arXiv subjects

Donghong Ji

Publications and source records attributed to Donghong Ji.

59 records · Page 4Linked to original sources

arXiv2020

Multi-Task Learning with Auxiliary Speaker Identification for Conversational Emotion Recognition

Conversational emotion recognition (CER) has attracted increasing interests in the natural language processing (NLP) community. Different from the vanilla emotion recognition, effective speaker-sensitive utterance representation is one major challenge for CER. In this paper, we exploit speaker identification (SI) as an auxiliary task to enhance the utterance representation in conversations. By this method, we can learn better speaker-aware contextual representations from the additional SI corpus. Experiments on two benchmark datasets demonstrate that the proposed architecture is highly effective for CER, obtaining new state-of-the-art results on two datasets.

cs.CL↗

arXiv2019

DLocRL: A Deep Learning Pipeline for Fine-Grained Location Recognition and Linking in Tweets

In recent years, with the prevalence of social media and smart devices, people causally reveal their locations such as shops, hotels, and restaurants in their tweets. Recognizing and linking such fine-grained location mentions to well-defined location profiles are beneficial for retrieval and recommendation systems. In this paper, we propose DLocRL, a new deep learning pipeline for fine-grained location recognition and linking in tweets, and verify its effectiveness on a real-world Twitter dataset.

cs.CL↗

arXiv2018

Discovering Key Nodes in a Temporal Social Network

[Background]Discovering key nodes plays a significant role in Social Network Analysis(SNA). Effective and accurate mining of key nodes promotes more successful applications in fields like advertisement and recommendation. [Methods] With focus on the temporal and categorical property of users' actions - when did they re-tweet or reply a message, as well as their social intimacy measured by structural embeddings, we designed a more sensitive PageRank-like algorithm to accommodate the growing and changing social network in the pursue of mining key nodes. [Results] Compared with our baseline PageRank algorithm, key nodes selected by our ranking algorithm noticeably perform better in the SIR disease simulations with SNAP Higgs dataset. [Conclusion] These results contributed to a better understanding of disseminations of social events over the network.

cs.SI↗

arXiv2016

Distance Metric Learning for Aspect Phrase Grouping

Aspect phrase grouping is an important task in aspect-level sentiment analysis. It is a challenging problem due to polysemy and context dependency. We propose an Attention-based Deep Distance Metric Learning (ADDML) method, by considering aspect phrase representation as well as context representation. First, leveraging the characteristics of the review text, we automatically generate aspect phrase sample pairs for distant supervision. Second, we feed word embeddings of aspect phrases and their contexts into an attention-based neural network to learn feature representation of contexts. Both aspect phrase embedding and context embedding are used to learn a deep feature subspace for measure the distances between aspect phrases for K-means clustering. Experiments on four review datasets show that the proposed method outperforms state-of-the-art strong baseline methods.

cs.CL↗

arXiv2016

A Bi-LSTM-RNN Model for Relation Classification Using Low-Cost Sequence Features

Relation classification is associated with many potential applications in the artificial intelligence area. Recent approaches usually leverage neural networks based on structure features such as syntactic or dependency features to solve this problem. However, high-cost structure features make such approaches inconvenient to be directly used. In addition, structure features are probably domain-dependent. Therefore, this paper proposes a bi-directional long-short-term-memory recurrent-neural-network (Bi-LSTM-RNN) model based on low-cost sequence features to address relation classification. This model divides a sentence or text segment into five parts, namely two target entities and their three contexts. It learns the representations of entities and their contexts, and uses them to classify relations. We evaluate our model on two standard benchmark datasets in different domains, namely SemEval-2010 Task 8 and BioNLP-ST 2016 Task BB3. In the former dataset, our model achieves comparable performance compared with other models using sequence features. In the latter dataset, our model obtains the third best results compared with other models in the official evaluation. Moreover, we find that the context between two target entities plays the most important role in relation classification. Furthermore, statistic experiments show that the context between two target entities can be used as an approximate replacement of the shortest dependency path when dependency parsing is not used.

cs.CL↗