Enhance Word Representation for Out-of-Vocabulary on Ubuntu Dialogue Corpus

JIANXIONG DONG, Jim Huang

Abstract:

Ubuntu dialogue corpus is the largest public available dialogue corpus to make it feasible to build end-to-end
deep neural network models directly from the conversation data. One challenge of Ubuntu dialogue corpus is
the large number of out-of-vocabulary words. In this paper we proposed an algorithm which combines the general pre-trained word embedding vectors with those generated on the task-specific training set to address this issue. We integrated character embedding into Chen et al's Enhanced LSTM method (ESIM) and used it to evaluate the effectiveness of our proposed method. For the task of next utterance selection, the proposed method has demonstrated a significant performance improvement against original ESIM and the new model has achieved state-of-the-art results on both Ubuntu dialogue corpus and Douban conversation corpus. In addition, we investigated the performance impact of end-of-utterance and end-of-turn token tags.

TL;DR: Combine information between pre-built word embedding and task-specific word representation to address out-of-vocabulary issue

Keywords: next utterance selection, ubuntu dialogue corpus, out-of-vocabulary, word representation

Code: [ jdongca2003/next_utterance_selection](https://github.com/jdongca2003/next_utterance_selection)

Data: [ConceptNet](https://paperswithcode.com/dataset/conceptnet), [Douban](https://paperswithcode.com/dataset/douban), [Douban Conversation Corpus](https://paperswithcode.com/dataset/douban-conversation-corpus), [WikiQA](https://paperswithcode.com/dataset/wikiqa)

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:1802.02614/code)