clustering and classification are two main tasks of text mining. Feature selection plays the key role in the quality of the clustering and classification results. Although word-based features such as term frequency-inverse document frequency (TF-IDF) vectors have been widely used in different applications, their shortcoming in capturing semantic concepts of text motivated researches to use...
متن کامل