=Paper=
{{Paper
|id=Vol-2456/paper91
|storemode=property
|title=Using Event Graph to Improve Question Answering in E-commerce Customer Service
|pdfUrl=https://ceur-ws.org/Vol-2456/paper91.pdf
|volume=Vol-2456
|authors=Feng-Lin Li,Kehan Chen,Yan Wan,Weijia Chen,Qi Huang,Yikun Guo
|dblpUrl=https://dblp.org/rec/conf/semweb/LiCWCHG19
}}
==Using Event Graph to Improve Question Answering in E-commerce Customer Service==
https://ceur-ws.org/Vol-2456/paper91.pdf
Using Event Graph to Improve Question Answering in
E-commerce Customer Service⋆
Feng-Lin Li, Kehan Chen, Yan wan, Weijia Chen, Qi Huang, Yikun Guo
Alibaba Group.
Hangzhou, China, 311100
{fenglin.lfl, yikun.gyk}@alibaba-inc.com
Abstract. AliMe is an intelligent assistant that offers question answering service
in the E-commerce customer service field. By representing knowledge as question
answer (QA) pairs, AliMe is able to serve millions of customer questions per day
and address 90%+ of them. However, in regulation-oriented scenarios, questions
of type “why”, “whether”, “what if ” and “how next” often require knowledge
reasoning to obtain a specific or precise answer, and QA-style knowledge repre-
sentation turns out to be insufficient. To enable AliMe to better understand and
serve customer questions, we propose to represent regulation knowledge as event
graph, design systematic approach to map customer questions to events, and per-
form reasoning on event graph according to business rules. We launch our new
system in the “counterfeiting penalty” scenario. Online results suggest that our
new approach is able to gain better resolution.
Keywords: Event Graph · Explainable Question Answering · Knowledge Rea-
soning
1 Introduction
We have been working on enabling AliMe to better understand customer questions for
years. The treatment of knowledge as QA pairs has allowed us to employ many kinds
of state-of-the-art deep learning techniques and achieve substantial progress in the E-
commerce customer service field. However, it also has several deficiencies, an important
one of that is the lacking of knowledge reasoning ability (a precise answer and its justi-
fication need to be specified, e.g., for a given question “售假处罚会影响商品发布吗？
Can I still release commodities if penalized for counterfeiting?”, we need to precisely re-
ply with “yes” or “no” and explain why). To address the challenge in regulation-oriented
scenarios, we propose to represent knowledge as event graph, and accordingly design a
systematic two-stage approach.
2 Event Graph Solutions
Event Graph. We define an ontology for event graph as in Fig 1(a) and show an ex-
cerpt of counterfeiting penalty event graph in Fig 1(b). In general, events can be clas-
sified into two classes: state-oriented and operation-oriented. The former describes a
⋆
Copyright © 2019 for this paper by its authors. Use permitted under Creative Commons License
Attribution 4.0 International (CC BY 4.0).
2 F-L. Li et al.
phenomenon or a situation of a real-world entity (e.g, deposit is “frozen”), and the lat-
ter indicates a function to be performed on an entity (e.g., “defreeze” deposit). Further,
an event could have properties such as “subject”, “object” and “trigger”. Note that the
properties of state-oriented events differ from those of operation-oriented ones in the
following aspect: for a state, customers often wonder why a certain situation is brought
about (“reason”, e.g., “Why I can not release commodities?”) or what to do under a
certain situation (“sequential”, e.g., “What should I do if I was penalized for counter-
feiting?”); for operations, one tend to concern about its feasibility (“operation_whether”,
e.g., “Can I defreeze my deposit?”), process (“operation_how”, e.g., “How to defreeze
my deposit?”) and result (“cause”, e.g., “What will happen if I appeal?”). To help judging
whether an operation can be performed, we adopt Compound Value Type (CVT) from
Freebase to capture multi-condition for an operation event. The adoption of CVT allows
us to explain why an operation is allowed or forbidden by checking specific conditions
(e.g., “appeal” is allowed when the “penality state” is in progress).
)
Condition-X Condition-Y
( ) )
Fig. 1. Event graph: ontology and example
Matching and Reasoning. We decompose the question answering process over
event graph into two stages: matching and reasoning. At the first stage, we employ deep
learning techniques to identify events, classify properties and recognize conditions. At
the second stage, we construct query graphs based on the foundational event graph and
according to business strategies (e.g., if customers ask about the influence of “counter-
feiting penalty”, we need to enumerate its neighbors within two hops along the “cause”
relation), and query the knowledge base to get the answer.
We apply our approach in the “counterfeiting penalty” scenario and gain an absolute
15% increase of resolution in our A/B test. We will test in more scenarios.
3 Conclusion
Capturing regulation knowledge as event graph rather than QA pairs enables us to con-
duct reasoning and precisely answer customer questions of type “why”, “whether”,
“what if”, “how next”, etc. Moreover, with CVT, event graph enables us to explain
the result of customer questions, gain better resolution and improve user satisfaction.