arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.13829cs.CLcs.AIcs.LG
收藏

通过多通道统一记忆生成答案

Answer Generation through Unified Memories over Multiple Passages

NTT Resonant Inc.(NTT Resonant公司)

Makoto Nakatsuji, Sohei Okui

摘要:

机器阅读理解方法通过引用问题的多个段落来生成答案,在AI和NLP社区中受到了广泛关注。然而,当前的方法在答案生成过程中不调查多个段落之间的关系,即使段落之间相关的主题可能是答案候选。我们的方法,称为神经答案生成通过统一的记忆在多个通道(GUM-MP),解决这个问题如下。首先,它确定段落中的哪些标记与问题相匹配。特别是,它调查了积极段落中的标记之间的匹配,这些标记被分配给问题,而消极段落中的标记与问题无关。接下来,它确定段落中的哪些标记与分配给同一问题的其他段落相匹配,同时调查它们匹配的主题。最后,将上述两种匹配结果的令牌序列编码到通道编码器中的统一存储器中,并使用具有多指针生成器机制的编码器-解码器学习答案序列。因此,GUM-MP可以通过指向跨段落出现的重要标记来生成答案。评估表明,GUM-MP产生更准确的结果比目前的模型。

英文摘要:

Machine reading comprehension methods that generate answers by referring to multiple passages for a question have gained much attention in AI and NLP communities. The current methods, however, do not investigate the relationships among multiple passages in the answer generation process, even though topics correlated among the passages may be answer candidates. Our method, called neural answer Generation through Unified Memories over Multiple Passages (GUM-MP), solves this problem as follows. First, it determines which tokens in the passages are matched to the question. In particular, it investigates matches between tokens in positive passages, which are assigned to the question, and those in negative passages, which are not related to the question. Next, it determines which tokens in the passage are matched to other passages assigned to the same question and at the same time it investigates the topics in which they are matched. Finally, it encodes the token sequences with the above two matching results into unified memories in the passage encoders and learns the answer sequence by using an encoder-decoder with a multiple-pointer-generator mechanism. As a result, GUM-MP can generate answers by pointing to important tokens present across passages. Evaluations indicate that GUM-MP generates much more accurate results than the current models do.

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。

↑