Mingwen Dong, Nischal Ashok Kumar, Yiqun Hu, Anuj Chauhan, Chung-Wei Hang, Shuaichen Chang, Lin Pan, Wuwei Lan, Henghui Zhu, Jiarong Jiang, Patrick Ng, Zhiguo Wang. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Hideo Kobayashi, Wuwei Lan, Peng Shi, Shuaichen Chang, Jiang Guo, Henghui Zhu, Zhiguo Wang, Patrick Ng. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Wuwei Lan, Chao Jiang, Wei Xu. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

The success of a text simplification system heavily depends on the quality and quantity of complex-simple sentence pairs in the training corpus, which are extracted by aligning sentences between parallel articles.To evaluate and improve sentence alignment quality, we create two manually annotated sentence-aligned datasets from two commonly used text simplification corpora, Newsela and Wikipedia.We propose a novel neural CRF alignment model which not only leverages the sequential nature of sentences in parallel documents but also utilizes a neural sentence pair model to capture semantic similarity.Experiments demonstrate that our proposed approach outperforms all the previous work on monolingual sentence alignment task by more than 5 points in F1.We apply our CRF aligner to construct two new text simplification datasets, NEWSELA-AUTO and WIKI-AUTO, which are much larger and of better quality compared to the existing datasets.A Transformer-based seq2seq model trained on our datasets establishes a new state-of-the-art for text simplification in both automatic and human evaluation. 1

Multilingual pre-trained Transformers, such as mBERT (Devlin et al., 2019) and XLM-RoBERTa (Conneau et al., 2020a), have been shown to enable the effective cross-lingual zero-shot transfer.However, their performance on Arabic information extraction (IE) tasks is not very well studied.In this paper, we pre-train a customized bilingual BERT, dubbed GigaBERT, that is designed specifically for Arabic NLP and English-to-Arabic zero-shot transfer learning.We study Giga-BERT's effectiveness on zero-short transfer across four IE tasks: named entity recognition, part-of-speech tagging, argument role labeling, and relation extraction.Our best model significantly outperforms mBERT, XLM-RoBERTa, and AraBERT (Antoun et al., 2020) in both the supervised and zero-shot transfer settings.We have made our pre-trained models publicly available at https://github.com

Travel time estimation is a crucial task for not only personal travel scheduling but also city planning. Previous methods focus on modeling toward road segments or sub-paths, then summing up for a final prediction, which have been recently replaced by deep neural models with end-to-end training. Usually, these methods are based on explicit feature representations, including spatio-temporal features, traffic states, etc. Here, we argue that the local traffic condition is closely tied up with the land-use and built environment, i.e., metro stations, arterial roads, intersections, commercial area, residential area, and etc, yet the relation is time-varying and too complicated to model explicitly and efficiently. Thus, this paper proposes an end-to-end multi-task deep neural model, named Deep Image to Time (DeepI2T), to learn the travel time mainly from the built environment images, a.k.a. the morphological layout images, and showoff the new state-of-the-art performance on real-world datasets in two cities. Moreover, our model is designed to tackle both path-aware and path-blind scenarios in the testing phase. This work opens up new opportunities of using the publicly available morphological layout images as considerable information in multiple geography-related smart city applications.

In this paper, we analyze several neural network designs (and their variations) for sentence pair modeling and compare their performance extensively across eight datasets, including paraphrase identification, semantic textual similarity, natural language inference, and question answering tasks. Although most of these models have claimed state-of-the-art performance, the original papers often reported on only one or two selected datasets. We provide a systematic study and show that (i) encoding contextual information by LSTM and inter-sentence interactions are critical, (ii) Tree-LSTM does not help as much as previously claimed but surprisingly improves performance on Twitter datasets, (iii) the Enhanced Sequential Inference Model is the best so far for larger datasets, while the Pairwise Word Interaction Model achieves the best performance when less data is available. We release our implementations as an open-source toolkit.

A major challenge in paraphrase research is the lack of parallel corpora.In this paper, we present a new method to collect large-scale sentential paraphrases from Twitter by linking tweets through shared URLs.The main advantage of our method is its simplicity, as it gets rid of the classifier or human in the loop needed to select data before annotation and subsequent application of paraphrase identification algorithms in the previous work.We present the largest human-labeled paraphrase corpus to date of 51,524 sentence pairs and the first cross-domain benchmarking for automatic paraphrase identification.In addition, we show that more than 30,000 new sentential paraphrases can be easily and continuously captured every month at ∼70% precision, and demonstrate their utility for downstream NLP tasks through phrasal paraphrase extraction.We make our code and data freely available.1

TCP in cast congestion which can introduce hundreds of milliseconds delay and up to 90% throughput degradation, severely affecting application performance, has been a practical issue in high-bandwidth low-latency data enter networks. Despite continuous efforts, prior solutions have significant drawbacks. They either only support quite a limited number of senders (e.g., 40-60), which is not sufficient, or require non-trivial system modifications, which is impractical and not incrementally deployable. We present PAC, a simple yet very effective design to tame TCP in cast congestion via Proactive ACK Control at the receiver. The key design principle behind PAC is that we treat ACK not only as the acknowledgement of received packets but also as the trigger for new packets. Leveraging data center network characteristics, PAC enforces a novel ACK control to release ACKs in such a way that the ACK-triggered in-flight data can fully utilize the bottleneck link without causing in cast collapse even when faced with over a thousand senders. We implement PAC on both Windows and Linux platforms, and extensively evaluate PAC using small-scale test bed experiments and large-scale ns-2 simulations. Our results show that PAC significantly outperforms the previous representative designs such as ICTCP and DCTCP by supporting 40X (i.e., 40?1600) more senders, further, it does not introduce spurious timeout and retransmission even when the measured 99th percentile RTT is only 3.6ms. Our implementation experiences show that PAC is readily deployable in production data enters, while requiring minimal system modification compared to prior designs.

Facial expression recognition from thermal infrared images has attracted more and more attentions in recent years. However, the features adopted in current work are either temperature statistical parameters extracted from the facial regions of interest or several hand-crafted features that are commonly used in visible spectrum. Till now there is no image features specially defined for thermal infrared images. In this paper, we are the first to propose using the Deep Boltzmann Machine to learn thermal features for expression recognition from thermal long wavelength infrared images. First, the face are located and normalized from the thermal infrared images. Then, a Deep Boltzmann Machine model composed of two layers is proposed. The parameters of the Deep Boltzmann Machine model are further fine-tuned for facial expression recognition after pre-training of feature learning. Comparison experimental results on the NVIE database demonstrate that our approach outperforms other approaches using temperature statistic features or hand-crafted features borrowed from visible domain. The learned features from the forehead, mouth, and cheek are more reliable for discriminating disgust, fear, and happiness compared with other facial areas.