Bei Shi


2020

pdf
Unsupervised KB-to-Text Generation with Auxiliary Triple Extraction using Dual Learning
Zihao Fu | Bei Shi | Lidong Bing | Wai Lam
Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing

KB-to-text task aims at generating texts based on the given KB triples. Traditional methods usually map KB triples to sentences via a supervised seq-to-seq model. However, existing annotated datasets are very limited and human labeling is very expensive. In this paper, we propose a method which trains the generation model in a completely unsupervised way with unaligned raw text data and KB triples. Our method exploits a novel dual training framework which leverages the inverse relationship between the KB-to-text generation task and an auxiliary triple extraction task. In our architecture, we reconstruct KB triples or texts via a closed-loop framework via linking a generator and an extractor. Therefore the loss function that accounts for the reconstruction error of KB triples and texts can be used to train the generator and extractor. To resolve the cold start problem in training, we propose a method using a pseudo data generator which generates pseudo texts and KB triples for learning an initial model. To resolve the multiple-triple problem, we design an allocated reinforcement learning component to optimize the reconstruction loss. The experimental results demonstrate that our model can outperform other unsupervised generation methods and close to the bound of supervised methods.

pdf
Partially-Aligned Data-to-Text Generation with Distant Supervision
Zihao Fu | Bei Shi | Wai Lam | Lidong Bing | Zhiyuan Liu
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

The Data-to-Text task aims to generate human-readable text for describing some given structured data enabling more interpretability. However, the typical generation task is confined to a few particular domains since it requires well-aligned data which is difficult and expensive to obtain. Using partially-aligned data is an alternative way of solving the dataset scarcity problem. This kind of data is much easier to obtain since it can be produced automatically. However, using this kind of data induces the over-generation problem posing difficulties for existing models, which tends to add unrelated excerpts during the generation procedure. In order to effectively utilize automatically annotated partially-aligned datasets, we extend the traditional generation task to a refined task called Partially-Aligned Data-to-Text Generation (PADTG) which is more practical since it utilizes automatically annotated data for training and thus considerably expands the application domains. To tackle this new task, we propose a novel distant supervision generation framework. It firstly estimates the input data’s supportiveness for each target word with an estimator and then applies a supportiveness adaptor and a rebalanced beam search to harness the over-generation problem in the training and generation phases respectively. We also contribute a partially-aligned dataset (The data and source code of this paper can be obtained from https://github.com/fuzihaofzh/distant_supervision_nlg) by sampling sentences from Wikipedia and automatically extracting corresponding KB triples for each sentence from Wikidata. The experimental results show that our framework outperforms all baseline models as well as verify the feasibility of utilizing partially-aligned data.

2018

pdf
Transformation Networks for Target-Oriented Sentiment Classification
Xin Li | Lidong Bing | Wai Lam | Bei Shi
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Target-oriented sentiment classification aims at classifying sentiment polarities over individual opinion targets in a sentence. RNN with attention seems a good fit for the characteristics of this task, and indeed it achieves the state-of-the-art performance. After re-examining the drawbacks of attention mechanism and the obstacles that block CNN to perform well in this classification task, we propose a new model that achieves new state-of-the-art results on a few benchmarks. Instead of attention, our model employs a CNN layer to extract salient features from the transformed word representations originated from a bi-directional RNN layer. Between the two layers, we propose a component which first generates target-specific representations of words in the sentence, and then incorporates a mechanism for preserving the original contextual information from the RNN layer.

pdf
Learning Domain-Sensitive and Sentiment-Aware Word Embeddings
Bei Shi | Zihao Fu | Lidong Bing | Wai Lam
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Word embeddings have been widely used in sentiment classification because of their efficacy for semantic representations of words. Given reviews from different domains, some existing methods for word embeddings exploit sentiment information, but they cannot produce domain-sensitive embeddings. On the other hand, some other existing methods can generate domain-sensitive word embeddings, but they cannot distinguish words with similar contexts but opposite sentiment polarity. We propose a new method for learning domain-sensitive and sentiment-aware embeddings that simultaneously capture the information of sentiment semantics and domain sensitivity of individual words. Our method can automatically determine and produce domain-common embeddings and domain-specific embeddings. The differentiation of domain-common and domain-specific words enables the advantage of data augmentation of common semantics from multiple domains and capture the varied semantics of specific words from different domains at the same time. Experimental results show that our model provides an effective way to learn domain-sensitive and sentiment-aware word embeddings which benefit sentiment classification at both sentence level and lexicon term level.

2016

pdf
Detecting Common Discussion Topics Across Culture From News Reader Comments
Bei Shi | Wai Lam | Lidong Bing | Yinqing Xu
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

2014

pdf
A Probabilistic Co-Bootstrapping Method for Entity Set Expansion
Bei Shi | Zhenzhong Zhang | Le Sun | Xianpei Han
Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers

2012

pdf
A Cascaded Approach for CIPS-SIGHAN Micro-Blog Word Segmentation Bakeoff 2012
Bei Shi | Xianpei Han | Le Sun
Proceedings of the Second CIPS-SIGHAN Joint Conference on Chinese Language Processing