Benchmarking Natural Language Understanding Services for building Conversational Agents

Code

• github.com/xliuhw/NLU-Evaluation-Data
  OfficialIn papernone★ 0
• github.com/PolyAI-LDN/task-specific-datasets
  none★ 163
• github.com/amazon-science/intent-aware-encoder
  pytorch★ 16
• github.com/lackel/hierarchical_weighted_scl
  pytorch★ 14
• github.com/lackel/sdc
  pytorch★ 9
• github.com/haodeqi/BenchmarkingIntentDetection
  none★ 3
• github.com/Lackel/DNA
  pytorch★ 1
• github.com/PolyAI-LDN/polyai-models
  tf★ 0
• github.com/RasaHQ/rasa
  none★ 0

Abstract

We have recently seen the emergence of several publicly available Natural Language Understanding (NLU) toolkits, which map user utterances to structured, but more abstract, Dialogue Act (DA) or Intent specifications, while making this process accessible to the lay developer. In this paper, we present the first wide coverage evaluation and comparison of some of the most popular NLU services, on a large, multi-domain (21 domains) dataset of 25K user utterances that we have collected and annotated with Intent and Entity Type specifications and which will be released as part of this submission. The results show that on Intent classification Watson significantly outperforms the other platforms, namely, Dialogflow, LUIS and Rasa; though these also perform well. Interestingly, on Entity Type recognition, Watson performs significantly worse due to its low Precision. Again, Dialogflow, LUIS and Rasa perform well on this task.

Tasks

Reproductions