Boxing Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Boxing Chen has a total of 94 co-authors. Here are the top co-authors by number of shared publications:
- Weihua Luo
Alibaba International Digital Commerce Group, Hangzhou, China
5 shared publications - Baosong Yang
Tongyi Lab Group Alibaba
4 shared publications - Kai Fan
Alibaba Group Tongyi Lab
4 shared publications - Derek Fai Wong
University of Macau
3 shared publications Haibo Zhang
Alibaba Group Hangzhou China
3 shared publications- Liang Yao
Alibaba Group Hangzhou China
3 shared publications
Latest Publications
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 4361-4366
M-DaQ: Retrieving Samples with Multilingual Diversity and Quality for Instruction Fine-Tuning Datasets
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 4361-4366
Open AccessM-DaQ: Retrieving Samples with Multilingual Diversity and Quality for Instruction Fine-Tuning Datasets
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1135-1144
Adapting Large Language Models to Log Analysis with Interpretable Domain Knowledge
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1135-1144
Open AccessAdapting Large Language Models to Log Analysis with Interpretable Domain Knowledge
- Open Access
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 293-302
CIRAL: A Test Collection for CLIR Evaluations in African Languages
Cross-lingual information retrieval (CLIR) continues to be an actively studied topic in information retrieval (IR), and there have been consistent efforts in curating test collections to support its research. However, there is a lack of high-quality human-annotated CLIR resources for African languages: the few existing collections are mostly curated synthetically or from sources with limited corpora for these languages. We present CIRAL, a test collection for cross-lingual retrieval with English queries and passages in four African languages: Hausa, Somali, Swahili, and Yoruba. CIRAL's corpora are obtained from Indigenous African websites and consist of a total of over 2.5 million passages. We gathered over 1,600 queries and 30k high-quality binary relevance judgments annotated by native speakers of the languages. Additional pools were also obtained at CIRAL's shared task, which was hosted at the Forum for Information Retrieval Evaluation 2023 to encourage community participation in CLIR for African languages. We describe the design and curation process of our test collection and provide reproducible baselines that demonstrate CIRAL's utility in evaluating the effectiveness of systems. CIRAL is available at https://github.com/ciralproject/ciral.
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 293-302
Open AccessCIRAL: A Test Collection for CLIR Evaluations in African Languages
Cross-lingual information retrieval (CLIR) continues to be an actively studied topic in information retrieval (IR), and there have been consistent efforts in curating test collections to support its research. However, there is a lack of high-quality human-annotated CLIR resources for African languages: the few existing collections are mostly curated synthetically or from sources with limited corpora for these languages. We present CIRAL, a test collection for cross-lingual retrieval with English queries and passages in four African languages: Hausa, Somali, Swahili, and Yoruba. CIRAL's corpora are obtained from Indigenous African websites and consist of a total of over 2.5 million passages. We gathered over 1,600 queries and 30k high-quality binary relevance judgments annotated by native speakers of the languages. Additional pools were also obtained at CIRAL's shared task, which was hosted at the Forum for Information Retrieval Evaluation 2023 to encourage community participation in CLIR for African languages. We describe the design and curation process of our test collection and provide reproducible baselines that demonstrate CIRAL's utility in evaluating the effectiveness of systems. CIRAL is available at https://github.com/ciralproject/ciral.
- Open Access
- 15 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 4-6
CIRAL at FIRE 2023: Cross-Lingual Information Retrieval for African Languages
This paper provides a short overview of the CIRAL track at the Forum for Information Retrieval Evaluation (FIRE) 2023. CIRAL focused on cross-lingual information retrieval (CLIR) between English and four African languages which include Hausa, Somali, Swahili, and Yoruba. In a bid to promote CLIR research for African languages and curate a test collection for the languages, community evaluations were carried out via pooling. We briefly discuss details of the task, dataset, relevance assessment and results from the track in this paper.
- 15 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 4-6
Open AccessCIRAL at FIRE 2023: Cross-Lingual Information Retrieval for African Languages
This paper provides a short overview of the CIRAL track at the Forum for Information Retrieval Evaluation (FIRE) 2023. CIRAL focused on cross-lingual information retrieval (CLIR) between English and four African languages which include Hausa, Somali, Swahili, and Yoruba. In a bid to promote CLIR research for African languages and curate a test collection for the languages, community evaluations were carried out via pooling. We briefly discuss details of the task, dataset, relevance assessment and results from the track in this paper.
- Open Access
Adapting Offline Speech Translation Models for Streaming with Future-Aware Distillation and Inference
A popular approach to streaming speech translation is to employ a single offline model with a wait-k policy to support different latency requirements, which is simpler than training multiple online models with different latency constraints. However, there is a mismatch problem in using a model trained with complete utterances for streaming inference with partial input. We demonstrate that speech representations extracted at the end of a streaming input are significantly different from those extracted from a complete utterance. To address this issue, we propose a new approach called Future-Aware Streaming Translation (FAST) that adapts an offline ST model for streaming input. FAST includes a Future-Aware Inference (FAI) strategy that incorporates future context through a trainable masked embedding, and a Future-Aware Distillation (FAD) framework that transfers future context from an approximation of full speech to streaming input. Our experiments on the MuST-C EnDe, EnEs, and EnFr benchmarks show that FAST achieves better trade-offs between translation quality and latency than strong baselines. Extensive analyses suggest that our methods effectively alleviate the aforementioned mismatch problem between offline training and online inference.
Open AccessAdapting Offline Speech Translation Models for Streaming with Future-Aware Distillation and Inference
A popular approach to streaming speech translation is to employ a single offline model with a wait-k policy to support different latency requirements, which is simpler than training multiple online models with different latency constraints. However, there is a mismatch problem in using a model trained with complete utterances for streaming inference with partial input. We demonstrate that speech representations extracted at the end of a streaming input are significantly different from those extracted from a complete utterance. To address this issue, we propose a new approach called Future-Aware Streaming Translation (FAST) that adapts an offline ST model for streaming input. FAST includes a Future-Aware Inference (FAI) strategy that incorporates future context through a trainable masked embedding, and a Future-Aware Distillation (FAD) framework that transfers future context from an approximation of full speech to streaming input. Our experiments on the MuST-C EnDe, EnEs, and EnFr benchmarks show that FAST achieves better trade-offs between translation quality and latency than strong baselines. Extensive analyses suggest that our methods effectively alleviate the aforementioned mismatch problem between offline training and online inference.
- Open Access
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 16600-16619
Adapting Offline Speech Translation Models for Streaming with Future-Aware Distillation and Inference
Biao Fu, Minpeng Liao, Kai Fan, Zhongqiang Huang, Boxing Chen, Yidong Chen, Xiaodong Shi. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 16600-16619
Open AccessAdapting Offline Speech Translation Models for Streaming with Future-Aware Distillation and Inference
Biao Fu, Minpeng Liao, Kai Fan, Zhongqiang Huang, Boxing Chen, Yidong Chen, Xiaodong Shi. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.
- Open Access
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 410-427
Tailor: A Soft-Prompt-Based Approach to Attribute-Based Controlled Text Generation
Kexin Yang, Dayiheng Liu, Wenqiang Lei, Baosong Yang, Mingfeng Xue, Boxing Chen, Jun Xie. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 410-427
Open AccessTailor: A Soft-Prompt-Based Approach to Attribute-Based Controlled Text Generation
Kexin Yang, Dayiheng Liu, Wenqiang Lei, Baosong Yang, Mingfeng Xue, Boxing Chen, Jun Xie. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.
- 10 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 31 (23299290) , 439-447
Towards Energy-Preserving Natural Language Understanding With Spiking Neural Networks
Artificial neural networks have shown promising results in a variety of natural language understanding (NLU) tasks. Despite their successes, conventional neural-based NLU models are criticized for high energy consumption, making them laborious to be widely applied in low-power electronics, such as smartphones and intelligent terminals. In this paper, we introduce a potential direction to alleviate this bottleneck by proposing a spiking encoder. The core of our model is bi-directional spiking neural network (SNN) which transforms numeric values into discrete spiking signals and replaces massive multiplications with much cheaper additive operations. We examine our model on sentiment classification and machine translation tasks. Experimental results reveal that our model achieves comparable classification and translation accuracy to advanced Transformer baseline, whereas significantly reduces the required computational energy to 0.82%.
- 10 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 31 (23299290) , 439-447
Towards Energy-Preserving Natural Language Understanding With Spiking Neural Networks
Artificial neural networks have shown promising results in a variety of natural language understanding (NLU) tasks. Despite their successes, conventional neural-based NLU models are criticized for high energy consumption, making them laborious to be widely applied in low-power electronics, such as smartphones and intelligent terminals. In this paper, we introduce a potential direction to alleviate this bottleneck by proposing a spiking encoder. The core of our model is bi-directional spiking neural network (SNN) which transforms numeric values into discrete spiking signals and replaces massive multiplications with much cheaper additive operations. We examine our model on sentiment classification and machine translation tasks. Experimental results reveal that our model achieves comparable classification and translation accuracy to advanced Transformer baseline, whereas significantly reduces the required computational energy to 0.82%.
- Open Access
- 9 June 2022
- Published by MIT Press in Computational Linguistics
- Vol. 48 (2) , 321-342
Challenges of Neural Machine Translation for Short Texts
Short texts (STs) present in a variety of scenarios, including query, dialog, and entity names. Most of the exciting studies in neural machine translation (NMT) are focused on tackling open problems concerning long sentences rather than short ones. The intuition behind is that, with respect to human learning and processing, short sequences are generally regarded as easy examples. In this article, we first dispel this speculation via conducting preliminary experiments, showing that the conventional state-of-the-art NMT approach, namely, Transformer (Vaswani et al. 2017), still suffers from over-translation and mistranslation errors over STs. After empirically investigating the rationale behind this, we summarize two challenges in NMT for STs associated with translation error types above, respectively: (1) the imbalanced length distribution in training set intensifies model inference calibration over STs, leading to more over-translation cases on STs; and (2) the lack of contextual information forces NMT to have higher data uncertainty on short sentences, and thus NMT model is troubled by considerable mistranslation errors. Some existing approaches, like balancing data distribution for training (e.g., data upsampling) and complementing contextual information (e.g., introducing translation memory) can alleviate the translation issues in NMT for STs. We encourage researchers to investigate other challenges in NMT for STs, thus reducing ST translation errors and enhancing translation quality.
- 9 June 2022
- Published by MIT Press in Computational Linguistics
- Vol. 48 (2) , 321-342
Open AccessChallenges of Neural Machine Translation for Short Texts
Short texts (STs) present in a variety of scenarios, including query, dialog, and entity names. Most of the exciting studies in neural machine translation (NMT) are focused on tackling open problems concerning long sentences rather than short ones. The intuition behind is that, with respect to human learning and processing, short sequences are generally regarded as easy examples. In this article, we first dispel this speculation via conducting preliminary experiments, showing that the conventional state-of-the-art NMT approach, namely, Transformer (Vaswani et al. 2017), still suffers from over-translation and mistranslation errors over STs. After empirically investigating the rationale behind this, we summarize two challenges in NMT for STs associated with translation error types above, respectively: (1) the imbalanced length distribution in training set intensifies model inference calibration over STs, leading to more over-translation cases on STs; and (2) the lack of contextual information forces NMT to have higher data uncertainty on short sentences, and thus NMT model is troubled by considerable mistranslation errors. Some existing approaches, like balancing data distribution for training (e.g., data upsampling) and complementing contextual information (e.g., introducing translation memory) can alleviate the translation issues in NMT for STs. We encourage researchers to investigate other challenges in NMT for STs, thus reducing ST translation errors and enhancing translation quality.
- Open Access
Non-Parametric Unsupervised Domain Adaptation for Neural Machine Translation
Recently, $k$NN-MT has shown the promising capability of directly incorporating the pre-trained neural machine translation (NMT) model with domain-specific token-level $k$-nearest-neighbor ($k$NN) retrieval to achieve domain adaptation without retraining. Despite being conceptually attractive, it heavily relies on high-quality in-domain parallel corpora, limiting its capability on unsupervised domain adaptation, where in-domain parallel corpora are scarce or nonexistent. In this paper, we propose a novel framework that directly uses in-domain monolingual sentences in the target language to construct an effective datastore for $k$-nearest-neighbor retrieval. To this end, we first introduce an autoencoder task based on the target language, and then insert lightweight adapters into the original NMT model to map the token-level representation of this task to the ideal representation of translation task. Experiments on multi-domain datasets demonstrate that our proposed approach significantly improves the translation accuracy with target-side monolingual data, while achieving comparable performance with back-translation.
Open AccessNon-Parametric Unsupervised Domain Adaptation for Neural Machine Translation
Recently, $k$NN-MT has shown the promising capability of directly incorporating the pre-trained neural machine translation (NMT) model with domain-specific token-level $k$-nearest-neighbor ($k$NN) retrieval to achieve domain adaptation without retraining. Despite being conceptually attractive, it heavily relies on high-quality in-domain parallel corpora, limiting its capability on unsupervised domain adaptation, where in-domain parallel corpora are scarce or nonexistent. In this paper, we propose a novel framework that directly uses in-domain monolingual sentences in the target language to construct an effective datastore for $k$-nearest-neighbor retrieval. To this end, we first introduce an autoencoder task based on the target language, and then insert lightweight adapters into the original NMT model to map the token-level representation of this task to the ideal representation of translation task. Experiments on multi-domain datasets demonstrate that our proposed approach significantly improves the translation accuracy with target-side monolingual data, while achieving comparable performance with back-translation.