Peng Liu


pdf bib
Building Sentiment Lexicons for Mainland Scandinavian Languages Using Machine Translation and Sentence Embeddings
Peng Liu | Cristina Marco | Jon Atle Gulla
Proceedings of the Thirteenth Language Resources and Evaluation Conference

This paper presents a simple but effective method to build sentiment lexicons for the three Mainland Scandinavian languages: Danish, Norwegian and Swedish. This method benefits from the English Sentiwordnet and a thesaurus in one of the target languages. Sentiment information from the English resource is mapped to the target languages by using machine translation and similarity measures based on sentence embeddings. A number of experiments with Scandinavian languages are performed in order to determine the best working sentence embedding algorithm for this task. A careful extrinsic evaluation on several datasets yields state-of-the-art results using a simple rule-based sentiment analysis algorithm. The resources are made freely available under an MIT License.

pdf bib
Balancing Multi-Domain Corpora Learning for Open-Domain Response Generation
Yujie Xing | Jinglun Cai | Nils Barlaug | Peng Liu | Jon Atle Gulla
Findings of the Association for Computational Linguistics: NAACL 2022

Open-domain conversational systems are assumed to generate equally good responses on multiple domains. Previous work achieved good performance on the single corpus, but training and evaluating on multiple corpora from different domains are less studied. This paper explores methods of generating relevant responses for each of multiple multi-domain corpora. We first examine interleaved learning which intermingles multiple corpora as the baseline. We then investigate two multi-domain learning methods, labeled learning and multi-task labeled learning, which encode each corpus through a unique corpus embedding. Furthermore, we propose Domain-specific Frequency (DF), a novel word-level importance weight that measures the relative importance of a word for a specific corpus compared to other corpora. Based on DF, we propose weighted learning, a method that integrates DF to the loss function. We also adopt DF as a new evaluation metric. Extensive experiments show that our methods gain significant improvements on both automatic and human evaluation. We share our code and data for reproducibility.


pdf bib
Email Threat Detection Using Distinct Neural Network Approaches
Esteban Castillo | Sreekar Dhaduvai | Peng Liu | Kartik-Singh Thakur | Adam Dalton | Tomek Strzalkowski
Proceedings for the First International Workshop on Social Threats in Online Conversations: Understanding and Management

This paper describes different approaches to detect malicious content in email interactions through a combination of machine learning and natural language processing tools. Specifically, several neural network designs are tested on word embedding representations to detect suspicious messages and separate them from non-suspicious, benign email. The proposed approaches are trained and tested on distinct email collections, including datasets constructed from publicly available corpora (such as Enron, APWG, etc.) as well as several smaller, non-public datasets used in recent government evaluations. Experimental results show that back-propagation both with and without recurrent neural layers outperforms current state of the art techniques that include supervised learning algorithms with stylometric elements of texts as features. Our results also demonstrate that word embedding vectors are effective means for capturing certain aspects of text meaning that can be teased out through machine learning in non-linear/complex neural networks, in order to obtain highly accurate detection of malicious emails based on email text alone.


pdf bib
YNU-HPCC at SemEval-2019 Task 8: Using A LSTM-Attention Model for Fact-Checking in Community Forums
Peng Liu | Jin Wang | Xuejie Zhang
Proceedings of the 13th International Workshop on Semantic Evaluation

We propose a system that uses a long short-term memory with attention mechanism (LSTM-Attention) model to complete the task. The LSTM-Attention model uses two LSTM to extract the features of the question and answer pair. Then, each of the features is sequentially composed using the attention mechanism, concatenating the two vectors into one. Finally, the concatenated vector is used as input for the MLP and the MLP’s output layer uses the softmax function to classify the provided answers into three categories. This model is capable of extracting the features of the question and answer pair well. The results show that the proposed system outperforms the baseline algorithm.


pdf bib
Approach to Selecting Best Development Set for Phrase-Based Statistical Machine Translation
Peng Liu | Yu Zhou | Chengqing Zong
Proceedings of the 23rd Pacific Asia Conference on Language, Information and Computation, Volume 1


pdf bib
Performance of Discriminative HMM Training in Noise
Jun Du | Peng Liu | Frank K. Soong | Jian-Lai Zhou | Ren-Hua Wang
International Journal of Computational Linguistics & Chinese Language Processing, Volume 12, Number 3, September 2007: Special Issue on Invited Papers from ISCSLP 2006


pdf bib
NLPR translation system for IWSLT 2006 evaluation campaign
Chunguang Chai | Jinhua Du | Wei Wei | Peng Liu | Keyan Zhou | Yanqing He | Chengqing Zong
Proceedings of the Third International Workshop on Spoken Language Translation: Evaluation Campaign