---
title: "Target-oriented Opinion Words Extraction with Target-fused"
description: "The paper presents TOWE (Target-oriented Opinion Words Extraction), a new subtask of Aspect… 24 references, cited by 69 papers here."
authors: ["Zhifang Fan", "Zhen Wu", "Xin-Yu Dai", "Shujian Huang", "Jiajun Chen"]
year: 2019
venue: "Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)"
source: "https://aclanthology.org/N19-1259/"
doi: "10.18653/v1/n19-1259"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/fan-2019-target-oriented-opinion-words-extraction/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/fan-2019-target-oriented-opinion-words-extraction/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2019](https://md.research.elamur.ai/free/en/papers/2019/page/3/) / Target-oriented Opinion Words Extraction with Target-fused Neural Sequence Labeling

# Target-oriented Opinion Words Extraction with Target-fused Neural Sequence Labeling

**Authors:** Zhifang Fan, Zhen Wu, [Xin-Yu Dai](https://md.research.elamur.ai/free/en/authors/xin-yu-dai/), [Shujian Huang](https://md.research.elamur.ai/free/en/authors/shujian-huang/) and [Jiajun Chen](https://md.research.elamur.ai/free/en/authors/jiajun-chen/) · **Year:** 2019 · **Venue:** [Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)](https://md.research.elamur.ai/free/en/venues/naacl/) ([NAACL 2019](https://md.research.elamur.ai/free/en/venues/naacl/2019/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/N19-1259/) · [PDF](https://aclanthology.org/N19-1259.pdf) · [DOI 10.18653/v1/n19-1259](https://doi.org/10.18653/v1/n19-1259) · [OpenAlex](https://openalex.org/W2946015932)

**Citations:** 220 citations (OpenAlex, 2026-10-14) · [69](https://md.research.elamur.ai/free/en/papers/fan-2019-target-oriented-opinion-words-extraction/cited-by/) in our library, of the 141,840 papers whose bibliographies we read

## Summary
The paper presents TOWE (Target-oriented Opinion Words Extraction), a new subtask of Aspect Based Sentiment Analysis (ABSA). Earlier work extracted opinion targets and opinion words separately, so it lost the link between them. TOWE takes a review sentence and one target term and labels the words that express opinions about that target, using the BIO scheme. This captures multi-word expressions and targets that carry several opinions.

The authors propose IOG, a neural sequence labeling model with a target-fused encoder. An Inward-LSTM carries context toward the target. An Outward-LSTM carries target information out into the left and right context. A global BiLSTM context is combined with both before decoding, using either a greedy or a CRF decoder.

The authors built four benchmark datasets from existing laptop and restaurant ABSA corpora. IOG beat rule-based baselines (distance and dependency rules), a pipeline, BiLSTM and TC-BiLSTM on every dataset. The work matters because it yields explicit target–opinion pairs, which can support downstream sentiment classification and pair-wise extractive opinion summarization.

## Key points
- TOWE is framed as BIO sequence labeling conditioned on a given target. The same sentence therefore gets different labels for different targets.
- In the ablation study, Outward-LSTM scored more than 10% higher in F1 than Inward-LSTM. Inward-LSTM alone performed about as poorly as a target-independent BiLSTM.
- Adding Inward-LSTM to Outward-LSTM (IO-LSTM) helped slightly. Adding global context (IOG) gave a further gain of roughly 1%, and a CRF decoder improved results a little more.
- Simply concatenating the target into the input (TC-BiLSTM) scored about 10% below IOG, apparently because other targets in the sentence interfere.
- The four datasets and the source code are released at github.com/NJUNLP/TOWE.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 9,085 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 8,888 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 9,296 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 9,206 works

## Cite

Cite as: Zhifang Fan, Zhen Wu, Xin-Yu Dai, Shujian Huang and Jiajun Chen. 2019. Target-oriented Opinion Words Extraction with Target-fused Neural Sequence Labeling. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{fan2019target,
  title = {{Target-oriented Opinion Words Extraction with Target-fused Neural Sequence Labeling}},
  author = {Zhifang Fan, Zhen Wu, Xin-Yu Dai, Shujian Huang and Jiajun Chen},
  booktitle = {Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)},
  year = {2019},
  doi = {10.18653/v1/n19-1259},
  url = {https://doi.org/10.18653/v1/n19-1259}
}
```

- [← previous SemEval-2019 Task 7: RumourEval, Determining Rumour Veracity and Support for Rumours](https://md.research.elamur.ai/free/en/papers/gorrell-2019-semeval-2019-task-7-rumoureval/)
- [next → GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verification](https://md.research.elamur.ai/free/en/papers/zhou-2019-gear-graph-based-evidence-aggregating/)
- [↑ back to papers of 2019](https://md.research.elamur.ai/free/en/papers/2019/page/3/)

## References

24 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural Computation, 9:1735– 1780. [find](https://scholar.google.com/scholar?q=Sepp+Hochreiter+and+Ju%CC%88rgen+Schmidhuber%2E+1997%2E+Long+short%2Dterm+memory%2E+Neural+Computation%2C+9%3A1735%E2%80%93+1780%2E)
2. Minqing Hu and Bing Liu. 2004. Mining and summarizing customer reviews. In Proceedings of the 10th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 168–177. [find](https://scholar.google.com/scholar?q=Minqing+Hu+and+Bing+Liu%2E+2004%2E+Mining+and+summarizing+customer+reviews%2E+In+Proceedings+of+the+10th+ACM+SIGKDD+International+Conference+on+Knowledge+Discovery+and+Data+Mining%2C+pages+168%E2%80%93177%2E)
3. Niklas Jakob and Iryna Gurevych. 2010. [Extracting opinion targets in a single and cross-domain setting with conditional random fields](https://md.research.elamur.ai/free/en/papers/jakob-2010-extracting-opinion-targets-single-cross/). In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, pages 1035–1045.
4. Diederik P. Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In Proceedings of the 3rd International Conference for Learning Representations. [find](https://scholar.google.com/scholar?q=Diederik+P%2E+Kingma+and+Jimmy+Ba%2E+2015%2E+Adam%3A+A+method+for+stochastic+optimization%2E+In+Proceedings+of+the+3rd+International+Conference+for+Learning+Representations%2E)
5. John D. Lafferty, Andrew McCallum, and Fernando C. N. Pereira. 2001. Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In Proceedings of the 18th International Conference on Machine Learning, pages 282– 289. [find](https://scholar.google.com/scholar?q=John+D%2E+Lafferty%2C+Andrew+McCallum%2C+and+Fernando+C%2E+N%2E+Pereira%2E+2001%2E+Conditional+random+fields%3A+Probabilistic+models+for+segmenting+and+labeling+sequence+data%2E+In+Proceedings+of+the+18th+International)
6. Xin Li and Wai Lam. 2017. Deep multi-task learning for aspect term extraction with memory interaction. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2886–2892. [find](https://scholar.google.com/scholar?q=Xin+Li+and+Wai+Lam%2E+2017%2E+Deep+multi%2Dtask+learning+for+aspect+term+extraction+with+memory+interaction%2E+In+Proceedings+of+the+2017+Conference+on+Empirical+Methods+in+Natural+Language+Processing%2C+pages+)
7. Bing Liu. 2012. Sentiment Analysis and Opinion Mining. Synthesis Lectures on Human Language Technologies. Morgan & Claypool Publishers. [find](https://scholar.google.com/scholar?q=Bing+Liu%2E+2012%2E+Sentiment+Analysis+and+Opinion+Mining%2E+Synthesis+Lectures+on+Human+Language+Technologies%2E+Morgan+%26+Claypool+Publishers%2E)
8. Kang Liu, Heng Li Xu, Yang Liu, and Jun Zhao. 2013. Opinion target extraction using partially-supervised word alignment model. In Proceedings of the 23rd International Joint Conference on Artificial Intelligence, pages 2134–2140. [find](https://scholar.google.com/scholar?q=Kang+Liu%2C+Heng+Li+Xu%2C+Yang+Liu%2C+and+Jun+Zhao%2E+2013%2E+Opinion+target+extraction+using+partially%2Dsupervised+word+alignment+model%2E+In+Proceedings+of+the+23rd+International+Joint+Conference+on+Artificial+I)
9. Pengfei Liu, Shafiq R. Joty, and Helen M. Meng. 2015. [Fine-grained opinion mining with recurrent neural networks and word embeddings](https://md.research.elamur.ai/free/en/papers/liu-2015-fine-grained-opinion-mining-recurrent/). In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 1433–1443.
10. Bo Pang and Lillian Lee. 2007. Opinion mining and sentiment analysis. Foundations and Trends in Information Retrieval, 2(1-2):1–135. [find](https://scholar.google.com/scholar?q=Bo+Pang+and+Lillian+Lee%2E+2007%2E+Opinion+mining+and+sentiment+analysis%2E+Foundations+and+Trends+in+Information+Retrieval%2C+2%281%2D2%29%3A1%E2%80%93135%2E)
11. Jeffrey Pennington, Richard Socher, and Christopher D. Manning. 2014. [Glove: Global vectors for word representation](https://md.research.elamur.ai/free/en/papers/pennington-2014-glove-global-vectors-word-representation/). In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, pages 1532–1543.
12. Maria Pontiki, Dimitris Galanis, Haris Papageorgiou, Ion Androutsopoulos, Suresh Manandhar, Mohammad Al-Smadi, Mahmoud Al-Ayyoub, Yanyan Zhao, Bing Qin, Orphée De Clercq, Véronique Hoste, Marianna Apidianaki, Xavier Tannier, Natalia V. Loukachevitch, Evgeniy Kotelnikov, Núria Bel, Salud Marı́a Ji… — [SemEval-2016 Task 5: Aspect Based Sentiment Analysis](https://md.research.elamur.ai/free/en/papers/pontiki-2016-semeval-2016-task-5-aspect/)
13. Maria Pontiki, Dimitris Galanis, Haris Papageorgiou, Suresh Manandhar, and Ion Androutsopoulos. 2015. [Semeval-2015 task 12: Aspect based sentiment analysis](https://md.research.elamur.ai/free/en/papers/pontiki-2015-semeval-2015-task-12-aspect/). In Proceedings of the 9th International Workshop on Semantic Evaluation, pages 486–495.
14. Maria Pontiki, Dimitris Galanis, John Pavlopoulos, Harris Papageorgiou, Ion Androutsopoulos, and Suresh Manandhar. 2014. [Semeval-2014 task 4: Aspect based sentiment analysis](https://md.research.elamur.ai/free/en/papers/pontiki-2014-semeval-2014-task-4-aspect/). In Proceedings of the 8th International Workshop on Semantic Evaluation, pages 27–35.
15. Soujanya Poria, Erik Cambria, and Alexander F. Gelbukh. 2016. Aspect extraction for opinion mining with a deep convolutional neural network. Knowledge-Based Systems, 108:42–49. [find](https://scholar.google.com/scholar?q=Soujanya+Poria%2C+Erik+Cambria%2C+and+Alexander+F%2E+Gelbukh%2E+2016%2E+Aspect+extraction+for+opinion+mining+with+a+deep+convolutional+neural+network%2E+Knowledge%2DBased+Systems%2C+108%3A42%E2%80%9349%2E)
16. Guang Qiu, Bing Liu, Jiajun Bu, and Chun Chen. 2011. [Opinion word expansion and target extraction through double propagation](https://md.research.elamur.ai/free/en/papers/qiu-2011-opinion-word-expansion-target-extraction/). Computational Linguistics, 37(1):9–27.
17. Lance Ramshaw and Mitch Marcus. 1995. [Text chunking using transformation-based learning](https://md.research.elamur.ai/free/en/papers/ramshaw-1995-text-chunking-transformation-based-learning/). In Third Workshop on Very Large Corpora.
18. Lei Shu, Hu Xu, and Bing Liu. 2017. Lifelong learning CRF for supervised aspect extraction. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, pages 148–154. [find](https://scholar.google.com/scholar?q=Lei+Shu%2C+Hu+Xu%2C+and+Bing+Liu%2E+2017%2E+Lifelong+learning+CRF+for+supervised+aspect+extraction%2E+In+Proceedings+of+the+55th+Annual+Meeting+of+the+Association+for+Computational+Linguistics%2C+pages+148%E2%80%93154%2E)
19. Duyu Tang, Bing Qin, Xiaocheng Feng, and Ting Liu. 2016. [Effective lstms for target-dependent sentiment classification](https://md.research.elamur.ai/free/en/papers/tang-2016-effective-lstms-target-dependent-sentiment/). In Proceedings of the 26th International Conference on Computational Linguistics: Technical Papers, pages 3298–3307.
20. Wenya Wang, Sinno Jialin Pan, Daniel Dahlmeier, and Xiaokui Xiao. 2016. [Recursive neural conditional random fields for aspect-based sentiment analysis](https://md.research.elamur.ai/free/en/papers/wang-2016-recursive-neural-conditional-random-fields/). In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 616–626.
21. Wenya Wang, Sinno Jialin Pan, Daniel Dahlmeier, and Xiaokui Xiao. 2017. Coupled multi-layer attentions for co-extraction of aspect and opinion terms. In Proceedings of the 31st AAAI Conference on Artificial Intelligence, pages 3316–3322. [find](https://scholar.google.com/scholar?q=Wenya+Wang%2C+Sinno+Jialin+Pan%2C+Daniel+Dahlmeier%2C+and+Xiaokui+Xiao%2E+2017%2E+Coupled+multi%2Dlayer+attentions+for+co%2Dextraction+of+aspect+and+opinion+terms%2E+In+Proceedings+of+the+31st+AAAI+Conference+on+Arti)
22. Hu Xu, Bing Liu, Lei Shu, and Philip S. Yu. 2018. [Double embeddings and cnn-based sequence labeling for aspect extraction](https://md.research.elamur.ai/free/en/papers/xu-2018-double-embeddings-cnn-based-sequence/). In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, pages 592–598.
23. Yichun Yin, Furu Wei, Li Dong, Kaimeng Xu, Ming Zhang, and Ming Zhou. 2016. Unsupervised word and dependency path embeddings for aspect term extraction. In Proceedings of the 25th International Joint Conference on Artificial Intelligence, pages 2979–2985. [find](https://scholar.google.com/scholar?q=Yichun+Yin%2C+Furu+Wei%2C+Li+Dong%2C+Kaimeng+Xu%2C+Ming+Zhang%2C+and+Ming+Zhou%2E+2016%2E+Unsupervised+word+and+dependency+path+embeddings+for+aspect+term+extraction%2E+In+Proceedings+of+the+25th+International+Joint+)
24. Li Zhuang, Feng Jing, and Xiaoyan Zhu. 2006. Movie review mining and summarization. In Proceedings of the 15th ACM International Conference on Information and Knowledge Management, pages 43–50. [find](https://scholar.google.com/scholar?q=Li+Zhuang%2C+Feng+Jing%2C+and+Xiaoyan+Zhu%2E+2006%2E+Movie+review+mining+and+summarization%2E+In+Proceedings+of+the+15th+ACM+International+Conference+on+Information+and+Knowledge+Management%2C+pages+43%E2%80%9350%2E)

*Updated 24 October 2026*