Long-form numerical reasoning aims to generate a reasoning program to calculate the answer for a given question. Previous work followed a retriever-generator framework, where the retriever selects key facts from a long-form document, and the generator generates a reasoning program based on the retrieved facts. However, they treated all facts equally without considering the different contributions of facts with and without numerical information. Furthermore, they ignored program consistency, leading to the wrong punishment of programs that differed from the ground truth. In order to address these issues, we proposed APOLLO (An optimized training aPproach fOr Long-form numericaL reasOning), to improve long-form numerical reasoning. APOLLO includes a number-aware negative sampling strategy for the retriever to discriminate key numerical facts, and a consistency-based reinforcement learning with target program augmentation for the generator to ultimately increase the execution accuracy. Experimental results on the FinQA and ConvFinQA leaderboards verify the effectiveness of our proposed methods, achieving the new state-of-the-art.

In recent years, multilingual pre-trained language models (mPLMs) have achieved significant progress in cross-lingual dense retrieval. However, most mPLMs neglect the importance of knowledge. Knowledge always conveys similar semantic concepts in a language-agnostic manner, while query-passage pairs in cross-lingual retrieval also share common factual information. Motivated by this observation, we introduce KEPT, a novel mPLM that effectively leverages knowledge to learn language-agnostic semantic representations. To achieve this, we construct a multilingual knowledge base using hyperlinks and cross-language page alignment data annotated by Wiki. From this knowledge base, we mine intra- and cross-language pairs by extracting symmetrically linked segments and multilingual entity descriptions. Subsequently, we adopt contrastive learning with the mined pairs to pre-train KEPT. We evaluate KEPT on three widely-used benchmarks, considering both zero-shot cross-lingual transfer and supervised multilingual fine-tuning scenarios. Extensive experimental results demonstrate that KEPT achieves strong multilingual and cross-lingual retrieval performance with significant improvements over existing mPLMs.

The dual-encoder has become the de facto architecture for dense retrieval.Typically, it computes the latent representations of the query and document independently, thus failing to fully capture the interactions between the query and document.To alleviate this, recent research has focused on obtaining query-informed document representations.During training, it expands the document with a real query, but during inference, it replaces the real query with a generated one.This inconsistency between training and inference causes the dense retrieval model to prioritize query information while disregarding the document when computing the document representation.Consequently, it performs even worse than the vanilla dense retrieval model because its performance heavily relies on the relevance between the generated queries and the real query.In this paper, we propose a curriculum sampling strategy that utilizes pseudo queries during training and progressively enhances the relevance between the generated query and the real query.By doing so, the retrieval model learns to extend its attention from the document alone to both the document and query, resulting in high-quality queryinformed document representations.Experimental results on both in-domain and out-ofdomain datasets demonstrate that our approach outperforms previous dense retrieval models.

Knowledge distillation is an effective way to transfer knowledge from a strong teacher to an efficient student model. Ideally, we expect the better the teacher is, the better the student performs. However, this expectation does not always come true. It is common that a strong teacher model results in a bad student via distillation due to the nonnegligible gap between teacher and student. To bridge the gap, we propose PROD, a PROgressive Distillation method, for dense retrieval. PROD consists of a teacher progressive distillation and a data progressive distillation to gradually improve the student. To alleviate catastrophic forgetting, we introduce a regularization term in each distillation process. We conduct extensive experiments on seven datasets including five widely-used publicly available benchmarks: MS MARCO Passage, TREC Passage 19, TREC Document 19, MS MARCO Document, and Natural Questions, as well as two industry datasets: Bing-Rel and Bing-Ads. PROD achieves the state-of-the-art in the distillation methods for dense retrieval. Our 6-layer student model even surpasses most of the existing 12-layer models on all five public benchmarks. The code and models are released in https://github.com/microsoft/SimXNS.

Xingwei He, Yeyun Gong, A-Long Jin, Weizhen Qi, Hang Zhang, Jian Jiao, Bartuer Zhou, Biao Cheng, Sm Yiu, Nan Duan. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. 2022.

Most existing pre-trained language representation models (PLMs) are sub-optimal in sentiment analysis tasks, as they capture the sentiment information from word-level while underconsidering sentence-level information.In this paper, we propose SentiWSP, a novel Sentiment-aware pre-trained language model with combined Word-level and Sentence-level Pre-training tasks.The word level pre-training task detects replaced sentiment words, via a generator-discriminator framework, to enhance the PLM's knowledge about sentiment words.The sentence level pre-training task further strengthens the discriminator via a contrastive learning framework, with similar sentences as negative samples, to encode sentiments in a sentence.Extensive experimental results show that SentiWSP achieves new state-of-the-art performance on various sentence-level and aspectlevel sentiment classification benchmarks.We have made our code and model publicly available at https://github.com/XMUDM/SentiWSP.

Xiaonan Li, Yeyun Gong, Yelong Shen, Xipeng Qiu, Hang Zhang, Bolun Yao, Weizhen Qi, Daxin Jiang, Weizhu Chen, Nan Duan. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. 2022.

In this paper, we introduce a two-level attention schema, Poolingformer, for long document modeling. Its first level uses a smaller sliding window pattern to aggregate information from neighbors. Its second level employs a larger window to increase receptive fields with pooling attention to reduce both computational cost and memory consumption. We first evaluate Poolingformer on two long sequence QA tasks: the monolingual NQ and the multilingual TyDi QA. Experimental results show that Poolingformer sits atop three official leaderboards measured by F1, outperforming previous state-of-the-art models by 1.9 points (79.8 vs. 77.9) on NQ long answer, 1.9 points (79.5 vs. 77.6) on TyDi QA passage answer, and 1.6 points (67.6 vs. 66.0) on TyDi QA minimal answer. We further evaluate Poolingformer on a long sequence summarization task. Experimental results on the arXiv benchmark continue to demonstrate its superior performance.

In January 2020, a COVID-19 outbreak was detected in Sichuan Province of China. Six weeks later, the outbreak was successfully contained. The aim of this work is to characterize the epidemiology of the Sichuan outbreak and estimate the impact of interventions in limiting SARS-CoV-2 transmission. We analyzed patient records for all laboratory-confirmed cases reported in the province for the period of January 21 to March 16, 2020. To estimate the basic and daily reproduction numbers, we used a Bayesian framework. In addition, we estimated the number of cases averted by the implemented control strategies. The outbreak resulted in 539 confirmed cases, lasted less than two months, and no further local transmission was detected after February 27. The median age of local cases was 8 years older than that of imported cases. We estimated R0 at 2.4 (95% CI: 1.6-3.7). The epidemic was self-sustained for about 3 weeks before going below the epidemic threshold 3 days after the declaration of a public health emergency by Sichuan authorities. Our findings indicate that, were the control measures be adopted four weeks later, the epidemic could have lasted 49 days longer (95% CI: 31-68 days), causing 9,216 more cases (95% CI: 1,317-25,545).