Zhe Zhang


pdf bib
MTL-SLT: Multi-Task Learning for Spoken Language Tasks
Zhiqi Huang | Milind Rao | Anirudh Raju | Zhe Zhang | Bach Bui | Chul Lee
Proceedings of the 4th Workshop on NLP for Conversational AI

Language understanding in speech-based systems has attracted extensive interest from both academic and industrial communities in recent years with the growing demand for voice-based applications. Prior works focus on independent research by the automatic speech recognition (ASR) and natural language processing (NLP) communities, or on jointly modeling the speech and NLP problems focusing on a single dataset or single NLP task. To facilitate the development of spoken language research, we introduce MTL-SLT, a multi-task learning framework for spoken language tasks. MTL-SLT takes speech as input, and outputs transcription, intent, named entities, summaries, and answers to text queries, supporting the tasks of spoken language understanding, spoken summarization and spoken question answering respectively. The proposed framework benefits from three key aspects: 1) pre-trained sub-networks of ASR model and language model; 2) multi-task learning objective to exploit shared knowledge from different tasks; 3) end-to-end training of ASR and downstream NLP task based on sequence loss. We obtain state-of-the-art results on spoken language understanding tasks such as SLURP and ATIS. Spoken summarization results are reported on a new dataset: Spoken-Gigaword.


pdf bib
Octa: Omissions and Conflicts in Target-Aspect Sentiment Analysis
Zhe Zhang | Chung-Wei Hang | Munindar Singh
Findings of the Association for Computational Linguistics: EMNLP 2020

Sentiments in opinionated text are often determined by both aspects and target words (or targets). We observe that targets and aspects interrelate in subtle ways, often yielding conflicting sentiments. Thus, a naive aggregation of sentiments from aspects and targets treated separately, as in existing sentiment analysis models, impairs performance. We propose Octa, an approach that jointly considers aspects and targets when inferring sentiments. To capture and quantify relationships between targets and context words, Octa uses a selective self-attention mechanism that handles implicit or missing targets. Specifically, Octa involves two layers of attention mechanisms for, respectively, selective attention between targets and context words and attention over words based on aspects. On benchmark datasets, Octa outperforms leading models by a large margin, yielding (absolute) gains in accuracy of 1.6% to 4.3%.


pdf bib
Leveraging Structural and Semantic Correspondence for Attribute-Oriented Aspect Sentiment Discovery
Zhe Zhang | Munindar Singh
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Opinionated text often involves attributes such as authorship and location that influence the sentiments expressed for different aspects. We posit that structural and semantic correspondence is both prevalent in opinionated text, especially when associated with attributes, and crucial in accurately revealing its latent aspect and sentiment structure. However, it is not recognized by existing approaches. We propose Trait, an unsupervised probabilistic model that discovers aspects and sentiments from text and associates them with different attributes. To this end, Trait infers and leverages structural and semantic correspondence using a Markov Random Field. We show empirically that by incorporating attributes explicitly Trait significantly outperforms state-of-the-art baselines both by generating attribute profiles that accord with our intuitions, as shown via visualization, and yielding topics of greater semantic cohesion.


pdf bib
Limbic: Author-Based Sentiment Aspect Modeling Regularized with Word Embeddings and Discourse Relations
Zhe Zhang | Munindar Singh
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

We propose Limbic, an unsupervised probabilistic model that addresses the problem of discovering aspects and sentiments and associating them with authors of opinionated texts. Limbic combines three ideas, incorporating authors, discourse relations, and word embeddings. For discourse relations, Limbic adopts a generative process regularized by a Markov Random Field. To promote words with high semantic similarity into the same topic, Limbic captures semantic regularities from word embeddings via a generalized Pólya Urn process. We demonstrate that Limbic (1) discovers aspects associated with sentiments with high lexical diversity; (2) outperforms state-of-the-art models by a substantial margin in topic cohesion and sentiment classification.


pdf bib
ReNew: A Semi-Supervised Framework for Generating Domain-Specific Lexicons and Sentiment Analysis
Zhe Zhang | Munindar P. Singh
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)