arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2109.02789cs.IRcs.CL
收藏

利用词级知识进行跨语言信息检索的混合注意力Transformer

Mixed Attention Transformer for Leveraging Word-Level Knowledge to Neural Cross-Lingual Information Retrieval

University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校)

Zhiqi Huang, Hamed Bonab, Sheikh Muhammad Sarwar, Razieh Rahimi, James Allan

摘要:

预先训练的上下文表示为许多下游任务提供了巨大的成功,包括文档排序。这种预训练表示的多语言版本提供了使用同一模型联合学习多种语言的可能性。虽然预计通过这种联合训练可以获得很大的收益,但在跨语言信息检索(CLIR)的情况下,多语言环境下的模型并没有达到与单语言环境下相同的性能水平。我们假设性能下降是由于查询和文档之间的翻译差距。在单语检索任务中,由于词汇输入相同,模型更容易识别出出现在文档中的查询词。然而,在将不同语言的单词投影到同一超空间的多语言预训练模型中,模型倾向于将查询词转换为相关词,即,出现在相似上下文中的术语,除了或有时不是目标语言中的同义词。这个属性给模型连接查询和文档中同时出现的术语带来了困难。为了解决这个问题,我们提出了一种新的混合注意力Transformer(MAT),它结合了外部的字级知识,如字典或翻译表。我们设计了一个三明治式的架构,将MAT嵌入到最近基于Transformer的深度神经模型中。通过将翻译知识编码成注意力矩阵,具有MAT的模型能够关注输入序列中的互译词。实验结果表明,外部知识的有效性和MAT嵌入的神经重排序模型的CLIR任务的显着改善。

英文摘要:

Pretrained contextualized representations offer great success for many downstream tasks, including document ranking. The multilingual versions of such pretrained representations provide a possibility of jointly learning many languages with the same model. Although it is expected to gain big with such joint training, in the case of cross lingual information retrieval (CLIR), the models under a multilingual setting are not achieving the same level of performance as those under a monolingual setting. We hypothesize that the performance drop is due to the translation gap between query and documents. In the monolingual retrieval task, because of the same lexical inputs, it is easier for model to identify the query terms that occurred in documents. However, in the multilingual pretrained models that the words in different languages are projected into the same hyperspace, the model tends to translate query terms into related terms, i.e., terms that appear in a similar context, in addition to or sometimes rather than synonyms in the target language. This property is creating difficulties for the model to connect terms that cooccur in both query and document. To address this issue, we propose a novel Mixed Attention Transformer (MAT) that incorporates external word level knowledge, such as a dictionary or translation table. We design a sandwich like architecture to embed MAT into the recent transformer based deep neural models. By encoding the translation knowledge into an attention matrix, the model with MAT is able to focus on the mutually translated words in the input sequence. Experimental results demonstrate the effectiveness of the external knowledge and the significant improvement of MAT embedded neural reranking model on CLIR task.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑