Fan Zhou


2023

pdf bib
Somali Information Retrieval Corpus: Bridging the Gap between Query Translation and Dedicated Language Resources
Abdisalam Badel | Ting Zhong | Wenxin Tai | Fan Zhou
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Despite the growing use of the Somali language in various online domains, research on Somali language information retrieval remains limited and primarily relies on query translation due to the lack of a dedicated corpus. To address this problem, we collaborated with language experts and natural language processing (NLP) researchers to create an annotated corpus for Somali information retrieval. This corpus comprises 2335 documents collected from various well-known online sites, such as hiiraan online, dhacdo net, and Somali poetry books. We explain how the corpus was constructed, and develop a Somali language information retrieval system using a pseudo-relevance feedback (PRF) query expansion technique on the corpus. Note that collecting such a data set for the low-resourced Somali language can help overcome NLP barriers, such as the lack of electronically available data sets. Which, if available, can enable the development of various NLP tools and applications such as question-answering and text classification. It also provides researchers with a valuable resource for investigating and developing new techniques and approaches for Somali.

pdf bib
Causal-Debias: Unifying Debiasing in Pretrained Language Models and Fine-tuning via Causal Invariant Learning
Fan Zhou | Yuzhou Mao | Liu Yu | Yi Yang | Ting Zhong
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Demographic biases and social stereotypes are common in pretrained language models (PLMs), and a burgeoning body of literature focuses on removing the unwanted stereotypical associations from PLMs. However, when fine-tuning these bias-mitigated PLMs in downstream natural language processing (NLP) applications, such as sentiment classification, the unwanted stereotypical associations resurface or even get amplified. Since pretrain&fine-tune is a major paradigm in NLP applications, separating the debiasing procedure of PLMs from fine-tuning would eventually harm the actual downstream utility. In this paper, we propose a unified debiasing framework Causal-Debias to remove unwanted stereotypical associations in PLMs during fine-tuning. Specifically, CausalDebias mitigates bias from a causal invariant perspective by leveraging the specific downstream task to identify bias-relevant and labelrelevant factors. We propose that bias-relevant factors are non-causal as they should have little impact on downstream tasks, while labelrelevant factors are causal. We perform interventions on non-causal factors in different demographic groups and design an invariant risk minimization loss to mitigate bias while maintaining task performance. Experimental results on three downstream tasks show that our proposed method can remarkably reduce unwanted stereotypical associations after PLMs are finetuned, while simultaneously minimizing the impact on PLMs and downstream applications.

2022

pdf bib
TaCube: Pre-computing Data Cubes for Answering Numerical-Reasoning Questions over Tabular Data
Fan Zhou | Mengkang Hu | Haoyu Dong | Zhoujun Cheng | Fan Cheng | Shi Han | Dongmei Zhang
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Existing auto-regressive pre-trained language models (PLMs) like T5 and BART, have been well applied to table question answering by UNIFIEDSKG and TAPEX, respectively, and demonstrated state-of-the-art results on multiple benchmarks. However, auto-regressive PLMs are challenged by recent emerging numerical reasoning datasets, such as TAT-QA, due to the error-prone implicit calculation. In this paper, we present TaCube, to pre-compute aggregation/arithmetic results for the table in advance, so that they are handy and readily available for PLMs to answer numerical reasoning questions. TaCube systematically and comprehensively covers a collection of computational operations over table segments. By simply concatenating TaCube to the input sequence of PLMs, it shows significant experimental effectiveness. TaCube promotes the F1 score from 49.6% to 66.2% on TAT-QA and achieves new state-of-the-art results on WikiTQ (59.6% denotation accuracy). TaCube’s improvements on numerical reasoning cases are even more notable: on TAT-QA, TaCube promotes the exact match accuracy of BART-large by 39.6% on sum, 52.5% on average, 36.6% on substraction, and 22.2% on division. We believe that TaCube is a general and portable pre-computation solution that can be potentially integrated to various numerical reasoning frameworks

2020

pdf bib
Interpretable Operational Risk Classification with Semi-Supervised Variational Autoencoder
Fan Zhou | Shengming Zhang | Yi Yang
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Operational risk management is one of the biggest challenges nowadays faced by financial institutions. There are several major challenges of building a text classification system for automatic operational risk prediction, including imbalanced labeled/unlabeled data and lacking interpretability. To tackle these challenges, we present a semi-supervised text classification framework that integrates multi-head attention mechanism with Semi-supervised variational inference for Operational Risk Classification (SemiORC). We empirically evaluate the framework on a real-world dataset. The results demonstrate that our method can better utilize unlabeled data and learn visually interpretable document representations. SemiORC also outperforms other baseline methods on operational risk classification.

pdf bib
Interpreting Twitter User Geolocation
Ting Zhong | Tianliang Wang | Fan Zhou | Goce Trajcevski | Kunpeng Zhang | Yi Yang
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Identifying user geolocation in online social networks is an essential task in many location-based applications. Existing methods rely on the similarity of text and network structure, however, they suffer from a lack of interpretability on the corresponding results, which is crucial for understanding model behavior. In this work, we adopt influence functions to interpret the behavior of GNN-based models by identifying the importance of training users when predicting the locations of the testing users. This methodology helps with providing meaningful explanations on prediction results. Furthermore, it also initiates an attempt to uncover the so-called “black-box” GNN-based models by investigating the effect of individual nodes.