Targeted aspect-based sentiment analysis via embedding commonsense knowledge into an attentive LSTM

Y Ma, H Peng, E Cambria - Proceedings of the AAAI conference on …, 2018 - ojs.aaai.org
Analyzing people's opinions and sentiments towards certain aspects is an important task of
natural language understanding. In this paper, we propose a novel solution to targeted …

A deep look into neural ranking models for information retrieval

J Guo, Y Fan, L Pang, L Yang, Q Ai, H Zamani… - Information Processing …, 2020 - Elsevier
Ranking models lie at the heart of research on information retrieval (IR). During the past
decades, different techniques have been proposed for constructing ranking models, from …

Adversarial learning for neural dialogue generation

J Li, W Monroe, T Shi, S Jean, A Ritter… - arXiv preprint arXiv …, 2017 - arxiv.org
In this paper, drawing intuition from the Turing test, we propose using adversarial training for
open-domain dialogue generation: the system is trained to produce sequences that are …

Deep reinforcement learning for dialogue generation

J Li, W Monroe, A Ritter, M Galley, J Gao… - arXiv preprint arXiv …, 2016 - arxiv.org
Recent neural models of dialogue generation offer great promise for generating responses
for conversational agents, but tend to be shortsighted, predicting utterances one at a time …

Sequential matching network: A new architecture for multi-turn response selection in retrieval-based chatbots

Y Wu, W Wu, C Xing, M Zhou, Z Li - arXiv preprint arXiv:1612.01627, 2016 - arxiv.org
We study response selection for multi-turn conversation in retrieval-based chatbots. Existing
work either concatenates utterances in context or matches a response with a highly abstract …

Sentic LSTM: a hybrid network for targeted aspect-based sentiment analysis

Y Ma, H Peng, T Khan, E Cambria, A Hussain - Cognitive Computation, 2018 - Springer
Sentiment analysis has emerged as one of the most popular natural language processing
(NLP) tasks in recent years. A classic setting of the task mainly involves classifying the …

Commonsense for generative multi-hop question answering tasks

L Bauer, Y Wang, M Bansal - arXiv preprint arXiv:1809.06309, 2018 - arxiv.org
Reading comprehension QA tasks have seen a recent surge in popularity, yet most works
have focused on fact-finding extractive QA. We instead focus on a more challenging multi …

Speaker-aware BERT for multi-turn response selection in retrieval-based chatbots

JC Gu, T Li, Q Liu, ZH Ling, Z Su, S Wei… - Proceedings of the 29th …, 2020 - dl.acm.org
In this paper, we study the problem of employing pre-trained language models for multi-turn
response selection in retrieval-based chatbots. A new model, named Speaker-Aware BERT …

Grounded conversation generation as guided traverses in commonsense knowledge graphs

H Zhang, Z Liu, C Xiong, Z Liu - arXiv preprint arXiv:1911.02707, 2019 - arxiv.org
Human conversations naturally evolve around related concepts and scatter to multi-hop
concepts. This paper presents a new conversation generation model, ConceptFlow, which …

One time of interaction may not be enough: Go deep with an interaction-over-interaction network for response selection in dialogues

C Tao, W Wu, C Xu, W Hu, D Zhao… - Proceedings of the 57th …, 2019 - aclanthology.org
Currently, researchers have paid great attention to retrieval-based dialogues in open-
domain. In particular, people study the problem by investigating context-response matching …