How to Do Things With Words

https://bura.brunel.ac.uk/bitstream/2438/14221/1/FullText.pdf

A survey of deep neural network architectures and their applications

A survey on deep learning for big data

We present Meena, a multi-turn open-domain chatbot trained end-to-end on data mined and filtered from public domain social media conversations. This 2.6B parameter neural network is simply trained to minimize perplexity of the next token. We also propose a human evaluation metric called Sensibleness and Specificity Average (SSA), which captures key elements of a human-like multi-turn conversation. Our experiments show strong correlation between perplexity and SSA. The fact that the best perplexity end-to-end trained Meena scores high on SSA (72% on multi-turn evaluation) suggests that a human-level SSA of 86% is potentially within reach if we can better optimize perplexity. Additionally, the full version of Meena (with a filtering mechanism and tuned decoding) scores 79% SSA, 23% higher in absolute SSA than the existing chatbots we evaluated.

Towards a Human-like Open-Domain Chatbot

While recent neural encoder-decoder models have shown great promise in modeling open-domain conversations, they often generate dull and generic responses. Unlike past work that has focused on diversifying the output of the decoder from word-level to alleviate this problem, we present a novel framework based on conditional variational autoencoders that capture the discourse-level diversity in the encoder. Our model uses latent variables to learn a distribution over potential conversational intents and generates diverse responses using only greedy decoders. We have further developed a novel variant that is integrated with linguistic prior knowledge for better performance. Finally, the training procedure is improved through introducing a bag-of-word loss. Our proposed models have been validated to generate significantly more diverse responses than baseline approaches and exhibit competence of discourse-level decision-making.

/pdf/learning-discourse-level-diversity-for-neural-dialog-models-32tzmp5oto.pdf

Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders

We consider incorporating topic information into a sequence-to-sequence framework to generate informative and interesting responses for chatbots. To this end, we propose a topic aware sequence-to-sequence (TA-Seq2Seq) model. The model utilizes topics to simulate prior human knowledge that guides them to form informative and interesting responses in conversation, and leverages topic information in generation by a joint attention mechanism and a biased generation probability. The joint attention mechanism summarizes the hidden vectors of an input message as context vectors by message attention and synthesizes topic vectors by topic attention from the topic words of the message obtained from a pre-trained LDA model, with these vectors jointly affecting the generation of words in decoding. To increase the possibility of topic words appearing in responses, the model modifies the generation probability of topic words by adding an extra probability item to bias the overall distribution. Empirical studies on both automatic evaluation metrics and human annotations show that TA-Seq2Seq can generate more informative and interesting responses, significantly outperforming state-of-the-art response generation models.

/pdf/topic-aware-neural-response-generation-4pv5ctv4x8.pdf

Topic Aware Neural Response Generation

We consider incorporating topic information as prior knowledge into the sequence to sequence (Seq2Seq) network structure with attention mechanism for response generation in chatbots. To this end, we propose a topic augmented joint attention based Seq2Seq (TAJA-Seq2Seq) model. In TAJA-Seq2Seq, information from input posts and information from topics related to the posts are simultaneously embedded into vector spaces by a content encoder and a topic encoder respectively. The two kinds of information interact with each other and help calibrate weights of each other in the joint attention mechanism in TAJA2Seq2Seq, and jointly determine the generation of responses in decoding. The model simulates how people behave in conversation and can generate well-focused and informative responses with the help of topic information. Empirical study on large scale human judged generation results show that our model outperforms Seq2Seq with attention on both response quality and diversity.

Topic Augmented Neural Response Generation with a Joint Attention Mechanism.

Mining topics in Twitter is increasingly attracting more attention. However, the shortness and informality of tweets leads to extreme sparse vector representation with a large vocabulary, which makes the conventional topic models (e.g., Latent Dirichlet Allocation) often fail to achieve high quality underlying topics. Luckily, tweets always show up with rich user-generated hash tags as keywords. In this paper, we propose a novel topic model to handle such semi-structured tweets, denoted as Hash tag Graph based Topic Model (HGTM). By utilizing relation information between hash tags in our hash tag graph, HGTMestablishes word semantic relations, even if they haven't co-occurred within a specific tweet. In addition, we enhance the dependencies of both multiple words and hash tags via latent variables (topics) modeled by HGTM. We illustrate that the user-contributed hash tags could serve as weakly-supervised information for topic modeling, and hash tag relation could reveal the semantic relation between tweets. Experiments on a real-world twitter data set show that our model provides an effective solution to discover more distinct and coherent topics than the state-of-the-art baselines and has a strong ability to control sparseness and noise in tweets.

Hashtag Graph Based Topic Model for Tweet Mining

Opinion entity extraction is a fundamental task in fine-grained opinion mining. Related studies generally extract aspects and/or opinion expressions without recognizing the relations between them. However, the relations are crucial for downstream tasks, including sentiment classification, opinion summarization, etc. In this paper, we explore Aspect-Opinion Pair Extraction (AOPE) task, which aims at extracting aspects and opinion expressions in pairs. To deal with this task, we propose Synchronous Double-channel Recurrent Network (SDRN) mainly consisting of an opinion entity extraction unit, a relation detection unit, and a synchronization unit. The opinion entity extraction unit and the relation detection unit are developed as two channels to extract opinion entities and relations simultaneously. Furthermore, within the synchronization unit, we design Entity Synchronization Mechanism (ESM) and Relation Synchronization Mechanism (RSM) to enhance the mutual benefit on the above two channels. To verify the performance of SDRN, we manually build three datasets based on SemEval 2014 and 2015 benchmarks. Extensive experiments demonstrate that SDRN achieves state-of-the-art performances.

/pdf/synchronous-double-channel-recurrent-network-for-aspect-5al0fmhgq9.pdf

Synchronous Double-channel Recurrent Network for Aspect-Opinion Pair Extraction.

In this paper, we introduce a new topic model to understand the chaotic microblogging environment by using hashtag graphs. Inferring topics on Twitter becomes a vital but challenging task in many important applications. The shortness and informality of tweets leads to extreme sparse vector representations with a large vocabulary. This makes the conventional topic models (e.g., latent Dirichlet allocation [1] and latent semantic analysis [2] ) fail to learn high quality topic structures. Tweets are always showing up with rich user-generated hashtags. The hashtags make tweets semi-structured inside and semantically related to each other. Since hashtags are utilized as keywords in tweets to mark messages or to form conversations, they provide an additional path to connect semantically related words. In this paper, treating tweets as semi-structured texts, we propose a novel topic model, denoted as Hashtag Graph-based Topic Model ( HGTM ) to discover topics of tweets. By utilizing hashtag relation information in hashtag graphs, HGTM is able to discover word semantic relations even if words are not co-occurred within a specific tweet. With this method, HGTM successfully alleviates the sparsity problem. Our investigation illustrates that the user-contributed hashtags could serve as weakly-supervised information for topic modeling, and the relation between hashtags could reveal latent semantic relation between words. We evaluate the effectiveness of HGTM on tweet (hashtag) clustering and hashtag classification problems. Experiments on two real-world tweet data sets show that HGTM has strong capability to handle sparseness and noise problem in tweets. Furthermore, HGTM can discover more distinct and coherent topics than the state-of-the-art baselines.

Jie Liu

Papers

Topic Aware Neural Response Generation

Topic Augmented Neural Response Generation with a Joint Attention Mechanism.

Hashtag Graph Based Topic Model for Tweet Mining

Synchronous Double-channel Recurrent Network for Aspect-Opinion Pair Extraction.

Using Hashtag Graph-Based Topic Model to Connect Semantically-Related Words Without Co-Occurrence in Microblogs