A Sequential Neural Encoder with Latent Structured Description for Modeling Sentences

TL;DR

This paper introduces SNELSD, a neural encoder that incorporates latent chunk-level structures into sentence modeling, improving semantic understanding without relying on external parsing.

Contribution

The paper presents a hierarchical neural model with latent chunk detection and description layers, enhancing sentence representations for NLP tasks.

Findings

SNELSD outperforms chain and tree-structured LSTMs on NLI and sentiment analysis.

The model effectively captures task-dependent chunking patterns.

End-to-end training without external syntax parsers.

Abstract

In this paper, we propose a sequential neural encoder with latent structured description (SNELSD) for modeling sentences. This model introduces latent chunk-level representations into conventional sequential neural encoders, i.e., recurrent neural networks (RNNs) with long short-term memory (LSTM) units, to consider the compositionality of languages in semantic modeling. An SNELSD model has a hierarchical structure that includes a detection layer and a description layer. The detection layer predicts the boundaries of latent word chunks in an input sentence and derives a chunk-level vector for each word. The description layer utilizes modified LSTM units to process these chunk-level vectors in a recurrent manner and produces sequential encoding outputs. These output vectors are further concatenated with word vectors or the outputs of a chain LSTM encoder to obtain the final sentence representation. All the model parameters are learned in an end-to-end manner without a dependency on additional text chunking or syntax parsing. A natural language inference (NLI) task and a sentiment analysis (SA) task are adopted to evaluate the performance of our proposed model. The experimental results demonstrate the effectiveness of the proposed SNELSD model on exploring task-dependent chunking patterns during the semantic modeling of sentences. Furthermore, the proposed method achieves better performance than conventional chain LSTMs and tree-structured LSTMs on both tasks.