arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2212.00301cs.CL
收藏

学习从多个选项中进行选择

Learning to Select from Multiple Options

University of Illinois at Chicago(伊利诺伊大学芝加哥分校);Penn State University(宾夕法尼亚州立大学);Salesforce Research(Salesforce研究院)

Jiangshu Du, Wenpeng Yin, Congying Xia, Philip S. Yu

AI总结:

针对文本蕴含(TE)成对建模无法感知其他选项且推理耗时的问题,提出Context-TE和Parallel-TE模型,通过引入上下文和并行决策提升选择性能与速度,在多项任务上达到SOTA。

摘要:

许多NLP任务可以被视为从一组选项中进行选择的问题,例如分类任务、多选题问答等。文本蕴含(TE)已被证明是处理这些选择问题的最先进(SOTA)方法。TE将输入文本视为前提(P),选项视为假设(H),然后通过对(P, H)进行成对建模来处理选择问题。这存在两个局限性:首先,成对建模不知道其他选项,这不太直观,因为人类通常通过比较竞争候选者来确定最佳选项;其次,成对TE的推理过程很耗时,尤其是当选项空间很大时。为了解决这两个问题,这项工作首先提出了一个上下文化TE模型(Context-TE),通过将其他k个选项作为当前(P, H)建模的上下文附加进去。Context-TE能够为H学习更可靠的决策,因为它考虑了各种上下文。其次,我们通过提出Parallel-TE来加速Context-TE,该模型同时学习多个选项的决策。Parallel-TE在保持与Context-TE相当的性能的同时,显著提高了推理速度。我们的方法在三个任务(超细实体类型化、意图检测和多选题问答)上进行了评估,这些任务都是具有不同选项数量的典型选择问题。实验表明我们的模型设定了新的SOTA性能;特别是,Parallel-TE在推理上比成对TE快k倍。我们的代码已在 https://github.com/jiangshdd/LearningToSelect 公开。

英文摘要:

Many NLP tasks can be regarded as a selection problem from a set of options, such as classification tasks, multi-choice question answering, etc. Textual entailment (TE) has been shown as the state-of-the-art (SOTA) approach to dealing with those selection problems. TE treats input texts as premises (P), options as hypotheses (H), then handles the selection problem by modeling (P, H) pairwise. Two limitations: first, the pairwise modeling is unaware of other options, which is less intuitive since humans often determine the best options by comparing competing candidates; second, the inference process of pairwise TE is time-consuming, especially when the option space is large. To deal with the two issues, this work first proposes a contextualized TE model (Context-TE) by appending other k options as the context of the current (P, H) modeling. Context-TE is able to learn more reliable decision for the H since it considers various context. Second, we speed up Context-TE by coming up with Parallel-TE, which learns the decisions of multiple options simultaneously. Parallel-TE significantly improves the inference speed while keeping comparable performance with Context-TE. Our methods are evaluated on three tasks (ultra-fine entity typing, intent detection and multi-choice QA) that are typical selection problems with different sizes of options. Experiments show our models set new SOTA performance; particularly, Parallel-TE is faster than the pairwise TE by k times in inference. Our code is publicly available at https://github.com/jiangshdd/LearningToSelect.

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。

↑